Performance of automated machine learning in detecting fundus diseases based on ophthalmologic B-scan ultrasound images

Aim To evaluate the efficacy of automated machine learning (AutoML) models in detecting fundus diseases using ocular B-scan ultrasound images.Methods Ophthalmologists annotated two B-scan ultrasound image datasets to develop three AutoML models—single-label, multi-class single-label and multi-label—...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen Zhao, Rui Jiang, Qian Chen, Qiaoling Wei
Format: Article
Language:English
Published: BMJ Publishing Group 2024-12-01
Series:BMJ Open Ophthalmology
Online Access:https://bmjophth.bmj.com/content/9/1/e001873.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850115177408626688
author Chen Zhao
Rui Jiang
Qian Chen
Qiaoling Wei
author_facet Chen Zhao
Rui Jiang
Qian Chen
Qiaoling Wei
author_sort Chen Zhao
collection DOAJ
description Aim To evaluate the efficacy of automated machine learning (AutoML) models in detecting fundus diseases using ocular B-scan ultrasound images.Methods Ophthalmologists annotated two B-scan ultrasound image datasets to develop three AutoML models—single-label, multi-class single-label and multi-label—on the Vertex artificial intelligence (AI) platform. Performance of these models was compared among themselves and against existing bespoke models for binary classification tasks.Results The training set involved 3938 images from 1378 patients, while batch predictions used an additional set of 336 images from 180 patients. The single-label AutoML model, trained on normal and abnormal fundus images, achieved an area under the precision-recall curve (AUPRC) of 0.9943. The multi-class single-label model, focused on single-pathology images, recorded an AUPRC of 0.9617, with performance metrics of these two single-label models proving comparable to those of previously published models. The multi-label model, designed to detect both single and multiple pathologies, posted an AUPRC of 0.9650. Pathology classification AUPRCs for the multi-class single-label model ranged from 0.9277 to 1.0000 and from 0.8780 to 0.9980 for the multi-label model. Batch prediction accuracies ranged from 86.57% to 97.65% for various fundus conditions in the multi-label AutoML model. Statistical analysis demonstrated that the single-label model significantly outperformed the other two models in all evaluated metrics (p<0.05).Conclusion AutoML models, developed by clinicians, effectively detected multiple fundus lesions with performance on par with that of deep-learning models crafted by AI specialists. This underscores AutoML’s potential to revolutionise ophthalmologic diagnostics, facilitating broader accessibility and application of sophisticated diagnostic technologies.
format Article
id doaj-art-058d05b8b8f64418a8b7c7f96d975ea7
institution OA Journals
issn 2397-3269
language English
publishDate 2024-12-01
publisher BMJ Publishing Group
record_format Article
series BMJ Open Ophthalmology
spelling doaj-art-058d05b8b8f64418a8b7c7f96d975ea72025-08-20T02:36:39ZengBMJ Publishing GroupBMJ Open Ophthalmology2397-32692024-12-019110.1136/bmjophth-2024-001873Performance of automated machine learning in detecting fundus diseases based on ophthalmologic B-scan ultrasound imagesChen Zhao0Rui Jiang1Qian Chen2Qiaoling Wei3Eye Institute and Department of Ophthalmology, Eye & ENT Hospital, Fudan University, Shanghai, ChinaEye Institute and Department of Ophthalmology, Eye & ENT Hospital, Fudan University, Shanghai, ChinaEye Institute and Department of Ophthalmology, Eye & ENT Hospital, Fudan University, Shanghai, ChinaEye Institute and Department of Ophthalmology, Eye & ENT Hospital, Fudan University, Shanghai, ChinaAim To evaluate the efficacy of automated machine learning (AutoML) models in detecting fundus diseases using ocular B-scan ultrasound images.Methods Ophthalmologists annotated two B-scan ultrasound image datasets to develop three AutoML models—single-label, multi-class single-label and multi-label—on the Vertex artificial intelligence (AI) platform. Performance of these models was compared among themselves and against existing bespoke models for binary classification tasks.Results The training set involved 3938 images from 1378 patients, while batch predictions used an additional set of 336 images from 180 patients. The single-label AutoML model, trained on normal and abnormal fundus images, achieved an area under the precision-recall curve (AUPRC) of 0.9943. The multi-class single-label model, focused on single-pathology images, recorded an AUPRC of 0.9617, with performance metrics of these two single-label models proving comparable to those of previously published models. The multi-label model, designed to detect both single and multiple pathologies, posted an AUPRC of 0.9650. Pathology classification AUPRCs for the multi-class single-label model ranged from 0.9277 to 1.0000 and from 0.8780 to 0.9980 for the multi-label model. Batch prediction accuracies ranged from 86.57% to 97.65% for various fundus conditions in the multi-label AutoML model. Statistical analysis demonstrated that the single-label model significantly outperformed the other two models in all evaluated metrics (p<0.05).Conclusion AutoML models, developed by clinicians, effectively detected multiple fundus lesions with performance on par with that of deep-learning models crafted by AI specialists. This underscores AutoML’s potential to revolutionise ophthalmologic diagnostics, facilitating broader accessibility and application of sophisticated diagnostic technologies.https://bmjophth.bmj.com/content/9/1/e001873.full
spellingShingle Chen Zhao
Rui Jiang
Qian Chen
Qiaoling Wei
Performance of automated machine learning in detecting fundus diseases based on ophthalmologic B-scan ultrasound images
BMJ Open Ophthalmology
title Performance of automated machine learning in detecting fundus diseases based on ophthalmologic B-scan ultrasound images
title_full Performance of automated machine learning in detecting fundus diseases based on ophthalmologic B-scan ultrasound images
title_fullStr Performance of automated machine learning in detecting fundus diseases based on ophthalmologic B-scan ultrasound images
title_full_unstemmed Performance of automated machine learning in detecting fundus diseases based on ophthalmologic B-scan ultrasound images
title_short Performance of automated machine learning in detecting fundus diseases based on ophthalmologic B-scan ultrasound images
title_sort performance of automated machine learning in detecting fundus diseases based on ophthalmologic b scan ultrasound images
url https://bmjophth.bmj.com/content/9/1/e001873.full
work_keys_str_mv AT chenzhao performanceofautomatedmachinelearningindetectingfundusdiseasesbasedonophthalmologicbscanultrasoundimages
AT ruijiang performanceofautomatedmachinelearningindetectingfundusdiseasesbasedonophthalmologicbscanultrasoundimages
AT qianchen performanceofautomatedmachinelearningindetectingfundusdiseasesbasedonophthalmologicbscanultrasoundimages
AT qiaolingwei performanceofautomatedmachinelearningindetectingfundusdiseasesbasedonophthalmologicbscanultrasoundimages