Diabetes problems can lead to an eye disease called Diabetic Retinopathy(DR),which permanently damages the blood vessels in the retina.If not treated early,DR becomes a significant reason for blindness.To identify the...Diabetes problems can lead to an eye disease called Diabetic Retinopathy(DR),which permanently damages the blood vessels in the retina.If not treated early,DR becomes a significant reason for blindness.To identify the DR and determine the stages,medical tests are very labor-intensive,expensive,and timeconsuming.To address the issue,a hybrid deep and machine learning techniquebased autonomous diagnostic system is provided in this paper.Our proposal is based on lesion segmentation of the fundus images based on the LuNet network.Then a Refined Attention Pyramid Network(RAPNet)is used for extracting global and local features.To increase the performance of the classifier,the unique features are selected from the extracted feature set using Aquila Optimizer(AO)algorithm.Finally,the LightGBM model is applied to classify the input image based on the severity.Several investigations have been done to analyze the performance of the proposed framework on three publically available datasets(MESSIDOR,APTOS,and IDRiD)using several performance metrics such as accuracy,precision,recall,and f1-score.The proposed classifier achieves 99.29%,99.35%,and 99.31%accuracy for these three datasets respectively.The outcomes of the experiments demonstrate that the suggested technique is effective for disease identification and reliable DR grading.展开更多
Diabetic retinopathy(DR)is one of the most common retinal vascular diseases and one of the main causes of blindness worldwide.Early detection and treatment can effectively delay vision decline and even blindness in pa...Diabetic retinopathy(DR)is one of the most common retinal vascular diseases and one of the main causes of blindness worldwide.Early detection and treatment can effectively delay vision decline and even blindness in patients with DR.In recent years,artificial intelligence(AI)models constructed by machine learning and deep learning(DL)algorithms have been widely used in ophthalmology research,especially in diagnosing and treating ophthalmic diseases,particularly DR.Regarding DR,AI has mainly been used in its diagnosis,grading,and lesion recognition and segmentation,and good research and application results have been achieved.This study summarizes the research progress in AI models based on machine learning and DL algorithms for DR diagnosis and discusses some limitations and challenges in AI research.展开更多
AIM:To compare the assessment outcomes of the characteristics of mild to moderate non-proliferative diabetic retinopathy(NPDR) established by fundus photography and fundus fluorescein angiography(FFA).METHODS:The fund...AIM:To compare the assessment outcomes of the characteristics of mild to moderate non-proliferative diabetic retinopathy(NPDR) established by fundus photography and fundus fluorescein angiography(FFA).METHODS:The fundus photos and FFA results of 260 patients with diabetes mellitus were reviewed.Diabetic retinopathy(DR) severity was graded based on the international classification standard.The microaneurysms,hemorrhages,and intraretinal microvascular abnormalities(IRMA) in FFA images of patients with mild to moderate NPDR were observed.The differences between the fundus photos and the FFA results were summarized,analyzed,and compared.RESULTS:The counting of intraretinal hemorrhages identified by FFA revealed that only 9 eyes(1.9%) had more than 20 intraretinal hemorrhages in all four quadrants;15 eyes(3.1%) had more than 20 intraretinal hemorrhages in three quadrants;26 eyes(5.4%) had over 20 intraretinal hemorrhages in two quadrants;and 37 eyes(7.7%) had more than 20 intraretinal hemorrhages in only one quadrant.Furthermore,the number of IRMAs appeared ≥4 in 17 eyes,3 in 35 eyes,2 in 69 eyes,and 1 in 93 eyes.CONCLUSION:FFA has higher detection accuracy of retinal angiopathy than fundus photography.FFA grading results are helpful for timely detection and proper treatment of lesions easily missed by fundus photography.展开更多
