Lupus Nephritis(LN)is a significant risk factor for morbidity and mortality in systemic lupus erythematosus,and nephropathology is still the gold standard for diagnosing LN.To assist pathologists in evaluating histopa...Lupus Nephritis(LN)is a significant risk factor for morbidity and mortality in systemic lupus erythematosus,and nephropathology is still the gold standard for diagnosing LN.To assist pathologists in evaluating histopathological images of LN,a 2D Rényi entropy multi-threshold image segmentation method is proposed in this research to apply to LN images.This method is based on an improved Cuckoo Search(CS)algorithm that introduces a Diffusion Mechanism(DM)and an Adaptiveβ-Hill Climbing(AβHC)strategy called the DMCS algorithm.The DMCS algorithm is tested on 30 benchmark functions of the IEEE CEC2017 dataset.In addition,the DMCS-based multi-threshold image segmentation method is also used to segment renal pathological images.Experimental results show that adding these two strategies improves the DMCS algorithm's ability to find the optimal solution.According to the three image quality evaluation metrics:PSNR,FSIM,and SSIM,the proposed image segmentation method performs well in image segmentation experiments.Our research shows that the DMCS algorithm is a helpful image segmentation method for renal pathological images.展开更多
The application of transformer networks and feature fusion models in medical image segmentation has aroused considerable attention within the academic circle.Nevertheless,two main obstacles persist:(1)the restrictions...The application of transformer networks and feature fusion models in medical image segmentation has aroused considerable attention within the academic circle.Nevertheless,two main obstacles persist:(1)the restrictions of the Transformer network in dealing with locally detailed features,and(2)the considerable loss of feature information in current feature fusion modules.To solve these issues,this study initially presents a refined feature extraction approach,employing a double-branch feature extraction network to capture complex multi-scale local and global information from images.Subsequently,we proposed a low-loss feature fusion method-Multi-branch Feature Fusion Enhancement Module(MFFEM),which realizes effective feature fusion with minimal loss.Simultaneously,the cross-layer cross-attention fusion module(CLCA)is adopted to further achieve adequate feature fusion by enhancing the interaction between encoders and decoders of various scales.Finally,the feasibility of our method was verified using the Synapse and ACDC datasets,demonstrating its competitiveness.The average DSC(%)was 83.62 and 91.99 respectively,and the average HD95(mm)was reduced to 19.55 and 1.15 respectively.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
Segmenting the lesion regions from the ultrasound （US） images is an important step in the intra-operative planning of some computer-aided therapies. High-Intensity Focused Ultrasound （HIFU）, as a popular computer-...Segmenting the lesion regions from the ultrasound （US） images is an important step in the intra-operative planning of some computer-aided therapies. High-Intensity Focused Ultrasound （HIFU）, as a popular computer-aided therapy, has been widely used in the treatment of uterine fibroids. However, such segmentation in HIFU remains challenge for two reasons： （1） the blurry or missing boundaries of lesion regions in the HIFU images and （2） the deformation of uterine fibroids caused by the patient＇s breathing or an external force during the US imaging process, which can lead to complex shapes of lesion regions. These factors have prevented classical active contour-based segmentation methods from yielding desired results for uterine fibroids in US images. In this paper, a novel active contour-based segmentation method is proposed, which utilizes the correlation information of target shapes among a sequence of images as prior knowledge to aid the existing active contour method. This prior knowledge can be interpreted as a unsupervised clustering of shapes prior modeling. Meanwhile, it is also proved that the shapes correlation has the low-rank property in a linear space, and the theory of matrix recovery is used as an effective tool to impose the proposed prior on an existing active contour model. Finally, an accurate method is developed to solve the proposed model by using the Augmented Lagrange Multiplier （ALM）. Experimental results from both synthetic and clinical uterine fibroids US image sequences demonstrate that the proposed method can consistently improve the performance of active contour models and increase the robustness against missing or misleading boundaries, and can greatly improve the efficiency of HIFU therapy.展开更多
Lots of noises and heterogeneous objects with various sizes coexist in a complex image,such as an ore image;the classical image thresholding method cannot effectively distinguish between ores.To segment ore objects wi...Lots of noises and heterogeneous objects with various sizes coexist in a complex image,such as an ore image;the classical image thresholding method cannot effectively distinguish between ores.To segment ore objects with various sizes simultaneously,two adaptive windows in the image were chosen for each pixel;the gray value of windows was calculated by Otsu＇s threshold method.To extract the object skeleton,the definition principle of distance transformation templates was proposed.The ores linked together in a binary image were separated by distance transformation and gray reconstruction.The seed region of each object was picked up from the local maximum gray region of the reconstruction image.Starting from these seed regions,the watershed method was used to segment ore object effectively.The proposed algorithm marks and segments most objects from complex images precisely.展开更多
In this study,a novel hybrid Water Cycle Moth-Flame Optimization(WCMFO)algorithm is proposed for multilevel thresholding brain image segmentation in Magnetic Resonance(MR)image slices.WCMFO constitutes a hybrid betwee...In this study,a novel hybrid Water Cycle Moth-Flame Optimization(WCMFO)algorithm is proposed for multilevel thresholding brain image segmentation in Magnetic Resonance(MR)image slices.WCMFO constitutes a hybrid between the two techniques,comprising the water cycle and moth-flame optimization algorithms.The optimal thresholds are obtained by maximizing the between class variance(Otsu’s function)of the image.To test the performance of threshold searching process,the proposed algorithm has been evaluated on standard benchmark of ten axial T2-weighted brain MR images for image segmentation.The experimental outcomes infer that it produces better optimal threshold values at a greater and quicker convergence rate.In contrast to other state-of-the-art methods,namely Adaptive Wind Driven Optimization(AWDO),Adaptive Bacterial Foraging(ABF)and Particle Swarm Optimization(PSO),the proposed algorithm has been found to be better at producing the best objective function,Peak Signal-to-Noise Ratio(PSNR),Standard Deviation(STD)and lower computational time values.Further,it was observed thatthe segmented image gives greater detail when the threshold level increases.Moreover,the statistical test result confirms that the best and mean values are almost zero and the average difference between best and mean value 1.86 is obtained through the 30 executions of the proposed algorithm.Thus,these images will lead to better segments of gray,white and cerebrospinal fluid that enable better clinical choices and diagnoses using a proposed algorithm.展开更多
