High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes an...High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes and wealth of spatial details pose challenges for semantic segmentation.While convolutional neural networks(CNNs)excel at capturing local features,they are limited in modeling long-range dependencies.Conversely,transformers utilize multihead self-attention to integrate global context effectively,but this approach often incurs a high computational cost.This paper proposes a global-local multiscale context network(GLMCNet)to extract both global and local multiscale contextual information from HRSIs.A detail-enhanced filtering module(DEFM)is proposed at the end of the encoder to refine the encoder outputs further,thereby enhancing the key details extracted by the encoder and effectively suppressing redundant information.In addition,a global-local multiscale transformer block(GLMTB)is proposed in the decoding stage to enable the modeling of rich multiscale global and local information.We also design a stair fusion mechanism to transmit deep semantic information from deep to shallow layers progressively.Finally,we propose the semantic awareness enhancement module(SAEM),which further enhances the representation of multiscale semantic features through spatial attention and covariance channel attention.Extensive ablation analyses and comparative experiments were conducted to evaluate the performance of the proposed method.Specifically,our method achieved a mean Intersection over Union(mIoU)of 86.89%on the ISPRS Potsdam dataset and 84.34%on the ISPRS Vaihingen dataset,outperforming existing models such as ABCNet and BANet.展开更多
Advanced traffic monitoring systems encounter substantial challenges in vehicle detection and classification due to the limitations of conventional methods,which often demand extensive computational resources and stru...Advanced traffic monitoring systems encounter substantial challenges in vehicle detection and classification due to the limitations of conventional methods,which often demand extensive computational resources and struggle with diverse data acquisition techniques.This research presents a novel approach for vehicle classification and recognition in aerial image sequences,integrating multiple advanced techniques to enhance detection accuracy.The proposed model begins with preprocessing using Multiscale Retinex(MSR)to enhance image quality,followed by Expectation-Maximization(EM)Segmentation for precise foreground object identification.Vehicle detection is performed using the state-of-the-art YOLOv10 framework,while feature extraction incorporates Maximally Stable Extremal Regions(MSER),Dense Scale-Invariant Feature Transform(Dense SIFT),and Zernike Moments Features to capture distinct object characteristics.Feature optimization is further refined through a Hybrid Swarm-based Optimization algorithm,ensuring optimal feature selection for improved classification performance.The final classification is conducted using a Vision Transformer,leveraging its robust learning capabilities for enhanced accuracy.Experimental evaluations on benchmark datasets,including UAVDT and the Unmanned Aerial Vehicle Intruder Dataset(UAVID),demonstrate the superiority of the proposed approach,achieving an accuracy of 94.40%on UAVDT and 93.57%on UAVID.The results highlight the efficacy of the model in significantly enhancing vehicle detection and classification in aerial imagery,outperforming existing methodologies and offering a statistically validated improvement for intelligent traffic monitoring systems compared to existing approaches.展开更多
This systematic review aims to comprehensively examine and compare deep learning methods for brain tumor segmentation and classification using MRI and other imaging modalities,focusing on recent trends from 2022 to 20...This systematic review aims to comprehensively examine and compare deep learning methods for brain tumor segmentation and classification using MRI and other imaging modalities,focusing on recent trends from 2022 to 2025.The primary objective is to evaluate methodological advancements,model performance,dataset usage,and existing challenges in developing clinically robust AI systems.We included peer-reviewed journal articles and highimpact conference papers published between 2022 and 2025,written in English,that proposed or evaluated deep learning methods for brain tumor segmentation and/or classification.Excluded were non-open-access publications,books,and non-English articles.A structured search was conducted across Scopus,Google Scholar,Wiley,and Taylor&Francis,with the last search performed in August 2025.Risk of bias was not formally quantified but considered during full-text screening based on dataset diversity,validation methods,and availability of performance metrics.We used narrative synthesis and tabular benchmarking to compare performance metrics(e.g.,accuracy,Dice score)across model types(CNN,Transformer,Hybrid),imaging modalities,and datasets.A total of 49 studies were included(43 journal articles and 6 conference papers).These studies spanned over 9 public datasets(e.g.,BraTS,Figshare,REMBRANDT,MOLAB)and utilized a range of imaging modalities,predominantly MRI.Hybrid models,especially ResViT and UNetFormer,consistently achieved high performance,with classification accuracy exceeding 98%and segmentation Dice scores above 0.90 across multiple studies.Transformers and hybrid architectures showed increasing adoption post2023.Many studies lacked external validation and were evaluated only on a few benchmark datasets,raising concerns about generalizability and dataset bias.Few studies addressed clinical interpretability or uncertainty quantification.Despite promising results,particularly for hybrid deep learning models,widespread clinical adoption remains limited due to lack of validation,interpretability concerns,and real-world deployment barriers.展开更多
Brain tumors require precise segmentation for diagnosis and treatment plans due to their complex morphology and heterogeneous characteristics.While MRI-based automatic brain tumor segmentation technology reduces the b...Brain tumors require precise segmentation for diagnosis and treatment plans due to their complex morphology and heterogeneous characteristics.While MRI-based automatic brain tumor segmentation technology reduces the burden on medical staff and provides quantitative information,existing methodologies and recent models still struggle to accurately capture and classify the fine boundaries and diverse morphologies of tumors.In order to address these challenges and maximize the performance of brain tumor segmentation,this research introduces a novel SwinUNETR-based model by integrating a new decoder block,the Hierarchical Channel-wise Attention Decoder(HCAD),into a powerful SwinUNETR encoder.The HCAD decoder block utilizes hierarchical features and channelspecific attention mechanisms to further fuse information at different scales transmitted from the encoder and preserve spatial details throughout the reconstruction phase.Rigorous evaluations on the recent BraTS GLI datasets demonstrate that the proposed SwinHCAD model achieved superior and improved segmentation accuracy on both the Dice score and HD95 metrics across all tumor subregions(WT,TC,and ET)compared to baseline models.In particular,the rationale and contribution of the model design were clarified through ablation studies to verify the effectiveness of the proposed HCAD decoder block.The results of this study are expected to greatly contribute to enhancing the efficiency of clinical diagnosis and treatment planning by increasing the precision of automated brain tumor segmentation.展开更多
Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone t...Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.展开更多
