Retinal vessel segmentation is a challenging medical task owing to small size of dataset,micro blood vessels and low image contrast.To address these issues,we introduce a novel convolutional neural network in this pap...Retinal vessel segmentation is a challenging medical task owing to small size of dataset,micro blood vessels and low image contrast.To address these issues,we introduce a novel convolutional neural network in this paper,which takes the advantage of both adversarial learning and recurrent neural network.An iterative design of network with recurrent unit is performed to refine the segmentation results from input retinal image gradually.Recurrent unit preserves high-level semantic information for feature reuse,so as to output a sufficiently refined segmentation map instead of a coarse mask.Moreover,an adversarial loss is imposing the integrity and connectivity constraints on the segmented vessel regions,thus greatly reducing topology errors of segmentation.The experimental results on the DRIVE dataset show that our method achieves area under curve and sensitivity of 98.17%and 80.64%,respectively.Our method achieves superior performance in retinal vessel segmentation compared with other existing state-of-the-art methods.展开更多
AIM：To apply the multifractal analysis method as a quantitative approach to a comprehensive description of the microvascular network architecture of the normal human retina.METHODS：Fifty volunteers were enrolled in ...AIM：To apply the multifractal analysis method as a quantitative approach to a comprehensive description of the microvascular network architecture of the normal human retina.METHODS：Fifty volunteers were enrolled in this study in the Ophthalmological Clinic of Cluj-Napoca,Romania,between January 2012 and January 2014. A set of 100 segmented and skeletonised human retinal images,corresponding to normal states of the retina were studied. An automatic unsupervised method for retinal vessel segmentation was applied before multifractal analysis. The multifractal analysis of digital retinal images was made with computer algorithms,applying the standard boxcounting method. Statistical analyses were performed using the Graph Pad In Stat software.RESULTS：The architecture of normal human retinal microvascular network was able to be described using the multifractal geometry. The average of generalized dimensions（D_q）for q=0,1,2,the width of the multifractal spectrum（Δα=α_（max）-α_（min））and the spectrum arms＇ heights difference（│Δf│）of the normal images were expressed as mean±standard deviation（SD）：for segmented versions,D_0=1.7014±0.0057; D_1=1.6507±0.0058; D_2=1.5772±0.0059; Δα=0.92441±0.0085; │Δf│= 0.1453±0.0051; for skeletonised versions,D_0=1.6303±0.0051; D_1=1.6012±0.0059; D_2=1.5531± 0.0058; Δα=0.65032±0.0162; │Δf│= 0.0238±0.0161. The average of generalized dimensions（D_q）for q=0,1,2,the width of the multifractal spectrum（Δα）and the spectrum arms＇ heights difference（│Δf│）of the segmented versions was slightly greater than the skeletonised versions.CONCLUSION：The multifractal analysis of fundus photographs may be used as a quantitative parameter for the evaluation of the complex three-dimensional structure of the retinal microvasculature as a potential marker for early detection of topological changes associated with retinal diseases.展开更多
Retinal images play an essential role in the early diagnosis of ophthalmic diseases.Automatic segmentation of retinal vessels in color fundus images is challenging due to the morphological differences between the reti...Retinal images play an essential role in the early diagnosis of ophthalmic diseases.Automatic segmentation of retinal vessels in color fundus images is challenging due to the morphological differences between the retinal vessels and the low-contrast background.At the same time,automated models struggle to capture representative and discriminative retinal vascular features.To fully utilize the structural information of the retinal blood vessels,we propose a novel deep learning network called Pre-Activated Convolution Residual and Triple Attention Mechanism Network(PCRTAM-Net).PCRTAM-Net uses the pre-activated dropout convolution residual method to improve the feature learning ability of the network.In addition,the residual atrous convolution spatial pyramid is integrated into both ends of the network encoder to extract multiscale information and improve blood vessel information flow.A triple attention mechanism is proposed to extract the structural information between vessel contexts and to learn long-range feature dependencies.We evaluate the proposed PCRTAM-Net on four publicly available datasets,DRIVE,CHASE_DB1,STARE,and HRF.Our model achieves state-of-the-art performance of 97.10%,97.70%,97.68%,and 97.14%for ACC and 83.05%,82.26%,84.64%,and 81.16%for F1,respectively.展开更多
文摘Retinal vessel segmentation is a challenging medical task owing to small size of dataset,micro blood vessels and low image contrast.To address these issues,we introduce a novel convolutional neural network in this paper,which takes the advantage of both adversarial learning and recurrent neural network.An iterative design of network with recurrent unit is performed to refine the segmentation results from input retinal image gradually.Recurrent unit preserves high-level semantic information for feature reuse,so as to output a sufficiently refined segmentation map instead of a coarse mask.Moreover,an adversarial loss is imposing the integrity and connectivity constraints on the segmented vessel regions,thus greatly reducing topology errors of segmentation.The experimental results on the DRIVE dataset show that our method achieves area under curve and sensitivity of 98.17%and 80.64%,respectively.Our method achieves superior performance in retinal vessel segmentation compared with other existing state-of-the-art methods.