Aiming at the problem that the existence of disturbances on the edges of light-stripe makes the segmentation of the light-stripes images difficult, a new segmentation algorithm based on edge-searching is presented. It...Aiming at the problem that the existence of disturbances on the edges of light-stripe makes the segmentation of the light-stripes images difficult, a new segmentation algorithm based on edge-searching is presented. It firstly calculates every edge pixel's horizontal coordinate grads to produce the corresponding grads-edge, then uses a designed length-variable l D template to scan the light-stripes' grads-edges. The template is able to find the disturbances with different width utilizing the distributing character of the edge disturbances. The found disturbances are eliminated finally. The algorithm not only can smoothly segment the light-stripes images, but also eliminate most disturbances on the light-stripes' edges without damaging the light-stripes images' 3D information. A practical example of using the proposed algorithm is given in the end. It is proved that the efficiency of the algorithm has been improved obviously by comparison.展开更多
Segmentation of the bladder in computerized tomography(CT) images is an important step in radiation therapy planning of prostate cancer. We present a new segmentation scheme to automatically delineate the bladder cont...Segmentation of the bladder in computerized tomography(CT) images is an important step in radiation therapy planning of prostate cancer. We present a new segmentation scheme to automatically delineate the bladder contour in CT images with three major steps. First,we use the mean shift algorithm to obtain a clustered image containing the rough contour of the bladder,which is then extracted in the second step by applying a region-growing algorithm with the initial seed point selected from a line-by-line scanning process. The third step is to refine the bladder contour more accurately using the rolling-ball algorithm. These steps are then extended to segment the bladder volume in a slice-by-slice manner. The obtained results were compared to manual segmentation by radiation oncologists. The average values of sensitivity,specificity,positive predictive value,negative predictive value,and Hausdorff distance are 86.5%,96.3%,90.5%,96.5%,and 2.8 pixels,respectively. The results show that the bladder can be accurately segmented.展开更多
Using conventional Mean Shift Algorithm to segment high spatial resolution Remote sensing images of mountainous areas usually leads to an unsatisfactory result, due to its rich texture information. In this paper, we p...Using conventional Mean Shift Algorithm to segment high spatial resolution Remote sensing images of mountainous areas usually leads to an unsatisfactory result, due to its rich texture information. In this paper, we propose an improved Mean Shift Algorithm in consideration of the characteristics of these images. First, images were classified into several homogeneous color regions and texture regions by conducting variance detection on the color space. Next, each homogeneous color region was directly segmented to generate the preliminary results by applying the Mean Shift Algorithm. For each texture region, we conduct a high-dimensional feature space by extracting information such as color, texture and shape comprehensively, and work out a proper bandwidth according to the normalized distribution density. Then the bandwidth variable Mean Shift Algorithm was applied to obtain segmentation results by conducting the pattern classification in feature space. Last, the final results were obtained by merging these regions by means of the constructed cost functions and removing the oversegmented regions from the merged regions. It has been experimentally segmented on the high spatial resolution remote sensing images collected by Quickbird and Unmanned Aerial Vehicle(UAV). We put forward an approach to evaluate the segmentation results by using the segmentation matching index(SMI). This takes into consideration both the area and the spectrum. The experimental results suggest that the improved Mean Shift Algorithm outperforms the conventional one in terms of accuracy of segmentation.展开更多
Magnetic resonance imaging(MRI)has been a prevalence technique for breast cancer diagnosis.Computer-aided detection and segmentation of lesions from MRIs plays a vital role for the MRI-based disease analysis.There are...Magnetic resonance imaging(MRI)has been a prevalence technique for breast cancer diagnosis.Computer-aided detection and segmentation of lesions from MRIs plays a vital role for the MRI-based disease analysis.There are two main issues of the existing breast lesion segmentation techniques:requir ing manual delineation of Regions of Interests(ROIs)as a step of initialization;and requiring a large amount of labeled images for model construction or parameter lear ning,while in real clinical or experimental settings,it is highly challenging to get suficient labeled MRIs.To resolve these issues,this work proposes a semi-supervised method for breast tumor segmentation based on super voxel strategies.After image segmentation with advanced cluster techniques,we take a supervised learning step to classify the tumor and nontumor patches in order to automatically locate the tumor regions in an MRI To obtain the opt imal performance of tumor extraction,we take extensive experiments to learn par ameters for tumor segmentation and dassification,and design 225 classifiers corresponding to diferent parameter settings.We call the proposed method as Semi supervised Tumor Segmentation(SSTS),and apply it to both mass and nonmass lesions.Experimental results show better performance of SsTS compared with five state of-the art methods.展开更多
Segmentation is the key step in auto-interpretation of high-resolution spaceborne synthetic aperture radar（SAR） images. A novel method is proposed based on integrating the geometric active contour（GAC） and the sup...Segmentation is the key step in auto-interpretation of high-resolution spaceborne synthetic aperture radar（SAR） images. A novel method is proposed based on integrating the geometric active contour（GAC） and the support vector machine（SVM）models. First, the images are segmented by using SVM and textural statistics. A likelihood measurement for every pixel is derived by using the initial segmentation. The Chan-Vese model then is modified by adding two items： the likelihood and the distance between the initial segmentation and the evolving contour. Experimental results using real SAR images demonstrate the good performance of the proposed method compared to several classic GAC models.展开更多