Mixture model based image segmentation method, which assumes that image pixels are independent and do not consider the position relationship between pixels, is not robust to noise and usually leads to misclassificatio...Mixture model based image segmentation method, which assumes that image pixels are independent and do not consider the position relationship between pixels, is not robust to noise and usually leads to misclassification. A new segmentation method, called multi-resolution Ganssian mixture model method, is proposed. First, an image pyramid is constructed and son-father link relationship is built between each level of pyramid. Then the mixture model segmentation method is applied to the top level. The segmentation result on the top level is passed top-down to the bottom level according to the son-father link relationship between levels. The proposed method considers not only local but also global information of image, it overcomes the effect of noise and can obtain better segmentation result. Experimental result demonstrates its effectiveness.展开更多
To solve the problem that the magnetic resonance(MR)image has weak boundaries,large amount of information,and low signal-to-noise ratio,we propose an image segmentation method based on the multi-resolution Markov rand...To solve the problem that the magnetic resonance(MR)image has weak boundaries,large amount of information,and low signal-to-noise ratio,we propose an image segmentation method based on the multi-resolution Markov random field(MRMRF)model.The algorithm uses undecimated dual-tree complex wavelet transformation to transform the image into multiple scales.The transformed low-frequency scale histogram is used to improve the initial clustering center of the K-means algorithm,and then other cluster centers are selected according to the maximum distance rule to obtain the coarse-scale segmentation.The results are then segmented by the improved MRMRF model.In order to solve the problem of fuzzy edge segmentation caused by the gray level inhomogeneity of MR image segmentation under the MRMRF model,it is proposed to introduce variable weight parameters in the segmentation process of each scale.Furthermore,the final segmentation results are optimized.We name this algorithm the variable-weight multi-resolution Markov random field(VWMRMRF).The simulation and clinical MR image segmentation verification show that the VWMRMRF algorithm has high segmentation accuracy and robustness,and can accurately and stably achieve low signal-to-noise ratio,weak boundary MR image segmentation.展开更多
In order to effectively improve the pathological diagnosis capability and feature resolution of 3D human brain CT images,a threshold segmentation method of multi-resolution 3D human brain CT image based on edge pixel ...In order to effectively improve the pathological diagnosis capability and feature resolution of 3D human brain CT images,a threshold segmentation method of multi-resolution 3D human brain CT image based on edge pixel grayscale feature decomposition is proposed in this paper.In this method,first,original 3D human brain image information is collected,and CT image filtering is performed to the collected information through the gradient value decomposition method,and edge contour features of the 3D human brain CT image are extracted.Then,the threshold segmentation method is adopted to segment the regional pixel feature block of the 3D human brain CT image to segment the image into block vectors with high-resolution feature points,and the 3D human brain CT image is reconstructed with the salient feature point as center.Simulation results show that the method proposed in this paper can provide accuracy up to 100%when the signal-to-noise ratio is 0,and with the increase of signal-to-noise ratio,the accuracy provided by this method is stable at 100%.Comparison results show that the threshold segmentation method of multi-resolution 3D human brain CT image based on edge pixel grayscale feature decomposition is signicantly better than traditional methods in pathological feature estimation accuracy,and it effectively improves the rapid pathological diagnosis and positioning recognition abilities to CT images.展开更多
The Internet of Vehicles (IoV) has become an important direction in the field of intelligent transportation, in which vehicle positioning is a crucial part. SLAM (Simultaneous Localization and Mapping) technology play...The Internet of Vehicles (IoV) has become an important direction in the field of intelligent transportation, in which vehicle positioning is a crucial part. SLAM (Simultaneous Localization and Mapping) technology plays a crucial role in vehicle localization and navigation. Traditional Simultaneous Localization and Mapping (SLAM) systems are designed for use in static environments, and they can result in poor performance in terms of accuracy and robustness when used in dynamic environments where objects are in constant movement. To address this issue, a new real-time visual SLAM system called MG-SLAM has been developed. Based on ORB-SLAM2, MG-SLAM incorporates a dynamic target detection process that enables the detection of both known and unknown moving objects. In this process, a separate semantic segmentation thread is required to segment dynamic target instances, and the Mask R-CNN algorithm is applied on the Graphics Processing Unit (GPU) to accelerate segmentation. To reduce computational cost, only key frames are segmented to identify known dynamic objects. Additionally, a multi-view geometry method is adopted to detect unknown moving objects. The results demonstrate that MG-SLAM achieves higher precision, with an improvement from 0.2730 m to 0.0135 m in precision. Moreover, the processing time required by MG-SLAM is significantly reduced compared to other dynamic scene SLAM algorithms, which illustrates its efficacy in locating objects in dynamic scenes.展开更多
To avoid the laborious annotation process for dense prediction tasks like semantic segmentation,unsupervised domain adaptation(UDA)methods have been proposed to leverage the abundant annotations from a source domain,s...To avoid the laborious annotation process for dense prediction tasks like semantic segmentation,unsupervised domain adaptation(UDA)methods have been proposed to leverage the abundant annotations from a source domain,such as virtual world(e.g.,3D games),and adapt models to the target domain(the real world)by narrowing the domain discrepancies.However,because of the large domain gap,directly aligning two distinct domains without considering the intermediates leads to inefficient alignment and inferior adaptation.To address this issue,we propose a novel learnable evolutionary Category Intermediates(CIs)guided UDA model named Leci,which enables the information transfer between the two domains via two processes,i.e.,Distilling and Blending.Starting from a random initialization,the CIs learn shared category-wise semantics automatically from two domains in the Distilling process.Then,the learned semantics in the CIs are sent back to blend the domain features through a residual attentive fusion(RAF)module,such that the categorywise features of both domains shift towards each other.As the CIs progressively and consistently learn from the varying feature distributions during training,they are evolutionary to guide the model to achieve category-wise feature alignment.Experiments on both GTA5 and SYNTHIA datasets demonstrate Leci's superiority over prior representative methods.展开更多
