Despite its remarkable performance on natural images,the segment anything model(SAM)lacks domain-specific information in medical imaging.and faces the challenge of losing local multi-scale information in the encoding ...Despite its remarkable performance on natural images,the segment anything model(SAM)lacks domain-specific information in medical imaging.and faces the challenge of losing local multi-scale information in the encoding phase.This paper presents a medical image segmentation model based on SAM with a local multi-scale feature encoder(LMSFE-SAM)to address the issues above.Firstly,based on the SAM,a local multi-scale feature encoder is introduced to improve the representation of features within local receptive field,thereby supplying the Vision Transformer(ViT)branch in SAM with enriched local multi-scale contextual information.At the same time,a multiaxial Hadamard product module(MHPM)is incorporated into the local multi-scale feature encoder in a lightweight manner to reduce the quadratic complexity and noise interference.Subsequently,a cross-branch balancing adapter is designed to balance the local and global information between the local multi-scale feature encoder and the ViT encoder in SAM.Finally,to obtain smaller input image size and to mitigate overlapping in patch embeddings,the size of the input image is reduced from 1024×1024 pixels to 256×256 pixels,and a multidimensional information adaptation component is developed,which includes feature adapters,position adapters,and channel-spatial adapters.This component effectively integrates the information from small-sized medical images into SAM,enhancing its suitability for clinical deployment.The proposed model demonstrates an average enhancement ranging from 0.0387 to 0.3191 across six objective evaluation metrics on BUSI,DDTI,and TN3K datasets compared to eight other representative image segmentation models.This significantly enhances the performance of the SAM on medical images,providing clinicians with a powerful tool in clinical diagnosis.展开更多
Efficient segmentation of oiled pixels in optical remotely sensed images is the precondition of optical identification and classification of different spilled oils,which remains one of the keys to optical remote sensi...Efficient segmentation of oiled pixels in optical remotely sensed images is the precondition of optical identification and classification of different spilled oils,which remains one of the keys to optical remote sensing of oil spills.Optical remotely sensed images of oil spills are inherently multidimensional and embedded with a complex knowledge framework.This complexity often hinders the effectiveness of mechanistic algorithms across varied scenarios.Although optical remote-sensing theory for oil spills has advanced,the scarcity of curated datasets and the difficulty of collecting them limit their usefulness for training deep learning models.This study introduces a data expansion strategy that utilizes the Segment Anything Model(SAM),effectively bridging the gap between traditional mechanism algorithms and emergent self-adaptive deep learning models.Optical dimension reduction is achieved through standardized preprocessing processes that address the decipherable properties of the input image.After preprocessing,SAM can swiftly and accurately segment spilled oil in images.The unified AI-based workflow significantly accelerates labeled-dataset creation and has proven effective for both rapid emergency intelligence during spill incidents and the rapid mapping and classification of oil footprints across China’s coastal waters.Our results show that coupling a remote sensing mechanism with a foundation model enables near-real-time,large-scale monitoring of complex surface slicks and offers guidance for the next generation of detection and quantification algorithms.展开更多
The use of AI technologies in remote sensing(RS)tasks has been the focus of many individuals in both the professional and academic domains.Having more accessible interfaces and tools that allow people of little or no ...The use of AI technologies in remote sensing(RS)tasks has been the focus of many individuals in both the professional and academic domains.Having more accessible interfaces and tools that allow people of little or no experience to intuitively interact with RS data of multiple formats is a potential provided by this integration.However,the use of AI and AI agents to help automate RS-related tasks is still in its infancy stage,with some frameworks and interfaces built on top of well-known vision language models(VLM)such as GPT-4,segment anything model(SAM),and grounding DINO.These tools do promise and draw guidelines on the potentials and limitations of existing solutions concerning the use of said models.In this work,the state of the art AI foundation models(FM)are reviewed and used in a multi-modal manner to ingest RS imagery input and perform zero-shot object detection using natural language.The natural language input is then used to define the classes or labels the model should look for,then,both inputs are fed to the pipeline.The pipeline presented in this work makes up for the shortcomings of the general knowledge FMs by stacking pre-processing and post-processing applications on top of the FMs;these applications include tiling to produce uniform patches of the original image for faster detection,outlier rejection of redundant bounding boxes using statistical and machine learning methods.The pipeline was tested with UAV,aerial and satellite images taken over multiple areas.The accuracy for the semantic segmentation showed improvement from the original 64%to approximately 80%-99%by utilizing the pipeline and techniques proposed in this work.GitHub Repository:MohanadDiab/LangRS.展开更多
Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the dataset.Initially,data augmentation mainly involved some simple transformations of images.Later,in ord...Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the dataset.Initially,data augmentation mainly involved some simple transformations of images.Later,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative models.However,these methods required a mass of computation of training or searching.In this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for images.Without the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved annotations.In this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation model.Multiple comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and COCO2017.On this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,respectively.Consequently,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.展开更多
In this paper,we introduce an innovative method for computer-aided design(CAD)segmentation by concatenating meshes and CAD models.Many previous CAD segmentation methods have achieved impressive performance using singl...In this paper,we introduce an innovative method for computer-aided design(CAD)segmentation by concatenating meshes and CAD models.Many previous CAD segmentation methods have achieved impressive performance using single representations,such as meshes,CAD,and point clouds.However,existing methods cannot effectively combine different three-dimensional model types for the direct conversion,alignment,and integrity maintenance of geometric and topological information.Hence,we propose an integration approach that combines the geometric accuracy of CAD data with the flexibility of mesh representations,as well as introduce a unique hybrid representation that combines CAD and mesh models to enhance segmentation accuracy.To combine these two model types,our hybrid system utilizes advanced-neural-network techniques to convert CAD models into mesh models.For complex CAD models,model segmentation is crucial for model retrieval and reuse.In partial retrieval,it aims to segment a complex CAD model into several simple components.The first component of our hybrid system involves advanced mesh-labeling algorithms that harness the digitization of CAD properties to mesh models.The second component integrates labelled face features for CAD segmentation by leveraging the abundant multisemantic information embedded in CAD models.This combination of mesh and CAD not only refines the accuracy of boundary delineation but also provides a comprehensive understanding of the underlying object semantics.This study uses the Fusion 360 Gallery dataset.Experimental results indicate that our hybrid method can segment these models with higher accuracy than other methods that use single representations.展开更多
Segmenting skin lesions is critical for early skin cancer detection.Existing CNN and Transformer-based methods face challenges such as high computational complexity and limited adaptability to variations in lesion siz...Segmenting skin lesions is critical for early skin cancer detection.Existing CNN and Transformer-based methods face challenges such as high computational complexity and limited adaptability to variations in lesion sizes.To overcome these limitations,we introduce MSAMamba-UNet,a lightweight model that integrates two novel architectures:Multi-Scale Mamba(MSMamba)and Adaptive Dynamic Gating Block(ADGB).MSMamba utilizes multi-scale decomposition and a parallel hierarchical structure to enhance the delineation of irregular lesion boundaries and sensitivity to small targets.ADGB dynamically selects convolutional kernels with varying receptive fields based on input features,improving the model’s capacity to accommodate diverse lesion textures and scales.Additionally,we introduce a Mix Attention Fusion Block(MAF)to enhance shallow feature representation by integrating parallel channel and pixel attention mechanisms.Extensive evaluation of MSAMamba-UNet on the ISIC 2016,ISIC 2017,and ISIC 2018 datasets demonstrates competitive segmentation accuracy with only 0.056 M parameters and 0.069 GFLOPs.Our experiments revealed that MSAMamba-UNet achieved IoU scores of 85.53%,85.47%,and 82.22%,as well as DSC scores of 92.20%,92.17%,and 90.24%,respectively.These results underscore the lightweight design and effectiveness of MSAMamba-UNet.展开更多