Coronavirus Disease 2019(COVID-19)is the most severe epidemic that is prevalent all over the world.How quickly and accurately identifying COVID-19 is of great significance to controlling the spread speed of the epidem...Coronavirus Disease 2019(COVID-19)is the most severe epidemic that is prevalent all over the world.How quickly and accurately identifying COVID-19 is of great significance to controlling the spread speed of the epidemic.Moreover,it is essential to accurately and rapidly identify COVID-19 lesions by analyzing Chest X-ray images.As we all know,image segmentation is a critical stage in image processing and analysis.To achieve better image segmentation results,this paper proposes to improve the multi-verse optimizer algorithm using the Rosenbrock method and diffusion mechanism named RDMVO.Then utilizes RDMVO to calculate the maximum Kapur’s entropy for multilevel threshold image segmentation.This image segmentation scheme is called RDMVO-MIS.We ran two sets of experiments to test the performance of RDMVO and RDMVO-MIS.First,RDMVO was compared with other excellent peers on IEEE CEC2017 to test the performance of RDMVO on benchmark functions.Second,the image segmentation experiment was carried out using RDMVO-MIS,and some meta-heuristic algorithms were selected as comparisons.The test image dataset includes Berkeley images and COVID-19 Chest X-ray images.The experimental results verify that RDMVO is highly competitive in benchmark functions and image segmentation experiments compared with other meta-heuristic algorithms.展开更多
Leukaemia is a type of blood cancer that is caused by undeveloped White Blood Cells(WBC),and it is also called a blast blood cell.In the marrow of human bones,leukaemia is developed and is responsible for blood cell g...Leukaemia is a type of blood cancer that is caused by undeveloped White Blood Cells(WBC),and it is also called a blast blood cell.In the marrow of human bones,leukaemia is developed and is responsible for blood cell generation with leukocytes and WBC,and if any cell gets blasted,then it may become a cause of death.Therefore,the diagnosis of leukaemia in its early stages helps greatly in the treatment along with saving human lives.Subsequently,in terms of detection,image segmentation techniques play a vital role,and they turn out to be the important image processing steps for the extraction of feature patterns from the Acute Lymphoblastic Leukaemia(ALL)type of blood cancer.Moreover,the image segmentation technique focuses on the division of cells by segmenting a microscopic image into background and cancer blood cell nucleus,which is well-known as the Region Of Interest(ROI).As a result,in this article,we attempt to build a segmentation technique capable of solving blood cell nucleus segmentation issues using four distinct scenarios,including K-means,FCM(Fuzzy Cmeans),K-means with FFA(Firefly Algorithm),and FCM with FFA.Also,we determine the most effective method of blood cell nucleus segmentation,which we subsequently use for the Leukaemia classification model.Finally,using the Convolution Neural Network(CNN)as a classifier,we developed a leukaemia cancer classification model from the microscopic images.The proposed system’s classification accuracy is tested using the CNN to test the model on the ALL-IDB dataset and equate it to the current state of the art.In terms of experimental analysis,we observed that the accuracy of the model is near to 99%,and it is far better than other existing models that are designed to segment and classify the types of leukaemia cancer in terms of ALL.展开更多
Remote sensing image segmentation is the basis of image understanding and analysis. However,the precision and the speed of segmentation can not meet the need of image analysis,due to strong uncertainty and rich textur...Remote sensing image segmentation is the basis of image understanding and analysis. However,the precision and the speed of segmentation can not meet the need of image analysis,due to strong uncertainty and rich texture details of remote sensing images. We proposed a new segmentation method based on Adaptive Genetic Algorithm(AGA) and Alternative Fuzzy C-Means(AFCM) . Segmentation thresholds were identified by AGA. Then the image was segmented by AFCM. The results indicate that the precision and the speed of segmentation have been greatly increased,and the accuracy of threshold selection is much higher compared with traditional Otsu and Fuzzy C-Means(FCM) segmentation methods. The segmentation results also show that multi-thresholds segmentation has been achieved by combining AGA with AFCM.展开更多
This paper presents a novel computerized technique for the segmentation of nuclei in hematoxylin and eosin(H&E)stained histopathology images.The purpose of this study is to overcome the challenges faced in automat...This paper presents a novel computerized technique for the segmentation of nuclei in hematoxylin and eosin(H&E)stained histopathology images.The purpose of this study is to overcome the challenges faced in automated nuclei segmentation due to the diversity of nuclei structures that arise from differences in tissue types and staining protocols,as well as the segmentation of variable-sized and overlapping nuclei.To this extent,the approach proposed in this study uses an ensemble of the UNet architecture with various Convolutional Neural Networks(CNN)architectures as encoder backbones,along with stain normalization and test time augmentation,to improve segmentation accuracy.Additionally,this paper employs a Structure-Preserving Color Normalization(SPCN)technique as a preprocessing step for stain normalization.The proposed model was trained and tested on both single-organ and multi-organ datasets,yielding an F1 score of 84.11%,mean Intersection over Union(IoU)of 81.67%,dice score of 84.11%,accuracy of 92.58%and precision of 83.78%on the multi-organ dataset,and an F1 score of 87.04%,mean IoU of 86.66%,dice score of 87.04%,accuracy of 96.69%and precision of 87.57%on the single-organ dataset.These findings demonstrate that the proposed model ensemble coupled with the right pre-processing and post-processing techniques enhances nuclei segmentation capabilities.展开更多
A leukocyte segmentation method based on S component and B component images is proposed.Threshold segmentation operation is applied to get two binary images in S component and B component images.The samples used in th...A leukocyte segmentation method based on S component and B component images is proposed.Threshold segmentation operation is applied to get two binary images in S component and B component images.The samples used in this study are peripheral blood smears.It is easy tofind from the two binary images that gray values are the same at every corresponding pixels in theleukocyte cytoplasm region,but opposite in the other regions.The feature shows that "IMAGEAND"operation can be employed on the two binary images to segment the cytoplasm region ofleukocyte.By doing"IMAGE XOR"operation between cytoplasn region and nucleus region,theleukocyte segment ation can be retrieved effectively.The segmentation accuracy is evaluated by comparing the segmentation result of the proposed method with the manual segmentation by ahematologist.Experiment results show that the proposed method is of a higher segmentationaccuracy and it also performs well when leukocytes overlap_with erythrocytes.The averagesegmentation accuracy of the proposed method reaches 97.7%for segmenting five types ofleukocyte.Good segmentation results provide an important foundation for leukocytes aut omaticrecognition.展开更多