Image segmentation is attracting increasing attention in the field of medical image analysis.Since widespread utilization across various medical applications,ensuring and improving segmentation accuracy has become a c...Image segmentation is attracting increasing attention in the field of medical image analysis.Since widespread utilization across various medical applications,ensuring and improving segmentation accuracy has become a crucial topic of research.With advances in deep learning,researchers have developed numerous methods that combine Transformers and convolutional neural networks(CNNs)to create highly accurate models for medical image segmentation.However,efforts to further enhance accuracy by developing larger and more complex models or training with more extensive datasets,significantly increase computational resource consumption.To address this problem,we propose BiCLIP-nnFormer(the prefix"Bi"refers to the use of two distinct CLIP models),a virtual multimodal instrument that leverages CLIP models to enhance the segmentation performance of a medical segmentation model nnFormer.Since two CLIP models(PMC-CLIP and CoCa-CLIP)are pre-trained on large datasets,they do not require additional training,thus conserving computation resources.These models are used offline to extract image and text embeddings from medical images.These embeddings are then processed by the proposed 3D CLIP adapter,which adapts the CLIP knowledge for segmentation tasks by fine-tuning.Finally,the adapted embeddings are fused with feature maps extracted from the nnFormer encoder for generating predicted masks.This process enriches the representation capabilities of the feature maps by integrating global multimodal information,leading to more precise segmentation predictions.We demonstrate the superiority of BiCLIP-nnFormer and the effectiveness of using CLIP models to enhance nnFormer through experiments on two public datasets,namely the Synapse multi-organ segmentation dataset(Synapse)and the Automatic Cardiac Diagnosis Challenge dataset(ACDC),as well as a self-annotated lung multi-category segmentation dataset(LMCS).展开更多
Brain tumors present significant challenges in medical diagnosis and treatment,where early detection is crucial for reducing morbidity and mortality rates.This research introduces a novel deep learning model,the Progr...Brain tumors present significant challenges in medical diagnosis and treatment,where early detection is crucial for reducing morbidity and mortality rates.This research introduces a novel deep learning model,the Progressive Layered U-Net(PLU-Net),designed to improve brain tumor segmentation accuracy from Magnetic Resonance Imaging(MRI)scans.The PLU-Net extends the standard U-Net architecture by incorporating progressive layering,attention mechanisms,and multi-scale data augmentation.The progressive layering involves a cascaded structure that refines segmentation masks across multiple stages,allowing the model to capture features at different scales and resolutions.Attention gates within the convolutional layers selectively focus on relevant features while suppressing irrelevant ones,enhancing the model's ability to delineate tumor boundaries.Additionally,multi-scale data augmentation techniques increase the diversity of training data and boost the model's generalization capabilities.Evaluated on the BraTS 2021 dataset,the PLU-Net achieved state-of-the-art performance with a dice coefficient of 0.91,specificity of 0.92,sensitivity of 0.89,Hausdorff95 of 2.5,outperforming other modified U-Net architectures in segmentation accuracy.These results underscore the effectiveness of the PLU-Net in improving brain tumor segmentation from MRI scans,supporting clinicians in early diagnosis,treatment planning,and the development of new therapies.展开更多
Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution mismatch.However,current copy-paste methods have three limitations:(1)t...Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution mismatch.However,current copy-paste methods have three limitations:(1)training the model solely with copy-paste mixed pictures from labeled and unlabeled input loses a lot of labeled information;(2)low-quality pseudo-labels can cause confirmation bias in pseudo-supervised learning on unlabeled data;(3)the segmentation performance in low-contrast and local regions is less than optimal.We design a Stochastic Augmentation-Based Dual-Teaching Auxiliary Training Strategy(SADT),which enhances feature diversity and learns high-quality features to overcome these problems.To be more precise,SADT trains the Student Network by using pseudo-label-based training from Teacher Network 1 and supervised learning with labeled data,which prevents the loss of rare labeled data.We introduce a bi-directional copy-pastemask with progressive high-entropy filtering to reduce data distribution disparities and mitigate confirmation bias in pseudo-supervision.For the mixed images,Deep-Shallow Spatial Contrastive Learning(DSSCL)is proposed in the feature spaces of Teacher Network 2 and the Student Network to improve the segmentation capabilities in low-contrast and local areas.In this procedure,the features retrieved by the Student Network are subjected to a random feature perturbation technique.On two openly available datasets,extensive trials show that our proposed SADT performs much better than the state-ofthe-art semi-supervised medical segmentation techniques.Using only 10%of the labeled data for training,SADT was able to acquire a Dice score of 90.10%on the ACDC(Automatic Cardiac Diagnosis Challenge)dataset.展开更多
Convolutional neural networks(CNNs)-based medical image segmentation technologies have been widely used in medical image segmentation because of their strong representation and generalization abilities.However,due to ...Convolutional neural networks(CNNs)-based medical image segmentation technologies have been widely used in medical image segmentation because of their strong representation and generalization abilities.However,due to the inability to effectively capture global information from images,CNNs can easily lead to loss of contours and textures in segmentation results.Notice that the transformer model can effectively capture the properties of long-range dependencies in the image,and furthermore,combining the CNN and the transformer can effectively extract local details and global contextual features of the image.Motivated by this,we propose a multi-branch and multi-scale attention network(M2ANet)for medical image segmentation,whose architecture consists of three components.Specifically,in the first component,we construct an adaptive multi-branch patch module for parallel extraction of image features to reduce information loss caused by downsampling.In the second component,we apply residual block to the well-known convolutional block attention module to enhance the network’s ability to recognize important features of images and alleviate the phenomenon of gradient vanishing.In the third component,we design a multi-scale feature fusion module,in which we adopt adaptive average pooling and position encoding to enhance contextual features,and then multi-head attention is introduced to further enrich feature representation.Finally,we validate the effectiveness and feasibility of the proposed M2ANet method through comparative experiments on four benchmark medical image segmentation datasets,particularly in the context of preserving contours and textures.展开更多
