Supervised Machine Learning Based Multi-Task Artificial Intelligence Classification of Retinopathies

被引:48
作者
Alam, Minhaj [1 ]
Le, David [1 ]
Lim, Jennifer, I [2 ]
Chan, Robison V. P. [2 ]
Yao, Xincheng [1 ,2 ]
机构
[1] Univ Illinois, Dept Bioengn, Chicago, IL 60607 USA
[2] Univ Illinois, Dept Ophthalmol & Visual Sci, Chicago, IL 60612 USA
关键词
ophthalmology; diabetic retinopathy; sickle cell retinopathy; quantitative analysis; computer aided diagnosis; artificial intelligence; support vector machine; optical coherence tomography angiography; COHERENCE TOMOGRAPHY ANGIOGRAPHY; SICKLE-CELL RETINOPATHY; DIABETIC-RETINOPATHY; RETINAL IMAGES; MICROVASCULAR DENSITY; MACULAR DEGENERATION; AUTOMATED DETECTION; QUANTIFICATION; VALIDATION; DIAGNOSIS;
D O I
10.3390/jcm8060872
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Artificial intelligence (AI) classification holds promise as a novel and affordable screening tool for clinical management of ocular diseases. Rural and underserved areas, which suffer from lack of access to experienced ophthalmologists may particularly benefit from this technology. Quantitative optical coherence tomography angiography (OCTA) imaging provides excellent capability to identify subtle vascular distortions, which are useful for classifying retinovascular diseases. However, application of AI for differentiation and classification of multiple eye diseases is not yet established. In this study, we demonstrate supervised machine learning based multi-task OCTA classification. We sought (1) to differentiate normal from diseased ocular conditions, (2) to differentiate different ocular disease conditions from each other, and (3) to stage the severity of each ocular condition. Quantitative OCTA features, including blood vessel tortuosity (BVT), blood vascular caliber (BVC), vessel perimeter index (VPI), blood vessel density (BVD), foveal avascular zone (FAZ) area (FAZ-A), and FAZ contour irregularity (FAZ-CI) were fully automatically extracted from the OCTA images. A stepwise backward elimination approach was employed to identify sensitive OCTA features and optimal-feature-combinations for the multi-task classification. For proof-of-concept demonstration, diabetic retinopathy (DR) and sickle cell retinopathy (SCR) were used to validate the supervised machine leaning classifier. The presented AI classification methodology is applicable and can be readily extended to other ocular diseases, holding promise to enable a mass-screening platform for clinical deployment and telemedicine.
引用
收藏
页数:15
相关论文
共 36 条
[1]   Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices [J].
Abramoff, Michael D. ;
Lavin, Philip T. ;
Birch, Michele ;
Shah, Nilay ;
Folk, James C. .
NPJ DIGITAL MEDICINE, 2018, 1
[2]   Automated detection of exudates in colored retinal images for diagnosis of diabetic retinopathy [J].
Akram, M. Usman ;
Tariq, Anam ;
Anjum, M. Almas ;
Javed, M. Younus .
APPLIED OPTICS, 2012, 51 (20) :4858-4866
[3]   QUANTITATIVE OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY FEATURES FOR OBJECTIVE CLASSIFICATION AND STAGING OF DIABETIC RETINOPATHY [J].
Alam, Minhaj ;
Zhang, Yue ;
Lim, Jennifer, I ;
Chan, Robison V. P. ;
Yang, Min ;
Yao, Xincheng .
RETINA-THE JOURNAL OF RETINAL AND VITREOUS DISEASES, 2020, 40 (02) :322-332
[4]   Computer-aided classification of sickle cell retinopathy using quantitative features in optical coherence tomography angiography [J].
Alam, Minhaj ;
Thapa, Damber ;
Lim, Jennifer I. ;
Cao, Dingcai ;
Yao, Xincheng .
BIOMEDICAL OPTICS EXPRESS, 2017, 8 (09) :4206-4216
[5]   Quantitative characteristics of sickle cell retinopathy in optical coherence tomography angiography [J].
Alam, Minhaj ;
Thapa, Damber ;
Lim, Jennifer I. ;
Cao, Dingcai ;
Yao, Xincheng .
BIOMEDICAL OPTICS EXPRESS, 2017, 8 (03) :1741-1753
[6]   MACULAR AND PERIMACULAR VASCULAR REMODELING IN SICKLING HEMOGLOBINOPATHIES [J].
ASDOURIAN, GK ;
NAGPAL, KC ;
BUSSE, B ;
GOLDBAUM, M ;
PATRIANAKOS, D ;
RABB, MF ;
GOLDBERG, MF .
BRITISH JOURNAL OF OPHTHALMOLOGY, 1976, 60 (06) :431-453
[7]   Statistical Model of Optical Coherence Tomography Angiography Parameters That Correlate With Severity of Diabetic Retinopathy [J].
Ashraf, Mohammed ;
Nesper, Peter L. ;
Jampol, Lee M. ;
Yu, Fei ;
Fawzi, Amani A. .
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2018, 59 (10) :4292-4298
[8]   Linking Retinal Microvasculature Features With Severity of Diabetic Retinopathy Using Optical Coherence Tomography Angiography [J].
Bhanushali, Devanshi ;
Anegondi, Neha ;
Gadde, Santosh G. K. ;
Srinivasan, Priya ;
Chidambara, Lavanya ;
Yadav, Naresh Kumar ;
Roy, Abhijit Sinha .
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2016, 57 (09) :OCT519-OCT525
[9]   Automated Grading of Age-Related Macular Degeneration From Color Fundus Images Using Deep Convolutional Neural Networks [J].
Burlina, Philippe M. ;
Joshi, Neil ;
Pekala, Michael ;
Pacheco, Katia D. ;
Freund, David E. ;
Bressler, Neil M. .
JAMA OPHTHALMOLOGY, 2017, 135 (11) :1170-1176
[10]   Should We Add Screening of Age-Related Macular Degeneration to Current Screening Programs for Diabetic Retinopathy? [J].
Chew, Emily Y. ;
Schachat, Andrew P. .
OPHTHALMOLOGY, 2015, 122 (11) :2155-2156