Multispectral imaging (MSI) technique is often used to capture imagesof the fundus by illuminating it with different wavelengths of light. However,these images are taken at different points in time such that eyeball m...Multispectral imaging (MSI) technique is often used to capture imagesof the fundus by illuminating it with different wavelengths of light. However,these images are taken at different points in time such that eyeball movementscan cause misalignment between consecutive images. The multispectral imagesequence reveals important information in the form of retinal and choroidal bloodvessel maps, which can help ophthalmologists to analyze the morphology of theseblood vessels in detail. This in turn can lead to a high diagnostic accuracy of several diseases. In this paper, we propose a novel semi-supervised end-to-end deeplearning framework called “Adversarial Segmentation and Registration Nets”(ASRNet) for the simultaneous estimation of the blood vessel segmentation andthe registration of multispectral images via an adversarial learning process. ASRNet consists of two subnetworks: (i) A segmentation module S that fulfills theblood vessel segmentation task, and (ii) A registration module R that estimatesthe spatial correspondence of an image pair. Based on the segmention-drivenregistration network, we train the segmentation network using a semi-supervisedadversarial learning strategy. Our experimental results show that the proposedASRNet can achieve state-of-the-art accuracy in segmentation and registrationtasks performed with real MSI datasets.展开更多
Objective:This study was aimed at validating the accuracy of a proposed algorithm for fully automatic 3D left atrial segmentation and to compare its performance with existing deep learning algorithms.Methods:A two-sta...Objective:This study was aimed at validating the accuracy of a proposed algorithm for fully automatic 3D left atrial segmentation and to compare its performance with existing deep learning algorithms.Methods:A two-stage method with a shared 3D U-Net was proposed to segment the 3D left atrium.In this archi-tecture,the 3D U-Net was used to extract 3D features,a two-stage strategy was used to decrease segmentation error caused by the class imbalance problem,and the shared network was designed to decrease model complexity.Model performance was evaluated with the DICE score,Jaccard index and Hausdorff distance.Results:Algorithm development and evaluation were performed with a set of 100 late gadolinium-enhanced car-diovascular magnetic resonance images.Our method achieved a DICE score of 0.918,a Jaccard index of 0.848 and a Hausdorff distance of 1.211,thus,outperforming existing deep learning algorithms.The best performance of the proposed model(DICE:0.851;Jaccard:0.750;Hausdorff distance:4.382)was also achieved on a publicly available 2013 image data set.Conclusion:The proposed two-stage method with a shared 3D U-Net is an efficient algorithm for fully automatic 3D left atrial segmentation.This study provides a solution for processing large datasets in resource-constrained applica-tions.Significance Statement:Studying atrial structure directly is crucial for comprehending and managing atrial fibril-lation(AF).Accurate reconstruction and measurement of atrial geometry for clinical purposes remains challenging,despite potential improvements in the visibility of AF-associated structures with late gadolinium-enhanced magnetic resonance imaging.This difficulty arises from the varying intensities caused by increased tissue enhancement and artifacts,as well as variability in image quality.Therefore,an efficient algorithm for fully automatic 3D left atrial seg-mentation is proposed in the present study.展开更多
Stroke and heart attack,which could be led by a kind of cerebrovascular and cardiovascular disease named as atherosclerosis,would seriously cause human morbidity and mortality.It is important for the early stage diagn...Stroke and heart attack,which could be led by a kind of cerebrovascular and cardiovascular disease named as atherosclerosis,would seriously cause human morbidity and mortality.It is important for the early stage diagnosis and monitoring medical intervention of the atherosclerosis.Carotid stenosis is a classical atherosclerotic lesion with vessel wall narrowing down and accumulating plaques burden.The carotid artery of intima-media thickness(IMT)is a key indicator to the disease.With the development of computer assisted diagnosis technology,the imaging techniques,segmentation algorithms,measurement methods,and evaluation tools have made considerable progress.Ultrasound imaging,being real-time,economic,reliable,and safe,now seems to become a standard in vascular assessment methodology especially for the measurement of IMT.This review firstly attempts to discuss the clinical relevance of measurements in clinical practice at first,and then followed by the challenges that one has to face when approaching the segmentation of ultrasound images.Secondly,the commonly used methods for the IMT segmentation and measurement are presented.Thirdly,discussion and evaluation of different segmentation techniques are performed.An overview of summary and future perspectives is given finally.展开更多
Objective and quantitative assessment of skin conditions is essential for cosmeceutical studies and research on skin aging and skin regeneration.Various handcraft-based image processing methods have been proposed to e...Objective and quantitative assessment of skin conditions is essential for cosmeceutical studies and research on skin aging and skin regeneration.Various handcraft-based image processing methods have been proposed to evaluate skin conditions objectively,but they have unavoidable disadvantages when used to analyze skin features accurately.This study proposes a hybrid segmentation scheme consisting of Deeplab v3+with an Inception-ResNet-v2 backbone,LightGBM,and morphological processing(MP)to overcome the shortcomings of handcraft-based approaches.First,we apply Deeplab v3+with an Inception-ResNet-v2 backbone for pixel segmentation of skin wrinkles and cells.Then,LightGBM and MP are used to enhance the pixel segmentation quality.Finally,we determine several skin features based on the results of wrinkle and cell segmentation.Our proposed segmentation scheme achieved a mean accuracy of 0.854,mean of intersection over union of 0.749,and mean boundary F1 score of 0.852,which achieved 1.1%,6.7%,and 14.8%improvement over the panoptic-based semantic segmentation method,respectively.展开更多
基金supported in part by the Natural Science Foundation of Zhejiang Province(LZ22F020005,LTGS23E070001)National Natural Science Foundation of China(62076185,U1809209).