Karst fractures serve as crucial seepage channels and storage spaces for carbonate natural gas reservoirs,and electrical image logs are vital data for visualizing and characterizing such fractures.However,the conventi...Karst fractures serve as crucial seepage channels and storage spaces for carbonate natural gas reservoirs,and electrical image logs are vital data for visualizing and characterizing such fractures.However,the conventional approach of identifying fractures using electrical image logs predominantly relies on manual processes that are not only time-consuming but also highly subjective.In addition,the heterogeneity and strong dissolution tendency of karst carbonate reservoirs lead to complexity and variety in fracture geometry,which makes it difficult to accurately identify fractures.In this paper,the electrical image logs network(EILnet)da deep-learning-based intelligent semantic segmentation model with a selective attention mechanism and selective feature fusion moduledwas created to enable the intelligent identification and segmentation of different types of fractures through electrical logging images.Data from electrical image logs representing structural and induced fractures were first selected using the sliding window technique before image inpainting and data augmentation were implemented for these images to improve the generalizability of the model.Various image-processing tools,including the bilateral filter,Laplace operator,and Gaussian low-pass filter,were also applied to the electrical logging images to generate a multi-attribute dataset to help the model learn the semantic features of the fractures.The results demonstrated that the EILnet model outperforms mainstream deep-learning semantic segmentation models,such as Fully Convolutional Networks(FCN-8s),U-Net,and SegNet,for both the single-channel dataset and the multi-attribute dataset.The EILnet provided significant advantages for the single-channel dataset,and its mean intersection over union(MIoU)and pixel accuracy(PA)were 81.32%and 89.37%,respectively.In the case of the multi-attribute dataset,the identification capability of all models improved to varying degrees,with the EILnet achieving the highest MIoU and PA of 83.43%and 91.11%,respectively.Further,applying the EILnet model to various blind wells demonstrated its ability to provide reliable fracture identification,thereby indicating its promising potential applications.展开更多
Convolutional neural network(CNN)with the encoder-decoder structure is popular in medical image segmentation due to its excellent local feature extraction ability but it faces limitations in capturing the global featu...Convolutional neural network(CNN)with the encoder-decoder structure is popular in medical image segmentation due to its excellent local feature extraction ability but it faces limitations in capturing the global feature.The transformer can extract the global information well but adapting it to small medical datasets is challenging and its computational complexity can be heavy.In this work,a serial and parallel network is proposed for the accurate 3D medical image segmentation by combining CNN and transformer and promoting feature interactions across various semantic levels.The core components of the proposed method include the cross window self-attention based transformer(CWST)and multi-scale local enhanced(MLE)modules.The CWST module enhances the global context understanding by partitioning 3D images into non-overlapping windows and calculating sparse global attention between windows.The MLE module selectively fuses features by computing the voxel attention between different branch features,and uses convolution to strengthen the dense local information.The experiments on the prostate,atrium,and pancreas MR/CT image datasets consistently demonstrate the advantage of the proposed method over six popular segmentation models in both qualitative evaluation and quantitative indexes such as dice similarity coefficient,Intersection over Union,95%Hausdorff distance and average symmetric surface distance.展开更多
Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people everywhere.Due to its ability to produce a detailed view of the soft tissues,including the s...Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people everywhere.Due to its ability to produce a detailed view of the soft tissues,including the spinal cord,nerves,intervertebral discs,and vertebrae,Magnetic Resonance Imaging is thought to be the most effective method for imaging the spine.The semantic segmentation of vertebrae plays a major role in the diagnostic process of lumbar diseases.It is difficult to semantically partition the vertebrae in Magnetic Resonance Images from the surrounding variety of tissues,including muscles,ligaments,and intervertebral discs.U-Net is a powerful deep-learning architecture to handle the challenges of medical image analysis tasks and achieves high segmentation accuracy.This work proposes a modified U-Net architecture namely MU-Net,consisting of the Meijering convolutional layer that incorporates the Meijering filter to perform the semantic segmentation of lumbar vertebrae L1 to L5 and sacral vertebra S1.Pseudo-colour mask images were generated and used as ground truth for training the model.The work has been carried out on 1312 images expanded from T1-weighted mid-sagittal MRI images of 515 patients in the Lumbar Spine MRI Dataset publicly available from Mendeley Data.The proposed MU-Net model for the semantic segmentation of the lumbar vertebrae gives better performance with 98.79%of pixel accuracy(PA),98.66%of dice similarity coefficient(DSC),97.36%of Jaccard coefficient,and 92.55%mean Intersection over Union(mean IoU)metrics using the mentioned dataset.展开更多
Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases.Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited t...Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases.Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited training data,imbalance data distribution,and inadequate feature extraction persist,hindering both the segmentation performance and optimal model generalization.Addressing these critical issues,the DEFFA-Unet is proposed featuring an additional encoder to process domain-invariant pre-processed inputs,thereby improving both richer feature encoding and enhanced model generalization.A feature filtering fusion module is developed to ensure the precise feature filtering and robust hybrid feature fusion.In response to the task-specific need for higher precision where false positives are very costly,traditional skip connections are replaced with the attention-guided feature reconstructing fusion module.Additionally,innovative data augmentation and balancing methods are proposed to counter data scarcity and distribution imbalance,further boosting the robustness and generalization of the model.With a comprehensive suite of evaluation metrics,extensive validations on four benchmark datasets(DRIVE,CHASEDB1,STARE,and HRF)and an SLO dataset(IOSTAR),demonstrate the proposed method’s superiority over both baseline and state-of-the-art models.Particularly the proposed method significantly outperforms the compared methods in cross-validation model generalization.展开更多
Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is cr...Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is crucial for computationally limited portable devices such as augmented reality and virtual reality.With the rapid advancements in deep learning,many network models have been developed specifically for eye image segmentation.Some methods divide the segmentation process into multiple stages to achieve model parameter miniaturization while enhancing output through post processing techniques to improve segmentation accuracy.These approaches significantly increase the inference time.Other networks adopt more complex encoding and decoding modules to achieve end-to-end output,which requires substantial computation.Therefore,balancing the model’s size,accuracy,and computational complexity is essential.To address these challenges,we propose a lightweight asymmetric UNet architecture and a projection loss function.We utilize ResNet-3 layer blocks to enhance feature extraction efficiency in the encoding stage.In the decoding stage,we employ regular convolutions and skip connections to upscale the feature maps from the latent space to the original image size,balancing the model size and segmentation accuracy.In addition,we leverage the geometric features of the eye region and design a projection loss function to further improve the segmentation accuracy without adding any additional inference computational cost.We validate our approach on the OpenEDS2019 dataset for virtual reality and achieve state-of-the-art performance with 95.33%mean intersection over union(mIoU).Our model has only 0.63M parameters and 350 FPS,which are 68%and 200%of the state-of-the-art model RITNet,respectively.展开更多
基金provided by the Science Research Project of Hebei Education Department under grant No.BJK2024115.
