AUTHOR=Miao Jinxin , Yu Jiale , Zou Wenjun , Su Na , Peng Zongyi , Wu Xinjing , Huang Junlong , Fang Yuan , Yuan Songtao , Xie Ping , Huang Kun , Chen Qiang , Hu Zizhong , Liu Qinghuai 

TITLE=Deep Learning Models for Segmenting Non-perfusion Area of Color Fundus Photographs in Patients With Branch Retinal Vein Occlusion

JOURNAL=Frontiers in Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2022.794045

DOI=10.3389/fmed.2022.794045

ISSN=2296-858X

ABSTRACT=PURPOSE: To develop artificial intelligence-based deep learning (DL) models for automatically detecting the ischemia type and the non-perfusion area (NPA) from color fundus photographs (CFPs) of patients with branch retinal vein occlusion (BRVO).
METHODS: This was a retrospective analysis of 274 CFPs from patients diagnosed with BRVO. All DL models were trained using a deep convolutional neural network based on 45° CFPs covering fovea and optic disk. We firstly trained a deep learning algorithm to identify BRVO patients with or without necessity of retinal photocoagulation from 219 CFPs and validated the algorithm on 55 CFPs. Next, we trained another deep learning algorithm to segment NPA from 104 CFPs and validated it on 29 CFPs, in which the NPA was manually delineated by 3 experienced ophthalmologists according to fundus fluorescein angiography. Both DL models have been five-fold cross-validated. The recall, precision, accuracy, and area under the curve (AUC) were used to evaluate the DL models, in comparison with three types of independent ophthalmologists of different seniority.
RESULTS: In the first DL model, the recall, precision, accuracy, and area under the curve (AUC) was 0.75 ± 0.08, 0.80 ± 0.07, 0.79 ± 0.02, 0.82 ± 0.03, respectively for predicting the necessity of laser photocoagulation for BRVO CFPs. The second DL model was able to segment NPA in CFPs of BRVO with an AUC of 0.96 ± 0.02. The recall, precision, and accuracy for segmenting NPA was 0.74 ± 0.05, 0.87 ± 0.02, 0.89 ± 0.02, respectively. The performance of the second DL model was nearly comparable to the senior doctors and significantly better than the residents.
CONCLUSION: These results indicate that the DL models can directly identify and segment the retinal NPA from the CFPs of patients with BRVO, which can further guide the laser photocoagulation. Further research is needed to identify NPA of peripheral retina of BRVO, or other diseases such as diabetic retinopathy.