Objective This study aimed to explore a novel method that integrates the segmentation guidance classification and the dif-fusion model augmentation to realize the automatic classification for tibial plateau fractures(...Objective This study aimed to explore a novel method that integrates the segmentation guidance classification and the dif-fusion model augmentation to realize the automatic classification for tibial plateau fractures(TPFs).Methods YOLOv8n-cls was used to construct a baseline model on the data of 3781 patients from the Orthopedic Trauma Center of Wuhan Union Hospital.Additionally,a segmentation-guided classification approach was proposed.To enhance the dataset,a diffusion model was further demonstrated for data augmentation.Results The novel method that integrated the segmentation-guided classification and diffusion model augmentation sig-nificantly improved the accuracy and robustness of fracture classification.The average accuracy of classification for TPFs rose from 0.844 to 0.896.The comprehensive performance of the dual-stream model was also significantly enhanced after many rounds of training,with both the macro-area under the curve(AUC)and the micro-AUC increasing from 0.94 to 0.97.By utilizing diffusion model augmentation and segmentation map integration,the model demonstrated superior efficacy in identifying SchatzkerⅠ,achieving an accuracy of 0.880.It yielded an accuracy of 0.898 for SchatzkerⅡandⅢand 0.913 for SchatzkerⅣ;for SchatzkerⅤandⅥ,the accuracy was 0.887;and for intercondylar ridge fracture,the accuracy was 0.923.Conclusion The dual-stream attention-based classification network,which has been verified by many experiments,exhibited great potential in predicting the classification of TPFs.This method facilitates automatic TPF assessment and may assist surgeons in the rapid formulation of surgical plans.展开更多
Background:Traditional imaging approaches to keratoconus(KCN)have thus far failed to produce a standardized approach for diagnosis.While many diagnostic modalities and metrics exist,none have proven robust enough to b...Background:Traditional imaging approaches to keratoconus(KCN)have thus far failed to produce a standardized approach for diagnosis.While many diagnostic modalities and metrics exist,none have proven robust enough to be considered a gold standard.This study aims to introduce novel metrics to differentiate between KCN and healthy corneas using three-dimensional(3D)measurements of surface area and volume.Methods:This retrospective observational study examined KCN patients along with healthy control patients between the ages of 20 and 79 years old at the University of Maryland,Baltimore.The selected patients underwent a nine-line raster scan anterior segment optical coherence tomography(AS-OCT).ImageJ was used to determine the central 6 mm of each image and each corneal image was then divided into six 1 mm segments.Free-D software was then used to render the nine different images into a 3D model to calculate corneal surface area and volume.A two-tailed Mann-Whitney test was used to assess statistical significance when comparing these subsets.Results:Thirty-three eyes with KCN,along with 33 healthy control,were enrolled.There were statistically significant differences between the healthy and KCN groups in the metric of anterior corneal surface area(13.927 vs.13.991 mm^(2),P=0.046),posterior corneal surface area(14.045 vs.14.173 mm^(2),P<0.001),and volume(8.430 vs.7.773 mm3,P<0.001)within the central 6 mm.Conclusions:3D corneal models derived from AS-OCT can be used to measure anterior corneal surface area,posterior corneal surface area,and corneal volume.All three parameters are statistically different between corneas with KCN and healthy corneas.Further study and application of these parameters may yield new methodologies for the detection of KCN.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
A new two-step framework is proposed for image segmentation. In the first step, the gray-value distribution of the given image is reshaped to have larger inter-class variance and less intra-class variance. In the sec-...A new two-step framework is proposed for image segmentation. In the first step, the gray-value distribution of the given image is reshaped to have larger inter-class variance and less intra-class variance. In the sec- ond step, the discriminant-based methods or clustering-based methods are performed on the reformed distribution. It is focused on the typical clustering methods-Gaussian mixture model （GMM） and its variant to demonstrate the feasibility of the framework. Due to the independence of the first step in its second step, it can be integrated into the pixel-based and the histogram-based methods to improve their segmentation quality. The experiments on artificial and real images show that the framework can achieve effective and robust segmentation results.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
he objective of the research is to develop a fast procedure for segmenting typical videophone images. In this paper, a new approach to color image segmentation based on HSI(Hue, Saturation, Intensity) color model is r...he objective of the research is to develop a fast procedure for segmenting typical videophone images. In this paper, a new approach to color image segmentation based on HSI(Hue, Saturation, Intensity) color model is reported. It is in contrast to the conventional approaches by using the three components of HSI color model in succession. This strategy makes the segmentation procedure much fast and effective. Experimental results with typical “headandshoulders” real images taken from videophone sequences show that the new appproach can fulfill the application requirements.展开更多