文摘High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes and wealth of spatial details pose challenges for semantic segmentation.While convolutional neural networks(CNNs)excel at capturing local features,they are limited in modeling long-range dependencies.Conversely,transformers utilize multihead self-attention to integrate global context effectively,but this approach often incurs a high computational cost.This paper proposes a global-local multiscale context network(GLMCNet)to extract both global and local multiscale contextual information from HRSIs.A detail-enhanced filtering module(DEFM)is proposed at the end of the encoder to refine the encoder outputs further,thereby enhancing the key details extracted by the encoder and effectively suppressing redundant information.In addition,a global-local multiscale transformer block(GLMTB)is proposed in the decoding stage to enable the modeling of rich multiscale global and local information.We also design a stair fusion mechanism to transmit deep semantic information from deep to shallow layers progressively.Finally,we propose the semantic awareness enhancement module(SAEM),which further enhances the representation of multiscale semantic features through spatial attention and covariance channel attention.Extensive ablation analyses and comparative experiments were conducted to evaluate the performance of the proposed method.Specifically,our method achieved a mean Intersection over Union(mIoU)of 86.89%on the ISPRS Potsdam dataset and 84.34%on the ISPRS Vaihingen dataset,outperforming existing models such as ABCNet and BANet.
文摘Advanced traffic monitoring systems encounter substantial challenges in vehicle detection and classification due to the limitations of conventional methods,which often demand extensive computational resources and struggle with diverse data acquisition techniques.This research presents a novel approach for vehicle classification and recognition in aerial image sequences,integrating multiple advanced techniques to enhance detection accuracy.The proposed model begins with preprocessing using Multiscale Retinex(MSR)to enhance image quality,followed by Expectation-Maximization(EM)Segmentation for precise foreground object identification.Vehicle detection is performed using the state-of-the-art YOLOv10 framework,while feature extraction incorporates Maximally Stable Extremal Regions(MSER),Dense Scale-Invariant Feature Transform(Dense SIFT),and Zernike Moments Features to capture distinct object characteristics.Feature optimization is further refined through a Hybrid Swarm-based Optimization algorithm,ensuring optimal feature selection for improved classification performance.The final classification is conducted using a Vision Transformer,leveraging its robust learning capabilities for enhanced accuracy.Experimental evaluations on benchmark datasets,including UAVDT and the Unmanned Aerial Vehicle Intruder Dataset(UAVID),demonstrate the superiority of the proposed approach,achieving an accuracy of 94.40%on UAVDT and 93.57%on UAVID.The results highlight the efficacy of the model in significantly enhancing vehicle detection and classification in aerial imagery,outperforming existing methodologies and offering a statistically validated improvement for intelligent traffic monitoring systems compared to existing approaches.
文摘This systematic review aims to comprehensively examine and compare deep learning methods for brain tumor segmentation and classification using MRI and other imaging modalities,focusing on recent trends from 2022 to 2025.The primary objective is to evaluate methodological advancements,model performance,dataset usage,and existing challenges in developing clinically robust AI systems.We included peer-reviewed journal articles and highimpact conference papers published between 2022 and 2025,written in English,that proposed or evaluated deep learning methods for brain tumor segmentation and/or classification.Excluded were non-open-access publications,books,and non-English articles.A structured search was conducted across Scopus,Google Scholar,Wiley,and Taylor&Francis,with the last search performed in August 2025.Risk of bias was not formally quantified but considered during full-text screening based on dataset diversity,validation methods,and availability of performance metrics.We used narrative synthesis and tabular benchmarking to compare performance metrics(e.g.,accuracy,Dice score)across model types(CNN,Transformer,Hybrid),imaging modalities,and datasets.A total of 49 studies were included(43 journal articles and 6 conference papers).These studies spanned over 9 public datasets(e.g.,BraTS,Figshare,REMBRANDT,MOLAB)and utilized a range of imaging modalities,predominantly MRI.Hybrid models,especially ResViT and UNetFormer,consistently achieved high performance,with classification accuracy exceeding 98%and segmentation Dice scores above 0.90 across multiple studies.Transformers and hybrid architectures showed increasing adoption post2023.Many studies lacked external validation and were evaluated only on a few benchmark datasets,raising concerns about generalizability and dataset bias.Few studies addressed clinical interpretability or uncertainty quantification.Despite promising results,particularly for hybrid deep learning models,widespread clinical adoption remains limited due to lack of validation,interpretability concerns,and real-world deployment barriers.
基金supported by Institute of Information&Communications Technology Planning&Evaluation(IITP)under the Metaverse Support Program to Nurture the Best Talents(IITP-2024-RS-2023-00254529)grant funded by the Korea government(MSIT).
文摘Brain tumors require precise segmentation for diagnosis and treatment plans due to their complex morphology and heterogeneous characteristics.While MRI-based automatic brain tumor segmentation technology reduces the burden on medical staff and provides quantitative information,existing methodologies and recent models still struggle to accurately capture and classify the fine boundaries and diverse morphologies of tumors.In order to address these challenges and maximize the performance of brain tumor segmentation,this research introduces a novel SwinUNETR-based model by integrating a new decoder block,the Hierarchical Channel-wise Attention Decoder(HCAD),into a powerful SwinUNETR encoder.The HCAD decoder block utilizes hierarchical features and channelspecific attention mechanisms to further fuse information at different scales transmitted from the encoder and preserve spatial details throughout the reconstruction phase.Rigorous evaluations on the recent BraTS GLI datasets demonstrate that the proposed SwinHCAD model achieved superior and improved segmentation accuracy on both the Dice score and HD95 metrics across all tumor subregions(WT,TC,and ET)compared to baseline models.In particular,the rationale and contribution of the model design were clarified through ablation studies to verify the effectiveness of the proposed HCAD decoder block.The results of this study are expected to greatly contribute to enhancing the efficiency of clinical diagnosis and treatment planning by increasing the precision of automated brain tumor segmentation.
基金National Science and Technology Council,the Republic of China,under grants NSTC 113-2221-E-194-011-MY3 and Research Center on Artificial Intelligence and Sustainability,National Chung Cheng University under the research project grant titled“Generative Digital Twin System Design for Sustainable Smart City Development in Taiwan.
文摘Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.
基金This project was supported by the National Natural Foundation of China (60404022) and the Foundation of Department ofEducation of Hebei Province (2002209).
