Background/aims Fundus fluorescein angiography (FFA) is an important technique to evaluate diabetic retinopathy (DR) and other retinal diseases. The interpretation of FFA images is complex and time-consuming, and the ability of diagnosis is uneven among different ophthalmologists. The aim of the study is to develop a clinically usable multilevel classification deep learning model for FFA images, including prediagnosis assessment and lesion classification.
Methods A total of 15 599 FFA images of 1558 eyes from 845 patients diagnosed with DR were collected and annotated. Three convolutional neural network (CNN) models were trained to generate the label of image quality, location, laterality of eye, phase and five lesions. Performance of the models was evaluated by accuracy, F-1 score, the area under the curve and human-machine comparison. The images with false positive and false negative results were analysed in detail.
Results Compared with LeNet-5 and VGG16, ResNet18 got the best result, achieving an accuracy of 80.79%–93.34% for prediagnosis assessment and an accuracy of 63.67%–88.88% for lesion detection. The human-machine comparison showed that the CNN had similar accuracy with junior ophthalmologists. The false positive and false negative analysis indicated a direction of improvement.
Conclusion This is the first study to do automated standardised labelling on FFA images. Our model is able to be applied in clinical practice, and will make great contributions to the development of intelligent diagnosis of FFA images.
Data availability statement
Data are available on reasonable request. Data are available by contacting the corresponding authors on reasonable request.
Statistics from Altmetric.com
If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.
Contributors ZG, KJ and JY conceived and designed the experiments. XP, JS and ZS collected and processed the data. ZG and XJ analysed the results. All authors reviewed the manuscript. JY is guarantor.
Funding This work was financially supported by National Natural Science Foundation of China (grant number U20A20386), National key research and development programme of China (grant number 2019YFC0118400), Key research and development programme of Zhejiang Province (grant number 2019C03020), Medical and Health Science and Technology Program of Zhejiang Province (grant number 2021RC064) and Clinical Medical Research Center for Eye Diseases of Zhejiang Province (grant number 2021E50007).
Competing interests None declared.
Provenance and peer review Not commissioned; externally peer reviewed.
Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.