One of the most complex tasks for computer-aided diagnosis(Intelligent decision support system)is the segmentation of lesions.Thus,this study proposes a new fully automated method for the segmentation of ovarian and b...One of the most complex tasks for computer-aided diagnosis(Intelligent decision support system)is the segmentation of lesions.Thus,this study proposes a new fully automated method for the segmentation of ovarian and breast ultrasound images.The main contributions of this research is the development of a novel Viola–James model capable of segmenting the ultrasound images of breast and ovarian cancer cases.In addition,proposed an approach that can efficiently generate region-of-interest(ROI)and new features that can be used in characterizing lesion boundaries.This study uses two databases in training and testing the proposed segmentation approach.The breast cancer database contains 250 images,while that of the ovarian tumor has 100 images obtained from several hospitals in Iraq.Results of the experiments showed that the proposed approach demonstrates better performance compared with those of other segmentation methods used for segmenting breast and ovarian ultrasound images.The segmentation result of the proposed system compared with the other existing techniques in the breast cancer data set was 78.8%.By contrast,the segmentation result of the proposed system in the ovarian tumor data set was 79.2%.In the classification results,we achieved 95.43%accuracy,92.20%sensitivity,and 97.5%specificity when we used the breast cancer data set.For the ovarian tumor data set,we achieved 94.84%accuracy,96.96%sensitivity,and 90.32%specificity.展开更多
An improved approach for J-value segmentation （JSEG） is presented for unsupervised color image segmentation. Instead of color quantization algorithm, an automatic classification method based on adaptive mean shift ...An improved approach for J-value segmentation （JSEG） is presented for unsupervised color image segmentation. Instead of color quantization algorithm, an automatic classification method based on adaptive mean shift （AMS） based clustering is used for nonparametric clustering of image data set. The clustering results are used to construct Gaussian mixture modelling （GMM） of image data for the calculation of soft J value. The region growing algorithm used in JSEG is then applied in segmenting the image based on the multiscale soft J-images. Experiments show that the synergism of JSEG and the soft classification based on AMS based clustering and GMM overcomes the limitations of JSEG successfully and is more robust.展开更多
基金supported by Natural Science Foundation Programme of Gansu Province(No.24JRRA231)National Natural Science Foundation of China(No.62061023)Gansu Provincial Science and Technology Plan Key Research and Development Program Project(No.24YFFA024).
文摘Despite its remarkable performance on natural images,the segment anything model(SAM)lacks domain-specific information in medical imaging.and faces the challenge of losing local multi-scale information in the encoding phase.This paper presents a medical image segmentation model based on SAM with a local multi-scale feature encoder(LMSFE-SAM)to address the issues above.Firstly,based on the SAM,a local multi-scale feature encoder is introduced to improve the representation of features within local receptive field,thereby supplying the Vision Transformer(ViT)branch in SAM with enriched local multi-scale contextual information.At the same time,a multiaxial Hadamard product module(MHPM)is incorporated into the local multi-scale feature encoder in a lightweight manner to reduce the quadratic complexity and noise interference.Subsequently,a cross-branch balancing adapter is designed to balance the local and global information between the local multi-scale feature encoder and the ViT encoder in SAM.Finally,to obtain smaller input image size and to mitigate overlapping in patch embeddings,the size of the input image is reduced from 1024×1024 pixels to 256×256 pixels,and a multidimensional information adaptation component is developed,which includes feature adapters,position adapters,and channel-spatial adapters.This component effectively integrates the information from small-sized medical images into SAM,enhancing its suitability for clinical deployment.The proposed model demonstrates an average enhancement ranging from 0.0387 to 0.3191 across six objective evaluation metrics on BUSI,DDTI,and TN3K datasets compared to eight other representative image segmentation models.This significantly enhances the performance of the SAM on medical images,providing clinicians with a powerful tool in clinical diagnosis.
基金The National Natural Science Foundation of China under contract No.42371380the National Key Research and Development Program of China under contract No.2023YFC2811800the Fundamental Research Funds for the Central Universities under contract No.0904-14380035.