文摘Mixture model based image segmentation method, which assumes that image pixels are independent and do not consider the position relationship between pixels, is not robust to noise and usually leads to misclassification. A new segmentation method, called multi-resolution Ganssian mixture model method, is proposed. First, an image pyramid is constructed and son-father link relationship is built between each level of pyramid. Then the mixture model segmentation method is applied to the top level. The segmentation result on the top level is passed top-down to the bottom level according to the son-father link relationship between levels. The proposed method considers not only local but also global information of image, it overcomes the effect of noise and can obtain better segmentation result. Experimental result demonstrates its effectiveness.
基金the National Natural Science Foundation of China(Grant No.11471004)the Key Research and Development Program of Shaanxi Province,China(Grant No.2018SF-251)。
文摘To solve the problem that the magnetic resonance(MR)image has weak boundaries,large amount of information,and low signal-to-noise ratio,we propose an image segmentation method based on the multi-resolution Markov random field(MRMRF)model.The algorithm uses undecimated dual-tree complex wavelet transformation to transform the image into multiple scales.The transformed low-frequency scale histogram is used to improve the initial clustering center of the K-means algorithm,and then other cluster centers are selected according to the maximum distance rule to obtain the coarse-scale segmentation.The results are then segmented by the improved MRMRF model.In order to solve the problem of fuzzy edge segmentation caused by the gray level inhomogeneity of MR image segmentation under the MRMRF model,it is proposed to introduce variable weight parameters in the segmentation process of each scale.Furthermore,the final segmentation results are optimized.We name this algorithm the variable-weight multi-resolution Markov random field(VWMRMRF).The simulation and clinical MR image segmentation verification show that the VWMRMRF algorithm has high segmentation accuracy and robustness,and can accurately and stably achieve low signal-to-noise ratio,weak boundary MR image segmentation.
文摘In order to effectively improve the pathological diagnosis capability and feature resolution of 3D human brain CT images,a threshold segmentation method of multi-resolution 3D human brain CT image based on edge pixel grayscale feature decomposition is proposed in this paper.In this method,first,original 3D human brain image information is collected,and CT image filtering is performed to the collected information through the gradient value decomposition method,and edge contour features of the 3D human brain CT image are extracted.Then,the threshold segmentation method is adopted to segment the regional pixel feature block of the 3D human brain CT image to segment the image into block vectors with high-resolution feature points,and the 3D human brain CT image is reconstructed with the salient feature point as center.Simulation results show that the method proposed in this paper can provide accuracy up to 100%when the signal-to-noise ratio is 0,and with the increase of signal-to-noise ratio,the accuracy provided by this method is stable at 100%.Comparison results show that the threshold segmentation method of multi-resolution 3D human brain CT image based on edge pixel grayscale feature decomposition is signicantly better than traditional methods in pathological feature estimation accuracy,and it effectively improves the rapid pathological diagnosis and positioning recognition abilities to CT images.
基金funded by the Natural Science Foundation of the Jiangsu Higher Education Institutions of China(grant number 22KJD440001)Changzhou Science&Technology Program(grant number CJ20220232).
文摘The Internet of Vehicles (IoV) has become an important direction in the field of intelligent transportation, in which vehicle positioning is a crucial part. SLAM (Simultaneous Localization and Mapping) technology plays a crucial role in vehicle localization and navigation. Traditional Simultaneous Localization and Mapping (SLAM) systems are designed for use in static environments, and they can result in poor performance in terms of accuracy and robustness when used in dynamic environments where objects are in constant movement. To address this issue, a new real-time visual SLAM system called MG-SLAM has been developed. Based on ORB-SLAM2, MG-SLAM incorporates a dynamic target detection process that enables the detection of both known and unknown moving objects. In this process, a separate semantic segmentation thread is required to segment dynamic target instances, and the Mask R-CNN algorithm is applied on the Graphics Processing Unit (GPU) to accelerate segmentation. To reduce computational cost, only key frames are segmented to identify known dynamic objects. Additionally, a multi-view geometry method is adopted to detect unknown moving objects. The results demonstrate that MG-SLAM achieves higher precision, with an improvement from 0.2730 m to 0.0135 m in precision. Moreover, the processing time required by MG-SLAM is significantly reduced compared to other dynamic scene SLAM algorithms, which illustrates its efficacy in locating objects in dynamic scenes.
基金Australian Research Council Project(FL-170100117).
文摘To avoid the laborious annotation process for dense prediction tasks like semantic segmentation,unsupervised domain adaptation(UDA)methods have been proposed to leverage the abundant annotations from a source domain,such as virtual world(e.g.,3D games),and adapt models to the target domain(the real world)by narrowing the domain discrepancies.However,because of the large domain gap,directly aligning two distinct domains without considering the intermediates leads to inefficient alignment and inferior adaptation.To address this issue,we propose a novel learnable evolutionary Category Intermediates(CIs)guided UDA model named Leci,which enables the information transfer between the two domains via two processes,i.e.,Distilling and Blending.Starting from a random initialization,the CIs learn shared category-wise semantics automatically from two domains in the Distilling process.Then,the learned semantics in the CIs are sent back to blend the domain features through a residual attentive fusion(RAF)module,such that the categorywise features of both domains shift towards each other.As the CIs progressively and consistently learn from the varying feature distributions during training,they are evolutionary to guide the model to achieve category-wise feature alignment.Experiments on both GTA5 and SYNTHIA datasets demonstrate Leci's superiority over prior representative methods.
基金funded by the National Natural Science Foundation of China(Grant No.6240072655)the Hubei Provincial Key Research and Development Program(Grant No.2023BCB151)+1 种基金the Wuhan Natural Science Foundation Exploration Program(Chenguang Program,Grant No.2024040801020202)the Natural Science Foundation of Hubei Province of China(Grant No.2025AFB148).