Diabetic Retinopathy(DR)is an eye disease that mainly affects people with diabetes.People affected by DR start losing their vision from an early stage even though the symptoms are identified only at the later stage.On...Diabetic Retinopathy(DR)is an eye disease that mainly affects people with diabetes.People affected by DR start losing their vision from an early stage even though the symptoms are identified only at the later stage.Once the vision is lost,it cannot be regained but can be prevented from causing any further damage.Early diagnosis of DR is required for preventing vision loss,for which a trained ophthalmologist is required.The clinical practice is time-consuming and is not much successful in identifying DR at early stages.Hence,Computer-Aided Diagnosis(CAD)system is a suitable alternative for screening and grading of DR for a larger population.This paper addresses the different stages in CAD system and the challenges in identifying and grading of DR by analyzing various recently evolved techniques.The performance metrics used to evaluate the Computer-Aided Diagnosis system for clinical practice is also discussed.展开更多
目的糖尿病性视网膜病变(diabetic retinopathy,DR)是一种常见的致盲性视网膜疾病,需要患者在早期就能够被诊断并接受治疗,否则将会造成永久性的视力丧失。能否检测到视网膜图像中的微小病变如微血管瘤,是糖尿病性视网膜病变分级的关键...目的糖尿病性视网膜病变(diabetic retinopathy,DR)是一种常见的致盲性视网膜疾病,需要患者在早期就能够被诊断并接受治疗,否则将会造成永久性的视力丧失。能否检测到视网膜图像中的微小病变如微血管瘤,是糖尿病性视网膜病变分级的关键。然而这些病变过于细小导致使用一般方法难以正确地辨别。为了解决这一问题,本文提出了一种基于多通道注意力选择机制的细粒度分级方法(fine-grained grading method based on multichannel attention selection,FGMAS)用于糖尿病性视网膜病变的分级。方法该方法结合了细粒度分类方法和多通道注意力选择机制,通过获取局部特征提升分级的准确度。此外考虑到每一层通道特征信息量与分类置信度的关系,本文引入了排序损失以优化每一层通道的信息量,用于获取更加具有信息量的局部区域。结果使用两个公开的视网膜数据集(Kaggle和Messidor)来评估提出的细粒度分级方法和多通道注意力选择机制的有效性。实验结果表明:FGMAS在Kaggle数据集上进行的五级分类任务中相较于现有方法,在平均准确度(average of classification accuracy,ACA)上取得了3.4%~10.4%的提升。尤其是对于病变点最小的1级病变,准确率提升了11%~18.9%。此外,本文使用FGMAS在Messidor数据集上进行二分类任务。在推荐转诊/不推荐转诊分类上FGMAS得到的准确度(accuracy,Acc)为0.912,比现有方法提升了0.1%~1.9%,同时AUC(area under the curve)为0.962,比现有方法提升了0.5%~9.9%;在正常/不正常分类上FGMAS得到的准确度为0.909,比现有方法提升了2.9%~8.8%,AUC为0.950,比现有方法提升了0.4%~8.9%。实验结果表明,本文方法在五分类和二分类上均优于现有方法。结论本文所提细粒度分级模型,综合了细粒度提取局部区域的思路以及多通道注意力选择机制,可以获得较为准确的分级结果。展开更多
文摘Diabetes problems can lead to an eye disease called Diabetic Retinopathy(DR),which permanently damages the blood vessels in the retina.If not treated early,DR becomes a significant reason for blindness.To identify the DR and determine the stages,medical tests are very labor-intensive,expensive,and timeconsuming.To address the issue,a hybrid deep and machine learning techniquebased autonomous diagnostic system is provided in this paper.Our proposal is based on lesion segmentation of the fundus images based on the LuNet network.Then a Refined Attention Pyramid Network(RAPNet)is used for extracting global and local features.To increase the performance of the classifier,the unique features are selected from the extracted feature set using Aquila Optimizer(AO)algorithm.Finally,the LightGBM model is applied to classify the input image based on the severity.Several investigations have been done to analyze the performance of the proposed framework on three publically available datasets(MESSIDOR,APTOS,and IDRiD)using several performance metrics such as accuracy,precision,recall,and f1-score.The proposed classifier achieves 99.29%,99.35%,and 99.31%accuracy for these three datasets respectively.The outcomes of the experiments demonstrate that the suggested technique is effective for disease identification and reliable DR grading.
基金Supported by Huzhou Science and Technology Planning Program(No.2019GY13).
文摘Diabetic retinopathy(DR)is one of the most common retinal vascular diseases and one of the main causes of blindness worldwide.Early detection and treatment can effectively delay vision decline and even blindness in patients with DR.In recent years,artificial intelligence(AI)models constructed by machine learning and deep learning(DL)algorithms have been widely used in ophthalmology research,especially in diagnosing and treating ophthalmic diseases,particularly DR.Regarding DR,AI has mainly been used in its diagnosis,grading,and lesion recognition and segmentation,and good research and application results have been achieved.This study summarizes the research progress in AI models based on machine learning and DL algorithms for DR diagnosis and discusses some limitations and challenges in AI research.