文摘Lupus Nephritis(LN)is a significant risk factor for morbidity and mortality in systemic lupus erythematosus,and nephropathology is still the gold standard for diagnosing LN.To assist pathologists in evaluating histopathological images of LN,a 2D Rényi entropy multi-threshold image segmentation method is proposed in this research to apply to LN images.This method is based on an improved Cuckoo Search(CS)algorithm that introduces a Diffusion Mechanism(DM)and an Adaptiveβ-Hill Climbing(AβHC)strategy called the DMCS algorithm.The DMCS algorithm is tested on 30 benchmark functions of the IEEE CEC2017 dataset.In addition,the DMCS-based multi-threshold image segmentation method is also used to segment renal pathological images.Experimental results show that adding these two strategies improves the DMCS algorithm's ability to find the optimal solution.According to the three image quality evaluation metrics:PSNR,FSIM,and SSIM,the proposed image segmentation method performs well in image segmentation experiments.Our research shows that the DMCS algorithm is a helpful image segmentation method for renal pathological images.
基金funded by the Henan Science and Technology research project(222103810042)Support by the open project of scientific research platform of grain information processing center of Henan University of Technology(KFJJ-2021-108)+1 种基金Support by the innovative funds plan of Henan University of Technology(2021ZKCJ14)Henan University of Technology Youth Backbone Teacher Program.
文摘The application of transformer networks and feature fusion models in medical image segmentation has aroused considerable attention within the academic circle.Nevertheless,two main obstacles persist:(1)the restrictions of the Transformer network in dealing with locally detailed features,and(2)the considerable loss of feature information in current feature fusion modules.To solve these issues,this study initially presents a refined feature extraction approach,employing a double-branch feature extraction network to capture complex multi-scale local and global information from images.Subsequently,we proposed a low-loss feature fusion method-Multi-branch Feature Fusion Enhancement Module(MFFEM),which realizes effective feature fusion with minimal loss.Simultaneously,the cross-layer cross-attention fusion module(CLCA)is adopted to further achieve adequate feature fusion by enhancing the interaction between encoders and decoders of various scales.Finally,the feasibility of our method was verified using the Synapse and ACDC datasets,demonstrating its competitiveness.The average DSC(%)was 83.62 and 91.99 respectively,and the average HD95(mm)was reduced to 19.55 and 1.15 respectively.
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Supported by the National Basic Research Program of China(2011CB707904)the Natural Science Foundation of China(61472289)Hubei Province Natural Science Foundation of China(2015CFB254)
文摘Segmenting the lesion regions from the ultrasound （US） images is an important step in the intra-operative planning of some computer-aided therapies. High-Intensity Focused Ultrasound （HIFU）, as a popular computer-aided therapy, has been widely used in the treatment of uterine fibroids. However, such segmentation in HIFU remains challenge for two reasons： （1） the blurry or missing boundaries of lesion regions in the HIFU images and （2） the deformation of uterine fibroids caused by the patient＇s breathing or an external force during the US imaging process, which can lead to complex shapes of lesion regions. These factors have prevented classical active contour-based segmentation methods from yielding desired results for uterine fibroids in US images. In this paper, a novel active contour-based segmentation method is proposed, which utilizes the correlation information of target shapes among a sequence of images as prior knowledge to aid the existing active contour method. This prior knowledge can be interpreted as a unsupervised clustering of shapes prior modeling. Meanwhile, it is also proved that the shapes correlation has the low-rank property in a linear space, and the theory of matrix recovery is used as an effective tool to impose the proposed prior on an existing active contour model. Finally, an accurate method is developed to solve the proposed model by using the Augmented Lagrange Multiplier （ALM）. Experimental results from both synthetic and clinical uterine fibroids US image sequences demonstrate that the proposed method can consistently improve the performance of active contour models and increase the robustness against missing or misleading boundaries, and can greatly improve the efficiency of HIFU therapy.
基金supported by the National Key Technologies R & D Program of China (No.2009BAB48B02)the National High-Tech Research and Development Program of China (Nos.2010AA060278600 and 2008AA062101)
文摘Lots of noises and heterogeneous objects with various sizes coexist in a complex image,such as an ore image;the classical image thresholding method cannot effectively distinguish between ores.To segment ore objects with various sizes simultaneously,two adaptive windows in the image were chosen for each pixel;the gray value of windows was calculated by Otsu＇s threshold method.To extract the object skeleton,the definition principle of distance transformation templates was proposed.The ores linked together in a binary image were separated by distance transformation and gray reconstruction.The seed region of each object was picked up from the local maximum gray region of the reconstruction image.Starting from these seed regions,the watershed method was used to segment ore object effectively.The proposed algorithm marks and segments most objects from complex images precisely.
文摘In this study,a novel hybrid Water Cycle Moth-Flame Optimization(WCMFO)algorithm is proposed for multilevel thresholding brain image segmentation in Magnetic Resonance(MR)image slices.WCMFO constitutes a hybrid between the two techniques,comprising the water cycle and moth-flame optimization algorithms.The optimal thresholds are obtained by maximizing the between class variance(Otsu’s function)of the image.To test the performance of threshold searching process,the proposed algorithm has been evaluated on standard benchmark of ten axial T2-weighted brain MR images for image segmentation.The experimental outcomes infer that it produces better optimal threshold values at a greater and quicker convergence rate.In contrast to other state-of-the-art methods,namely Adaptive Wind Driven Optimization(AWDO),Adaptive Bacterial Foraging(ABF)and Particle Swarm Optimization(PSO),the proposed algorithm has been found to be better at producing the best objective function,Peak Signal-to-Noise Ratio(PSNR),Standard Deviation(STD)and lower computational time values.Further,it was observed thatthe segmented image gives greater detail when the threshold level increases.Moreover,the statistical test result confirms that the best and mean values are almost zero and the average difference between best and mean value 1.86 is obtained through the 30 executions of the proposed algorithm.Thus,these images will lead to better segments of gray,white and cerebrospinal fluid that enable better clinical choices and diagnoses using a proposed algorithm.