文摘Image segmentation is attracting increasing attention in the field of medical image analysis.Since widespread utilization across various medical applications,ensuring and improving segmentation accuracy has become a crucial topic of research.With advances in deep learning,researchers have developed numerous methods that combine Transformers and convolutional neural networks(CNNs)to create highly accurate models for medical image segmentation.However,efforts to further enhance accuracy by developing larger and more complex models or training with more extensive datasets,significantly increase computational resource consumption.To address this problem,we propose BiCLIP-nnFormer(the prefix"Bi"refers to the use of two distinct CLIP models),a virtual multimodal instrument that leverages CLIP models to enhance the segmentation performance of a medical segmentation model nnFormer.Since two CLIP models(PMC-CLIP and CoCa-CLIP)are pre-trained on large datasets,they do not require additional training,thus conserving computation resources.These models are used offline to extract image and text embeddings from medical images.These embeddings are then processed by the proposed 3D CLIP adapter,which adapts the CLIP knowledge for segmentation tasks by fine-tuning.Finally,the adapted embeddings are fused with feature maps extracted from the nnFormer encoder for generating predicted masks.This process enriches the representation capabilities of the feature maps by integrating global multimodal information,leading to more precise segmentation predictions.We demonstrate the superiority of BiCLIP-nnFormer and the effectiveness of using CLIP models to enhance nnFormer through experiments on two public datasets,namely the Synapse multi-organ segmentation dataset(Synapse)and the Automatic Cardiac Diagnosis Challenge dataset(ACDC),as well as a self-annotated lung multi-category segmentation dataset(LMCS).
文摘Brain tumors present significant challenges in medical diagnosis and treatment,where early detection is crucial for reducing morbidity and mortality rates.This research introduces a novel deep learning model,the Progressive Layered U-Net(PLU-Net),designed to improve brain tumor segmentation accuracy from Magnetic Resonance Imaging(MRI)scans.The PLU-Net extends the standard U-Net architecture by incorporating progressive layering,attention mechanisms,and multi-scale data augmentation.The progressive layering involves a cascaded structure that refines segmentation masks across multiple stages,allowing the model to capture features at different scales and resolutions.Attention gates within the convolutional layers selectively focus on relevant features while suppressing irrelevant ones,enhancing the model's ability to delineate tumor boundaries.Additionally,multi-scale data augmentation techniques increase the diversity of training data and boost the model's generalization capabilities.Evaluated on the BraTS 2021 dataset,the PLU-Net achieved state-of-the-art performance with a dice coefficient of 0.91,specificity of 0.92,sensitivity of 0.89,Hausdorff95 of 2.5,outperforming other modified U-Net architectures in segmentation accuracy.These results underscore the effectiveness of the PLU-Net in improving brain tumor segmentation from MRI scans,supporting clinicians in early diagnosis,treatment planning,and the development of new therapies.
基金supported by the Natural Science Foundation of China(No.41804112,author:Chengyun Song).
文摘Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution mismatch.However,current copy-paste methods have three limitations:(1)training the model solely with copy-paste mixed pictures from labeled and unlabeled input loses a lot of labeled information;(2)low-quality pseudo-labels can cause confirmation bias in pseudo-supervised learning on unlabeled data;(3)the segmentation performance in low-contrast and local regions is less than optimal.We design a Stochastic Augmentation-Based Dual-Teaching Auxiliary Training Strategy(SADT),which enhances feature diversity and learns high-quality features to overcome these problems.To be more precise,SADT trains the Student Network by using pseudo-label-based training from Teacher Network 1 and supervised learning with labeled data,which prevents the loss of rare labeled data.We introduce a bi-directional copy-pastemask with progressive high-entropy filtering to reduce data distribution disparities and mitigate confirmation bias in pseudo-supervision.For the mixed images,Deep-Shallow Spatial Contrastive Learning(DSSCL)is proposed in the feature spaces of Teacher Network 2 and the Student Network to improve the segmentation capabilities in low-contrast and local areas.In this procedure,the features retrieved by the Student Network are subjected to a random feature perturbation technique.On two openly available datasets,extensive trials show that our proposed SADT performs much better than the state-ofthe-art semi-supervised medical segmentation techniques.Using only 10%of the labeled data for training,SADT was able to acquire a Dice score of 90.10%on the ACDC(Automatic Cardiac Diagnosis Challenge)dataset.
基金supported by the Natural Science Foundation of the Anhui Higher Education Institutions of China(Grant Nos.2023AH040149 and 2024AH051915)the Anhui Provincial Natural Science Foundation(Grant No.2208085MF168)+1 种基金the Science and Technology Innovation Tackle Plan Project of Maanshan(Grant No.2024RGZN001)the Scientific Research Fund Project of Anhui Medical University(Grant No.2023xkj122).
文摘Convolutional neural networks(CNNs)-based medical image segmentation technologies have been widely used in medical image segmentation because of their strong representation and generalization abilities.However,due to the inability to effectively capture global information from images,CNNs can easily lead to loss of contours and textures in segmentation results.Notice that the transformer model can effectively capture the properties of long-range dependencies in the image,and furthermore,combining the CNN and the transformer can effectively extract local details and global contextual features of the image.Motivated by this,we propose a multi-branch and multi-scale attention network(M2ANet)for medical image segmentation,whose architecture consists of three components.Specifically,in the first component,we construct an adaptive multi-branch patch module for parallel extraction of image features to reduce information loss caused by downsampling.In the second component,we apply residual block to the well-known convolutional block attention module to enhance the network’s ability to recognize important features of images and alleviate the phenomenon of gradient vanishing.In the third component,we design a multi-scale feature fusion module,in which we adopt adaptive average pooling and position encoding to enhance contextual features,and then multi-head attention is introduced to further enrich feature representation.Finally,we validate the effectiveness and feasibility of the proposed M2ANet method through comparative experiments on four benchmark medical image segmentation datasets,particularly in the context of preserving contours and textures.
基金the National Natural Science Foundation of China(42472194,42302153,and 42002144)the Fundamental Research Funds for the Central Univer-sities(22CX06002A).
文摘Karst fractures serve as crucial seepage channels and storage spaces for carbonate natural gas reservoirs,and electrical image logs are vital data for visualizing and characterizing such fractures.However,the conventional approach of identifying fractures using electrical image logs predominantly relies on manual processes that are not only time-consuming but also highly subjective.In addition,the heterogeneity and strong dissolution tendency of karst carbonate reservoirs lead to complexity and variety in fracture geometry,which makes it difficult to accurately identify fractures.In this paper,the electrical image logs network(EILnet)da deep-learning-based intelligent semantic segmentation model with a selective attention mechanism and selective feature fusion moduledwas created to enable the intelligent identification and segmentation of different types of fractures through electrical logging images.Data from electrical image logs representing structural and induced fractures were first selected using the sliding window technique before image inpainting and data augmentation were implemented for these images to improve the generalizability of the model.Various image-processing tools,including the bilateral filter,Laplace operator,and Gaussian low-pass filter,were also applied to the electrical logging images to generate a multi-attribute dataset to help the model learn the semantic features of the fractures.The results demonstrated that the EILnet model outperforms mainstream deep-learning semantic segmentation models,such as Fully Convolutional Networks(FCN-8s),U-Net,and SegNet,for both the single-channel dataset and the multi-attribute dataset.The EILnet provided significant advantages for the single-channel dataset,and its mean intersection over union(MIoU)and pixel accuracy(PA)were 81.32%and 89.37%,respectively.In the case of the multi-attribute dataset,the identification capability of all models improved to varying degrees,with the EILnet achieving the highest MIoU and PA of 83.43%and 91.11%,respectively.Further,applying the EILnet model to various blind wells demonstrated its ability to provide reliable fracture identification,thereby indicating its promising potential applications.