基金the Program"Partnerships in priority domains"with the support of the National Education Ministry,the Executive Agency for Higher Education,Research,Development and Innovation Funding (UEFISCDI),Romania (Project code:PN-II-PT-PCCA-2013-4-1232)
文摘AIM：To apply the multifractal analysis method as a quantitative approach to a comprehensive description of the microvascular network architecture of the normal human retina.METHODS：Fifty volunteers were enrolled in this study in the Ophthalmological Clinic of Cluj-Napoca,Romania,between January 2012 and January 2014. A set of 100 segmented and skeletonised human retinal images,corresponding to normal states of the retina were studied. An automatic unsupervised method for retinal vessel segmentation was applied before multifractal analysis. The multifractal analysis of digital retinal images was made with computer algorithms,applying the standard boxcounting method. Statistical analyses were performed using the Graph Pad In Stat software.RESULTS：The architecture of normal human retinal microvascular network was able to be described using the multifractal geometry. The average of generalized dimensions（D_q）for q=0,1,2,the width of the multifractal spectrum（Δα=α_（max）-α_（min））and the spectrum arms＇ heights difference（│Δf│）of the normal images were expressed as mean±standard deviation（SD）：for segmented versions,D_0=1.7014±0.0057; D_1=1.6507±0.0058; D_2=1.5772±0.0059; Δα=0.92441±0.0085; │Δf│= 0.1453±0.0051; for skeletonised versions,D_0=1.6303±0.0051; D_1=1.6012±0.0059; D_2=1.5531± 0.0058; Δα=0.65032±0.0162; │Δf│= 0.0238±0.0161. The average of generalized dimensions（D_q）for q=0,1,2,the width of the multifractal spectrum（Δα）and the spectrum arms＇ heights difference（│Δf│）of the segmented versions was slightly greater than the skeletonised versions.CONCLUSION：The multifractal analysis of fundus photographs may be used as a quantitative parameter for the evaluation of the complex three-dimensional structure of the retinal microvasculature as a potential marker for early detection of topological changes associated with retinal diseases.
基金supported by the Open Funds from Guangxi Key Laboratory of Image and Graphic Intelligent Processing under Grant No.GIIP2209the National Natural Science Foundation of China under Grant Nos.62172120 and 62002082the Natural Science Foundation of Guangxi Province of China under Grant Nos.2019GXNSFAA245014 and 2020GXNSFBA238014.
文摘Retinal images play an essential role in the early diagnosis of ophthalmic diseases.Automatic segmentation of retinal vessels in color fundus images is challenging due to the morphological differences between the retinal vessels and the low-contrast background.At the same time,automated models struggle to capture representative and discriminative retinal vascular features.To fully utilize the structural information of the retinal blood vessels,we propose a novel deep learning network called Pre-Activated Convolution Residual and Triple Attention Mechanism Network(PCRTAM-Net).PCRTAM-Net uses the pre-activated dropout convolution residual method to improve the feature learning ability of the network.In addition,the residual atrous convolution spatial pyramid is integrated into both ends of the network encoder to extract multiscale information and improve blood vessel information flow.A triple attention mechanism is proposed to extract the structural information between vessel contexts and to learn long-range feature dependencies.We evaluate the proposed PCRTAM-Net on four publicly available datasets,DRIVE,CHASE_DB1,STARE,and HRF.Our model achieves state-of-the-art performance of 97.10%,97.70%,97.68%,and 97.14%for ACC and 83.05%,82.26%,84.64%,and 81.16%for F1,respectively.