基金This project is supported by National Natural Science Foundation of China(No.50275120,No.50535030)Great Science and Technology Project of Xi'an City,China(No.CX200206)
文摘Aiming at the problem that the existence of disturbances on the edges of light-stripe makes the segmentation of the light-stripes images difficult, a new segmentation algorithm based on edge-searching is presented. It firstly calculates every edge pixel's horizontal coordinate grads to produce the corresponding grads-edge, then uses a designed length-variable l D template to scan the light-stripes' grads-edges. The template is able to find the disturbances with different width utilizing the distributing character of the edge disturbances. The found disturbances are eliminated finally. The algorithm not only can smoothly segment the light-stripes images, but also eliminate most disturbances on the light-stripes' edges without damaging the light-stripes images' 3D information. A practical example of using the proposed algorithm is given in the end. It is proved that the efficiency of the algorithm has been improved obviously by comparison.
基金Project (No. 60675023) supported by the National Natural Science Foundation of China
文摘Segmentation of the bladder in computerized tomography(CT) images is an important step in radiation therapy planning of prostate cancer. We present a new segmentation scheme to automatically delineate the bladder contour in CT images with three major steps. First,we use the mean shift algorithm to obtain a clustered image containing the rough contour of the bladder,which is then extracted in the second step by applying a region-growing algorithm with the initial seed point selected from a line-by-line scanning process. The third step is to refine the bladder contour more accurately using the rolling-ball algorithm. These steps are then extended to segment the bladder volume in a slice-by-slice manner. The obtained results were compared to manual segmentation by radiation oncologists. The average values of sensitivity,specificity,positive predictive value,negative predictive value,and Hausdorff distance are 86.5%,96.3%,90.5%,96.5%,and 2.8 pixels,respectively. The results show that the bladder can be accurately segmented.
基金supported by the Fundamental Research Funds for the Central Universities of China (Grant No.2013SCU11006)the Key Laboratory of Digital Mapping and Land Information Application of National Administration of Surveying,Mapping and Geoinformation of China (Grant No.DM2014SC02)the Key Laboratory of Geospecial Information Technology,Ministry of Land and Resources of China (Grant No.KLGSIT201504)
文摘Using conventional Mean Shift Algorithm to segment high spatial resolution Remote sensing images of mountainous areas usually leads to an unsatisfactory result, due to its rich texture information. In this paper, we propose an improved Mean Shift Algorithm in consideration of the characteristics of these images. First, images were classified into several homogeneous color regions and texture regions by conducting variance detection on the color space. Next, each homogeneous color region was directly segmented to generate the preliminary results by applying the Mean Shift Algorithm. For each texture region, we conduct a high-dimensional feature space by extracting information such as color, texture and shape comprehensively, and work out a proper bandwidth according to the normalized distribution density. Then the bandwidth variable Mean Shift Algorithm was applied to obtain segmentation results by conducting the pattern classification in feature space. Last, the final results were obtained by merging these regions by means of the constructed cost functions and removing the oversegmented regions from the merged regions. It has been experimentally segmented on the high spatial resolution remote sensing images collected by Quickbird and Unmanned Aerial Vehicle(UAV). We put forward an approach to evaluate the segmentation results by using the segmentation matching index(SMI). This takes into consideration both the area and the spectrum. The experimental results suggest that the improved Mean Shift Algorithm outperforms the conventional one in terms of accuracy of segmentation.
基金the National Natural Science Foundation of China(Grants No 61702274)the Natural Science Foundation of Jiangsu Province(Grants No BK20170958).
文摘Magnetic resonance imaging(MRI)has been a prevalence technique for breast cancer diagnosis.Computer-aided detection and segmentation of lesions from MRIs plays a vital role for the MRI-based disease analysis.There are two main issues of the existing breast lesion segmentation techniques:requir ing manual delineation of Regions of Interests(ROIs)as a step of initialization;and requiring a large amount of labeled images for model construction or parameter lear ning,while in real clinical or experimental settings,it is highly challenging to get suficient labeled MRIs.To resolve these issues,this work proposes a semi-supervised method for breast tumor segmentation based on super voxel strategies.After image segmentation with advanced cluster techniques,we take a supervised learning step to classify the tumor and nontumor patches in order to automatically locate the tumor regions in an MRI To obtain the opt imal performance of tumor extraction,we take extensive experiments to learn par ameters for tumor segmentation and dassification,and design 225 classifiers corresponding to diferent parameter settings.We call the proposed method as Semi supervised Tumor Segmentation(SSTS),and apply it to both mass and nonmass lesions.Experimental results show better performance of SsTS compared with five state of-the art methods.
基金supported by the National Natural Science Foundation of China(4117132741301361)+2 种基金the National Key Basic Research Program of China(973 Program)(2012CB719903)the Science and Technology Project of Ministry of Transport of People’s Republic of China(2012-364-X11-803)the Shanghai Municipal Natural Science Foundation(12ZR1433200)
文摘Segmentation is the key step in auto-interpretation of high-resolution spaceborne synthetic aperture radar（SAR） images. A novel method is proposed based on integrating the geometric active contour（GAC） and the support vector machine（SVM）models. First, the images are segmented by using SVM and textural statistics. A likelihood measurement for every pixel is derived by using the initial segmentation. The Chan-Vese model then is modified by adding two items： the likelihood and the distance between the initial segmentation and the evolving contour. Experimental results using real SAR images demonstrate the good performance of the proposed method compared to several classic GAC models.
基金supported by the Natural Science Foundation of Zhejiang Province(LY21F020001,LZ22F020005)National Natural Science Foundation of China(62076185,U1809209)+1 种基金Science and Technology Plan Project of Wenzhou,China(ZG2020026)We also acknowledge the respected editor and reviewers'efforts to enhance the quality of this research.