基金Supported by National Natural Science Foundation of China (No.U20A20363,No.81970776,No.81671844)Special Fund of the Academy of Medical Sciences of Heilongjiang Province for Scientific Research (No.CR201809)+2 种基金Natural Science Foundation of Heilongjiang Province,China (No.LH2020H039)Higher Education Reform Project of Heilongjiang Province,China (No.SJGY20180332)Heilongjiang Provincial Postdoctoral Research Fund (No.LBH-Z18221)。
文摘AIM:To compare the assessment outcomes of the characteristics of mild to moderate non-proliferative diabetic retinopathy(NPDR) established by fundus photography and fundus fluorescein angiography(FFA).METHODS:The fundus photos and FFA results of 260 patients with diabetes mellitus were reviewed.Diabetic retinopathy(DR) severity was graded based on the international classification standard.The microaneurysms,hemorrhages,and intraretinal microvascular abnormalities(IRMA) in FFA images of patients with mild to moderate NPDR were observed.The differences between the fundus photos and the FFA results were summarized,analyzed,and compared.RESULTS:The counting of intraretinal hemorrhages identified by FFA revealed that only 9 eyes(1.9%) had more than 20 intraretinal hemorrhages in all four quadrants;15 eyes(3.1%) had more than 20 intraretinal hemorrhages in three quadrants;26 eyes(5.4%) had over 20 intraretinal hemorrhages in two quadrants;and 37 eyes(7.7%) had more than 20 intraretinal hemorrhages in only one quadrant.Furthermore,the number of IRMAs appeared ≥4 in 17 eyes,3 in 35 eyes,2 in 69 eyes,and 1 in 93 eyes.CONCLUSION:FFA has higher detection accuracy of retinal angiopathy than fundus photography.FFA grading results are helpful for timely detection and proper treatment of lesions easily missed by fundus photography.
文摘Diabetic Retinopathy(DR)is an eye disease that mainly affects people with diabetes.People affected by DR start losing their vision from an early stage even though the symptoms are identified only at the later stage.Once the vision is lost,it cannot be regained but can be prevented from causing any further damage.Early diagnosis of DR is required for preventing vision loss,for which a trained ophthalmologist is required.The clinical practice is time-consuming and is not much successful in identifying DR at early stages.Hence,Computer-Aided Diagnosis(CAD)system is a suitable alternative for screening and grading of DR for a larger population.This paper addresses the different stages in CAD system and the challenges in identifying and grading of DR by analyzing various recently evolved techniques.The performance metrics used to evaluate the Computer-Aided Diagnosis system for clinical practice is also discussed.
文摘目的糖尿病性视网膜病变(diabetic retinopathy,DR)是一种常见的致盲性视网膜疾病,需要患者在早期就能够被诊断并接受治疗,否则将会造成永久性的视力丧失。能否检测到视网膜图像中的微小病变如微血管瘤,是糖尿病性视网膜病变分级的关键。然而这些病变过于细小导致使用一般方法难以正确地辨别。为了解决这一问题,本文提出了一种基于多通道注意力选择机制的细粒度分级方法(fine-grained grading method based on multichannel attention selection,FGMAS)用于糖尿病性视网膜病变的分级。方法该方法结合了细粒度分类方法和多通道注意力选择机制,通过获取局部特征提升分级的准确度。此外考虑到每一层通道特征信息量与分类置信度的关系,本文引入了排序损失以优化每一层通道的信息量,用于获取更加具有信息量的局部区域。结果使用两个公开的视网膜数据集(Kaggle和Messidor)来评估提出的细粒度分级方法和多通道注意力选择机制的有效性。实验结果表明:FGMAS在Kaggle数据集上进行的五级分类任务中相较于现有方法,在平均准确度(average of classification accuracy,ACA)上取得了3.4%~10.4%的提升。尤其是对于病变点最小的1级病变,准确率提升了11%~18.9%。此外,本文使用FGMAS在Messidor数据集上进行二分类任务。在推荐转诊/不推荐转诊分类上FGMAS得到的准确度(accuracy,Acc)为0.912,比现有方法提升了0.1%~1.9%,同时AUC(area under the curve)为0.962,比现有方法提升了0.5%~9.9%;在正常/不正常分类上FGMAS得到的准确度为0.909,比现有方法提升了2.9%~8.8%,AUC为0.950,比现有方法提升了0.4%~8.9%。实验结果表明,本文方法在五分类和二分类上均优于现有方法。结论本文所提细粒度分级模型,综合了细粒度提取局部区域的思路以及多通道注意力选择机制,可以获得较为准确的分级结果。