文摘Efficient segmentation of oiled pixels in optical remotely sensed images is the precondition of optical identification and classification of different spilled oils,which remains one of the keys to optical remote sensing of oil spills.Optical remotely sensed images of oil spills are inherently multidimensional and embedded with a complex knowledge framework.This complexity often hinders the effectiveness of mechanistic algorithms across varied scenarios.Although optical remote-sensing theory for oil spills has advanced,the scarcity of curated datasets and the difficulty of collecting them limit their usefulness for training deep learning models.This study introduces a data expansion strategy that utilizes the Segment Anything Model(SAM),effectively bridging the gap between traditional mechanism algorithms and emergent self-adaptive deep learning models.Optical dimension reduction is achieved through standardized preprocessing processes that address the decipherable properties of the input image.After preprocessing,SAM can swiftly and accurately segment spilled oil in images.The unified AI-based workflow significantly accelerates labeled-dataset creation and has proven effective for both rapid emergency intelligence during spill incidents and the rapid mapping and classification of oil footprints across China’s coastal waters.Our results show that coupling a remote sensing mechanism with a foundation model enables near-real-time,large-scale monitoring of complex surface slicks and offers guidance for the next generation of detection and quantification algorithms.
文摘The use of AI technologies in remote sensing(RS)tasks has been the focus of many individuals in both the professional and academic domains.Having more accessible interfaces and tools that allow people of little or no experience to intuitively interact with RS data of multiple formats is a potential provided by this integration.However,the use of AI and AI agents to help automate RS-related tasks is still in its infancy stage,with some frameworks and interfaces built on top of well-known vision language models(VLM)such as GPT-4,segment anything model(SAM),and grounding DINO.These tools do promise and draw guidelines on the potentials and limitations of existing solutions concerning the use of said models.In this work,the state of the art AI foundation models(FM)are reviewed and used in a multi-modal manner to ingest RS imagery input and perform zero-shot object detection using natural language.The natural language input is then used to define the classes or labels the model should look for,then,both inputs are fed to the pipeline.The pipeline presented in this work makes up for the shortcomings of the general knowledge FMs by stacking pre-processing and post-processing applications on top of the FMs;these applications include tiling to produce uniform patches of the original image for faster detection,outlier rejection of redundant bounding boxes using statistical and machine learning methods.The pipeline was tested with UAV,aerial and satellite images taken over multiple areas.The accuracy for the semantic segmentation showed improvement from the original 64%to approximately 80%-99%by utilizing the pipeline and techniques proposed in this work.GitHub Repository:MohanadDiab/LangRS.
基金Natural Science Foundation of Zhejiang Province,Grant/Award Number:LY23F020025Science and Technology Commissioner Program of Huzhou,Grant/Award Number:2023GZ42Sichuan Provincial Science and Technology Support Program,Grant/Award Numbers:2023ZHCG0005,2023ZHCG0008。
文摘Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the dataset.Initially,data augmentation mainly involved some simple transformations of images.Later,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative models.However,these methods required a mass of computation of training or searching.In this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for images.Without the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved annotations.In this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation model.Multiple comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and COCO2017.On this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,respectively.Consequently,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.
基金Supported by the National Key Research and Development Program of China(2024YFB3311703)National Natural Science Foundation of China(61932003)Beijing Science and Technology Plan Project(Z221100006322003).
文摘In this paper,we introduce an innovative method for computer-aided design(CAD)segmentation by concatenating meshes and CAD models.Many previous CAD segmentation methods have achieved impressive performance using single representations,such as meshes,CAD,and point clouds.However,existing methods cannot effectively combine different three-dimensional model types for the direct conversion,alignment,and integrity maintenance of geometric and topological information.Hence,we propose an integration approach that combines the geometric accuracy of CAD data with the flexibility of mesh representations,as well as introduce a unique hybrid representation that combines CAD and mesh models to enhance segmentation accuracy.To combine these two model types,our hybrid system utilizes advanced-neural-network techniques to convert CAD models into mesh models.For complex CAD models,model segmentation is crucial for model retrieval and reuse.In partial retrieval,it aims to segment a complex CAD model into several simple components.The first component of our hybrid system involves advanced mesh-labeling algorithms that harness the digitization of CAD properties to mesh models.The second component integrates labelled face features for CAD segmentation by leveraging the abundant multisemantic information embedded in CAD models.This combination of mesh and CAD not only refines the accuracy of boundary delineation but also provides a comprehensive understanding of the underlying object semantics.This study uses the Fusion 360 Gallery dataset.Experimental results indicate that our hybrid method can segment these models with higher accuracy than other methods that use single representations.