文摘Coronavirus Disease 2019(COVID-19)is the most severe epidemic that is prevalent all over the world.How quickly and accurately identifying COVID-19 is of great significance to controlling the spread speed of the epidemic.Moreover,it is essential to accurately and rapidly identify COVID-19 lesions by analyzing Chest X-ray images.As we all know,image segmentation is a critical stage in image processing and analysis.To achieve better image segmentation results,this paper proposes to improve the multi-verse optimizer algorithm using the Rosenbrock method and diffusion mechanism named RDMVO.Then utilizes RDMVO to calculate the maximum Kapur’s entropy for multilevel threshold image segmentation.This image segmentation scheme is called RDMVO-MIS.We ran two sets of experiments to test the performance of RDMVO and RDMVO-MIS.First,RDMVO was compared with other excellent peers on IEEE CEC2017 to test the performance of RDMVO on benchmark functions.Second,the image segmentation experiment was carried out using RDMVO-MIS,and some meta-heuristic algorithms were selected as comparisons.The test image dataset includes Berkeley images and COVID-19 Chest X-ray images.The experimental results verify that RDMVO is highly competitive in benchmark functions and image segmentation experiments compared with other meta-heuristic algorithms.
基金We deeply acknowledge Taif University for supporting this study through Taif University Researchers Supporting Project number(TURSP-2020/115),Taif University,Taif,Saudi Arabia.
文摘Leukaemia is a type of blood cancer that is caused by undeveloped White Blood Cells(WBC),and it is also called a blast blood cell.In the marrow of human bones,leukaemia is developed and is responsible for blood cell generation with leukocytes and WBC,and if any cell gets blasted,then it may become a cause of death.Therefore,the diagnosis of leukaemia in its early stages helps greatly in the treatment along with saving human lives.Subsequently,in terms of detection,image segmentation techniques play a vital role,and they turn out to be the important image processing steps for the extraction of feature patterns from the Acute Lymphoblastic Leukaemia(ALL)type of blood cancer.Moreover,the image segmentation technique focuses on the division of cells by segmenting a microscopic image into background and cancer blood cell nucleus,which is well-known as the Region Of Interest(ROI).As a result,in this article,we attempt to build a segmentation technique capable of solving blood cell nucleus segmentation issues using four distinct scenarios,including K-means,FCM(Fuzzy Cmeans),K-means with FFA(Firefly Algorithm),and FCM with FFA.Also,we determine the most effective method of blood cell nucleus segmentation,which we subsequently use for the Leukaemia classification model.Finally,using the Convolution Neural Network(CNN)as a classifier,we developed a leukaemia cancer classification model from the microscopic images.The proposed system’s classification accuracy is tested using the CNN to test the model on the ALL-IDB dataset and equate it to the current state of the art.In terms of experimental analysis,we observed that the accuracy of the model is near to 99%,and it is far better than other existing models that are designed to segment and classify the types of leukaemia cancer in terms of ALL.
基金Under the auspices of National Natural Science Foundation of China (No. 30370267)Key Project of Jilin Provincial Science & Technology Department (No. 20075014)
文摘Remote sensing image segmentation is the basis of image understanding and analysis. However,the precision and the speed of segmentation can not meet the need of image analysis,due to strong uncertainty and rich texture details of remote sensing images. We proposed a new segmentation method based on Adaptive Genetic Algorithm(AGA) and Alternative Fuzzy C-Means(AFCM) . Segmentation thresholds were identified by AGA. Then the image was segmented by AFCM. The results indicate that the precision and the speed of segmentation have been greatly increased,and the accuracy of threshold selection is much higher compared with traditional Otsu and Fuzzy C-Means(FCM) segmentation methods. The segmentation results also show that multi-thresholds segmentation has been achieved by combining AGA with AFCM.
文摘This paper presents a novel computerized technique for the segmentation of nuclei in hematoxylin and eosin(H&E)stained histopathology images.The purpose of this study is to overcome the challenges faced in automated nuclei segmentation due to the diversity of nuclei structures that arise from differences in tissue types and staining protocols,as well as the segmentation of variable-sized and overlapping nuclei.To this extent,the approach proposed in this study uses an ensemble of the UNet architecture with various Convolutional Neural Networks(CNN)architectures as encoder backbones,along with stain normalization and test time augmentation,to improve segmentation accuracy.Additionally,this paper employs a Structure-Preserving Color Normalization(SPCN)technique as a preprocessing step for stain normalization.The proposed model was trained and tested on both single-organ and multi-organ datasets,yielding an F1 score of 84.11%,mean Intersection over Union(IoU)of 81.67%,dice score of 84.11%,accuracy of 92.58%and precision of 83.78%on the multi-organ dataset,and an F1 score of 87.04%,mean IoU of 86.66%,dice score of 87.04%,accuracy of 96.69%and precision of 87.57%on the single-organ dataset.These findings demonstrate that the proposed model ensemble coupled with the right pre-processing and post-processing techniques enhances nuclei segmentation capabilities.
文摘A leukocyte segmentation method based on S component and B component images is proposed.Threshold segmentation operation is applied to get two binary images in S component and B component images.The samples used in this study are peripheral blood smears.It is easy tofind from the two binary images that gray values are the same at every corresponding pixels in theleukocyte cytoplasm region,but opposite in the other regions.The feature shows that "IMAGEAND"operation can be employed on the two binary images to segment the cytoplasm region ofleukocyte.By doing"IMAGE XOR"operation between cytoplasn region and nucleus region,theleukocyte segment ation can be retrieved effectively.The segmentation accuracy is evaluated by comparing the segmentation result of the proposed method with the manual segmentation by ahematologist.Experiment results show that the proposed method is of a higher segmentationaccuracy and it also performs well when leukocytes overlap_with erythrocytes.The averagesegmentation accuracy of the proposed method reaches 97.7%for segmenting five types ofleukocyte.Good segmentation results provide an important foundation for leukocytes aut omaticrecognition.
