TY - JOUR
T1 - PADAr
T2 - physician-oriented artificial intelligence-facilitating diagnosis aid for retinal diseases
AU - Lin, Po Kang
AU - Chiu, Yu Hsien
AU - Huang, Chiu Jung
AU - Wang, Chien Yao
AU - Pan, Mei Lien
AU - Wang, Da Wei
AU - Liao, Hong Yuan Mark
AU - Chen, Yong Sheng
AU - Kuan, Chieh Hsiung
AU - Lin, Shih Yen
AU - Chen, Li Fen
N1 - Publisher Copyright:
© The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.
PY - 2022/7/1
Y1 - 2022/7/1
N2 - Purpose: Retinopathy screening via digital imaging is promising for early detection and timely treatment, and tracking retinopathic abnormality over time can help to reveal the risk of disease progression. We developed an innovative physician-oriented artificial intelligence-facilitating diagnosis aid system for retinal diseases for screening multiple retinopathies and monitoring the regions of potential abnormality over time. Approach: Our dataset contains 4908 fundus images from 304 eyes with image-level annotations, including diabetic retinopathy, age-related macular degeneration, cellophane maculopathy, pathological myopia, and healthy control (HC). The screening model utilized a VGG-based feature extractor and multiple-binary convolutional neural network-based classifiers. Images in time series were aligned via affine transforms estimated through speeded-up robust features. Heatmaps of retinopathy were generated from the feature extractor using gradient-weighted class activation mapping++, and individual candidate retinopathy sites were identified from the heatmaps using clustering algorithm. Nested cross-validation with a train-to-test split of 80% to 20% was used to evaluate the performance of the screening model. Results: Our screening model achieved 99% accuracy, 93% sensitivity, and 97% specificity in discriminating between patients with retinopathy and HCs. For discriminating between types of retinopathy, our model achieved an averaged performance of 80% accuracy, 78% sensitivity, 94% specificity, 79% F1-score, and Cohen's kappa coefficient of 0.70. Moreover, visualization results were also shown to provide reasonable candidate sites of retinopathy. Conclusions: Our results demonstrated the capability of the proposed model for extracting diagnostic information of the abnormality and lesion locations, which allows clinicians to focus on patient-centered treatment and untangles the pathological plausibility hidden in deep learning models.
AB - Purpose: Retinopathy screening via digital imaging is promising for early detection and timely treatment, and tracking retinopathic abnormality over time can help to reveal the risk of disease progression. We developed an innovative physician-oriented artificial intelligence-facilitating diagnosis aid system for retinal diseases for screening multiple retinopathies and monitoring the regions of potential abnormality over time. Approach: Our dataset contains 4908 fundus images from 304 eyes with image-level annotations, including diabetic retinopathy, age-related macular degeneration, cellophane maculopathy, pathological myopia, and healthy control (HC). The screening model utilized a VGG-based feature extractor and multiple-binary convolutional neural network-based classifiers. Images in time series were aligned via affine transforms estimated through speeded-up robust features. Heatmaps of retinopathy were generated from the feature extractor using gradient-weighted class activation mapping++, and individual candidate retinopathy sites were identified from the heatmaps using clustering algorithm. Nested cross-validation with a train-to-test split of 80% to 20% was used to evaluate the performance of the screening model. Results: Our screening model achieved 99% accuracy, 93% sensitivity, and 97% specificity in discriminating between patients with retinopathy and HCs. For discriminating between types of retinopathy, our model achieved an averaged performance of 80% accuracy, 78% sensitivity, 94% specificity, 79% F1-score, and Cohen's kappa coefficient of 0.70. Moreover, visualization results were also shown to provide reasonable candidate sites of retinopathy. Conclusions: Our results demonstrated the capability of the proposed model for extracting diagnostic information of the abnormality and lesion locations, which allows clinicians to focus on patient-centered treatment and untangles the pathological plausibility hidden in deep learning models.
KW - computer-aided diagnosis
KW - lesion-sites visualization
KW - multi-retinopathy classification
UR - http://www.scopus.com/inward/record.url?scp=85142181333&partnerID=8YFLogxK
U2 - 10.1117/1.JMI.9.4.044501
DO - 10.1117/1.JMI.9.4.044501
M3 - Article
AN - SCOPUS:85142181333
SN - 2329-4302
VL - 9
JO - Journal of Medical Imaging
JF - Journal of Medical Imaging
IS - 4
M1 - 044501
ER -