基金National Key Research and Development Program of China,Grant/Award Number:2018YFE0206900China Postdoctoral Science Foundation,Grant/Award Number:2023M731204+2 种基金The Open Project of Key Laboratory for Quality Evaluation of Ultrasound Surgical Equipment of National Medical Products Administration,Grant/Award Number:SMDTKL-2023-1-01The Hubei Province Key Research and Development Project,Grant/Award Number:2023BCB007CAAI-Huawei MindSpore Open Fund。
文摘Convolutional neural network(CNN)with the encoder-decoder structure is popular in medical image segmentation due to its excellent local feature extraction ability but it faces limitations in capturing the global feature.The transformer can extract the global information well but adapting it to small medical datasets is challenging and its computational complexity can be heavy.In this work,a serial and parallel network is proposed for the accurate 3D medical image segmentation by combining CNN and transformer and promoting feature interactions across various semantic levels.The core components of the proposed method include the cross window self-attention based transformer(CWST)and multi-scale local enhanced(MLE)modules.The CWST module enhances the global context understanding by partitioning 3D images into non-overlapping windows and calculating sparse global attention between windows.The MLE module selectively fuses features by computing the voxel attention between different branch features,and uses convolution to strengthen the dense local information.The experiments on the prostate,atrium,and pancreas MR/CT image datasets consistently demonstrate the advantage of the proposed method over six popular segmentation models in both qualitative evaluation and quantitative indexes such as dice similarity coefficient,Intersection over Union,95%Hausdorff distance and average symmetric surface distance.
文摘Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people everywhere.Due to its ability to produce a detailed view of the soft tissues,including the spinal cord,nerves,intervertebral discs,and vertebrae,Magnetic Resonance Imaging is thought to be the most effective method for imaging the spine.The semantic segmentation of vertebrae plays a major role in the diagnostic process of lumbar diseases.It is difficult to semantically partition the vertebrae in Magnetic Resonance Images from the surrounding variety of tissues,including muscles,ligaments,and intervertebral discs.U-Net is a powerful deep-learning architecture to handle the challenges of medical image analysis tasks and achieves high segmentation accuracy.This work proposes a modified U-Net architecture namely MU-Net,consisting of the Meijering convolutional layer that incorporates the Meijering filter to perform the semantic segmentation of lumbar vertebrae L1 to L5 and sacral vertebra S1.Pseudo-colour mask images were generated and used as ground truth for training the model.The work has been carried out on 1312 images expanded from T1-weighted mid-sagittal MRI images of 515 patients in the Lumbar Spine MRI Dataset publicly available from Mendeley Data.The proposed MU-Net model for the semantic segmentation of the lumbar vertebrae gives better performance with 98.79%of pixel accuracy(PA),98.66%of dice similarity coefficient(DSC),97.36%of Jaccard coefficient,and 92.55%mean Intersection over Union(mean IoU)metrics using the mentioned dataset.
文摘Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases.Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited training data,imbalance data distribution,and inadequate feature extraction persist,hindering both the segmentation performance and optimal model generalization.Addressing these critical issues,the DEFFA-Unet is proposed featuring an additional encoder to process domain-invariant pre-processed inputs,thereby improving both richer feature encoding and enhanced model generalization.A feature filtering fusion module is developed to ensure the precise feature filtering and robust hybrid feature fusion.In response to the task-specific need for higher precision where false positives are very costly,traditional skip connections are replaced with the attention-guided feature reconstructing fusion module.Additionally,innovative data augmentation and balancing methods are proposed to counter data scarcity and distribution imbalance,further boosting the robustness and generalization of the model.With a comprehensive suite of evaluation metrics,extensive validations on four benchmark datasets(DRIVE,CHASEDB1,STARE,and HRF)and an SLO dataset(IOSTAR),demonstrate the proposed method’s superiority over both baseline and state-of-the-art models.Particularly the proposed method significantly outperforms the compared methods in cross-validation model generalization.
基金supported by the HFIPS Director’s Foundation(YZJJ202207-TS),the National Natural Science Foundation of China(82371931)the Natural Science Foundation of Anhui Province(2008085MC69)+3 种基金the Natural Science Foundation of Hefei City(2021033)the General Scientific Research Project of Anhui Provincial Health Commission(AHWJ2021b150)the Collaborative Innovation Program of Hefei Science Center,CAS(2021HSC-CIP013)the Anhui Province Key Research and Development Project(202204295107020004).
文摘Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is crucial for computationally limited portable devices such as augmented reality and virtual reality.With the rapid advancements in deep learning,many network models have been developed specifically for eye image segmentation.Some methods divide the segmentation process into multiple stages to achieve model parameter miniaturization while enhancing output through post processing techniques to improve segmentation accuracy.These approaches significantly increase the inference time.Other networks adopt more complex encoding and decoding modules to achieve end-to-end output,which requires substantial computation.Therefore,balancing the model’s size,accuracy,and computational complexity is essential.To address these challenges,we propose a lightweight asymmetric UNet architecture and a projection loss function.We utilize ResNet-3 layer blocks to enhance feature extraction efficiency in the encoding stage.In the decoding stage,we employ regular convolutions and skip connections to upscale the feature maps from the latent space to the original image size,balancing the model size and segmentation accuracy.In addition,we leverage the geometric features of the eye region and design a projection loss function to further improve the segmentation accuracy without adding any additional inference computational cost.We validate our approach on the OpenEDS2019 dataset for virtual reality and achieve state-of-the-art performance with 95.33%mean intersection over union(mIoU).Our model has only 0.63M parameters and 350 FPS,which are 68%and 200%of the state-of-the-art model RITNet,respectively.