基金supported in part by the National Natural Science Foundation of China under Grant 62201201the Foundation of Henan Educational Committee under Grant 242102211042.
文摘Segmenting skin lesions is critical for early skin cancer detection.Existing CNN and Transformer-based methods face challenges such as high computational complexity and limited adaptability to variations in lesion sizes.To overcome these limitations,we introduce MSAMamba-UNet,a lightweight model that integrates two novel architectures:Multi-Scale Mamba(MSMamba)and Adaptive Dynamic Gating Block(ADGB).MSMamba utilizes multi-scale decomposition and a parallel hierarchical structure to enhance the delineation of irregular lesion boundaries and sensitivity to small targets.ADGB dynamically selects convolutional kernels with varying receptive fields based on input features,improving the model’s capacity to accommodate diverse lesion textures and scales.Additionally,we introduce a Mix Attention Fusion Block(MAF)to enhance shallow feature representation by integrating parallel channel and pixel attention mechanisms.Extensive evaluation of MSAMamba-UNet on the ISIC 2016,ISIC 2017,and ISIC 2018 datasets demonstrates competitive segmentation accuracy with only 0.056 M parameters and 0.069 GFLOPs.Our experiments revealed that MSAMamba-UNet achieved IoU scores of 85.53%,85.47%,and 82.22%,as well as DSC scores of 92.20%,92.17%,and 90.24%,respectively.These results underscore the lightweight design and effectiveness of MSAMamba-UNet.
基金supported by the National Natural Science Foundation of China(Nos.81974355 and 82172524)Key Research and Development Program of Hubei Province(No.2021BEA161)+2 种基金National Innovation Platform Development Program(No.2020021105012440)Open Project Funding of the Hubei Key Laboratory of Big Data Intelligent Analysis and Application,Hubei University(No.2024BDIAA03)Free Innovation Preliminary Research Fund of Wuhan Union Hospital(No.2024XHYN047).
文摘Objective This study aimed to explore a novel method that integrates the segmentation guidance classification and the dif-fusion model augmentation to realize the automatic classification for tibial plateau fractures(TPFs).Methods YOLOv8n-cls was used to construct a baseline model on the data of 3781 patients from the Orthopedic Trauma Center of Wuhan Union Hospital.Additionally,a segmentation-guided classification approach was proposed.To enhance the dataset,a diffusion model was further demonstrated for data augmentation.Results The novel method that integrated the segmentation-guided classification and diffusion model augmentation sig-nificantly improved the accuracy and robustness of fracture classification.The average accuracy of classification for TPFs rose from 0.844 to 0.896.The comprehensive performance of the dual-stream model was also significantly enhanced after many rounds of training,with both the macro-area under the curve(AUC)and the micro-AUC increasing from 0.94 to 0.97.By utilizing diffusion model augmentation and segmentation map integration,the model demonstrated superior efficacy in identifying SchatzkerⅠ,achieving an accuracy of 0.880.It yielded an accuracy of 0.898 for SchatzkerⅡandⅢand 0.913 for SchatzkerⅣ;for SchatzkerⅤandⅥ,the accuracy was 0.887;and for intercondylar ridge fracture,the accuracy was 0.923.Conclusion The dual-stream attention-based classification network,which has been verified by many experiments,exhibited great potential in predicting the classification of TPFs.This method facilitates automatic TPF assessment and may assist surgeons in the rapid formulation of surgical plans.