基金supported by the National Natural Science Foundation of China(Grant Nos.81871508 and 61773246)the Major Program of Shandong Province Natural Science Foundation(Grant No.ZR2019ZD04 and ZR2018ZB0419)the Taishan Scholar Program of Shandong Province of China(Grant No.TSHW201502038).
文摘Multispectral imaging (MSI) technique is often used to capture imagesof the fundus by illuminating it with different wavelengths of light. However,these images are taken at different points in time such that eyeball movementscan cause misalignment between consecutive images. The multispectral imagesequence reveals important information in the form of retinal and choroidal bloodvessel maps, which can help ophthalmologists to analyze the morphology of theseblood vessels in detail. This in turn can lead to a high diagnostic accuracy of several diseases. In this paper, we propose a novel semi-supervised end-to-end deeplearning framework called “Adversarial Segmentation and Registration Nets”(ASRNet) for the simultaneous estimation of the blood vessel segmentation andthe registration of multispectral images via an adversarial learning process. ASRNet consists of two subnetworks: (i) A segmentation module S that fulfills theblood vessel segmentation task, and (ii) A registration module R that estimatesthe spatial correspondence of an image pair. Based on the segmention-drivenregistration network, we train the segmentation network using a semi-supervisedadversarial learning strategy. Our experimental results show that the proposedASRNet can achieve state-of-the-art accuracy in segmentation and registrationtasks performed with real MSI datasets.
基金This research was funded by the Guangdong Provincial Natural Science Foundation(2023A1515012833J.B.)+6 种基金Science and Technology Program of Guangzhou(202201010544J.B.)the National Natural Science Foundation of China(61901192J.B.)National Key Research and Development Project(2019YFC0120100,2019YFC0121907 and 2019YFC0121904H.W.,J.B.and Y.L.)Guangdong Provincial Key Laboratory of Traditional Chinese Medicine Informatization(2021B1212040007).
文摘Objective:This study was aimed at validating the accuracy of a proposed algorithm for fully automatic 3D left atrial segmentation and to compare its performance with existing deep learning algorithms.Methods:A two-stage method with a shared 3D U-Net was proposed to segment the 3D left atrium.In this archi-tecture,the 3D U-Net was used to extract 3D features,a two-stage strategy was used to decrease segmentation error caused by the class imbalance problem,and the shared network was designed to decrease model complexity.Model performance was evaluated with the DICE score,Jaccard index and Hausdorff distance.Results:Algorithm development and evaluation were performed with a set of 100 late gadolinium-enhanced car-diovascular magnetic resonance images.Our method achieved a DICE score of 0.918,a Jaccard index of 0.848 and a Hausdorff distance of 1.211,thus,outperforming existing deep learning algorithms.The best performance of the proposed model(DICE:0.851;Jaccard:0.750;Hausdorff distance:4.382)was also achieved on a publicly available 2013 image data set.Conclusion:The proposed two-stage method with a shared 3D U-Net is an efficient algorithm for fully automatic 3D left atrial segmentation.This study provides a solution for processing large datasets in resource-constrained applica-tions.Significance Statement:Studying atrial structure directly is crucial for comprehending and managing atrial fibril-lation(AF).Accurate reconstruction and measurement of atrial geometry for clinical purposes remains challenging,despite potential improvements in the visibility of AF-associated structures with late gadolinium-enhanced magnetic resonance imaging.This difficulty arises from the varying intensities caused by increased tissue enhancement and artifacts,as well as variability in image quality.Therefore,an efficient algorithm for fully automatic 3D left atrial seg-mentation is proposed in the present study.
基金This work is supported by Projects of International Cooperation and Exchanges,National Natural Science Foundation of China(NSFC)(Grant No.:30911120497)the National 973 project Grant No.:2011CB933103.
文摘Stroke and heart attack,which could be led by a kind of cerebrovascular and cardiovascular disease named as atherosclerosis,would seriously cause human morbidity and mortality.It is important for the early stage diagnosis and monitoring medical intervention of the atherosclerosis.Carotid stenosis is a classical atherosclerotic lesion with vessel wall narrowing down and accumulating plaques burden.The carotid artery of intima-media thickness(IMT)is a key indicator to the disease.With the development of computer assisted diagnosis technology,the imaging techniques,segmentation algorithms,measurement methods,and evaluation tools have made considerable progress.Ultrasound imaging,being real-time,economic,reliable,and safe,now seems to become a standard in vascular assessment methodology especially for the measurement of IMT.This review firstly attempts to discuss the clinical relevance of measurements in clinical practice at first,and then followed by the challenges that one has to face when approaching the segmentation of ultrasound images.Secondly,the commonly used methods for the IMT segmentation and measurement are presented.Thirdly,discussion and evaluation of different segmentation techniques are performed.An overview of summary and future perspectives is given finally.
基金This work was supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.2020R1F1A1074885)was supported by the Brain Korea 21 Project in 2021(No.4199990114242).
文摘Objective and quantitative assessment of skin conditions is essential for cosmeceutical studies and research on skin aging and skin regeneration.Various handcraft-based image processing methods have been proposed to evaluate skin conditions objectively,but they have unavoidable disadvantages when used to analyze skin features accurately.This study proposes a hybrid segmentation scheme consisting of Deeplab v3+with an Inception-ResNet-v2 backbone,LightGBM,and morphological processing(MP)to overcome the shortcomings of handcraft-based approaches.First,we apply Deeplab v3+with an Inception-ResNet-v2 backbone for pixel segmentation of skin wrinkles and cells.Then,LightGBM and MP are used to enhance the pixel segmentation quality.Finally,we determine several skin features based on the results of wrinkle and cell segmentation.Our proposed segmentation scheme achieved a mean accuracy of 0.854,mean of intersection over union of 0.749,and mean boundary F1 score of 0.852,which achieved 1.1%,6.7%,and 14.8%improvement over the panoptic-based semantic segmentation method,respectively.