文摘Background:Traditional imaging approaches to keratoconus(KCN)have thus far failed to produce a standardized approach for diagnosis.While many diagnostic modalities and metrics exist,none have proven robust enough to be considered a gold standard.This study aims to introduce novel metrics to differentiate between KCN and healthy corneas using three-dimensional(3D)measurements of surface area and volume.Methods:This retrospective observational study examined KCN patients along with healthy control patients between the ages of 20 and 79 years old at the University of Maryland,Baltimore.The selected patients underwent a nine-line raster scan anterior segment optical coherence tomography(AS-OCT).ImageJ was used to determine the central 6 mm of each image and each corneal image was then divided into six 1 mm segments.Free-D software was then used to render the nine different images into a 3D model to calculate corneal surface area and volume.A two-tailed Mann-Whitney test was used to assess statistical significance when comparing these subsets.Results:Thirty-three eyes with KCN,along with 33 healthy control,were enrolled.There were statistically significant differences between the healthy and KCN groups in the metric of anterior corneal surface area(13.927 vs.13.991 mm^(2),P=0.046),posterior corneal surface area(14.045 vs.14.173 mm^(2),P<0.001),and volume(8.430 vs.7.773 mm3,P<0.001)within the central 6 mm.Conclusions:3D corneal models derived from AS-OCT can be used to measure anterior corneal surface area,posterior corneal surface area,and corneal volume.All three parameters are statistically different between corneas with KCN and healthy corneas.Further study and application of these parameters may yield new methodologies for the detection of KCN.
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 the National Natural Science Foundation of China(60505004,60773061)~~
文摘A new two-step framework is proposed for image segmentation. In the first step, the gray-value distribution of the given image is reshaped to have larger inter-class variance and less intra-class variance. In the sec- ond step, the discriminant-based methods or clustering-based methods are performed on the reformed distribution. It is focused on the typical clustering methods-Gaussian mixture model （GMM） and its variant to demonstrate the feasibility of the framework. Due to the independence of the first step in its second step, it can be integrated into the pixel-based and the histogram-based methods to improve their segmentation quality. The experiments on artificial and real images show that the framework can achieve effective and robust segmentation results.
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.
文摘he objective of the research is to develop a fast procedure for segmenting typical videophone images. In this paper, a new approach to color image segmentation based on HSI(Hue, Saturation, Intensity) color model is reported. It is in contrast to the conventional approaches by using the three components of HSI color model in succession. This strategy makes the segmentation procedure much fast and effective. Experimental results with typical “headandshoulders” real images taken from videophone sequences show that the new appproach can fulfill the application requirements.
文摘One of the most complex tasks for computer-aided diagnosis(Intelligent decision support system)is the segmentation of lesions.Thus,this study proposes a new fully automated method for the segmentation of ovarian and breast ultrasound images.The main contributions of this research is the development of a novel Viola–James model capable of segmenting the ultrasound images of breast and ovarian cancer cases.In addition,proposed an approach that can efficiently generate region-of-interest(ROI)and new features that can be used in characterizing lesion boundaries.This study uses two databases in training and testing the proposed segmentation approach.The breast cancer database contains 250 images,while that of the ovarian tumor has 100 images obtained from several hospitals in Iraq.Results of the experiments showed that the proposed approach demonstrates better performance compared with those of other segmentation methods used for segmenting breast and ovarian ultrasound images.The segmentation result of the proposed system compared with the other existing techniques in the breast cancer data set was 78.8%.By contrast,the segmentation result of the proposed system in the ovarian tumor data set was 79.2%.In the classification results,we achieved 95.43%accuracy,92.20%sensitivity,and 97.5%specificity when we used the breast cancer data set.For the ovarian tumor data set,we achieved 94.84%accuracy,96.96%sensitivity,and 90.32%specificity.
文摘An improved approach for J-value segmentation （JSEG） is presented for unsupervised color image segmentation. Instead of color quantization algorithm, an automatic classification method based on adaptive mean shift （AMS） based clustering is used for nonparametric clustering of image data set. The clustering results are used to construct Gaussian mixture modelling （GMM） of image data for the calculation of soft J value. The region growing algorithm used in JSEG is then applied in segmenting the image based on the multiscale soft J-images. Experiments show that the synergism of JSEG and the soft classification based on AMS based clustering and GMM overcomes the limitations of JSEG successfully and is more robust.
