Self-Supervised Learning for Improved Optical Coherence Tomography Detection of Macular Telangiectasia Type 2.
Details
Serval ID
serval:BIB_240ACAA1058F
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Self-Supervised Learning for Improved Optical Coherence Tomography Detection of Macular Telangiectasia Type 2.
Journal
JAMA ophthalmology
Working group(s)
MacTel Research Group
Contributor(s)
Okada M., Gaudric A., Schwartz S., Constable I., Yannuzzi L.A., Egan C., Singerman L., Gillies M., Friedlander M., Lange C., Holz F., Comer G., Brucker A., Bernstein P., Rosenfeld P., Miller J., Yan J., Duncan J., Weinberg D., Sallo F., Hoyng C.B., Charbel Issa P., Bucher F., Berger B., Rich R., Miller D., Lee C., Do D., Bakri S., Higgins P., Zhuk S.A., Randhawa S., Raphaelian P.V., Sneed S., Khanani A., Lee M., Warrow D., Fawzi A., Goldberg R., Barb S.M., Elman M.J., Wykoff C., Finley T., Wells Iii J.A., Fish G., Randolph J., Boyer D., Qureshi J., Blinder K.
ISSN
2168-6173 (Electronic)
ISSN-L
2168-6165
Publication state
Published
Issued date
01/03/2024
Peer-reviewed
Oui
Editor
Okada M Gaudric A. Schwartz S. Constable I. Yannuzzi L. A. Egan C. Singerman L. Gillies M. Friedlander M. Lange C. Holz F. Comer G. Brucker A. Bernstein P. Rosenfeld P. Miller J. Yan J. Duncan J. Weinberg D. Sallo F. Hoyng C. B. Charbel Issa P. Bucher F. Berger B. Rich R. Miller D. Lee C. Do D. Bakri S. Higgins P. Zhuk S. A. Randhawa S. Raphaelian P. V. Sneed S. Khanani A. Lee M. Warrow D. Fawzi A. Goldberg R. Barb S. M. Elman M. J. Wykoff C. Finley T. Wells Iii J. A. Fish G. Randolph J. Boyer D. Qureshi J. Blinder K., MacTel Research Group
Volume
142
Number
3
Pages
226-233
Language
english
Notes
Publication types: Journal Article ; Comment
Publication Status: ppublish
Publication Status: ppublish
Abstract
Deep learning image analysis often depends on large, labeled datasets, which are difficult to obtain for rare diseases.
To develop a self-supervised approach for automated classification of macular telangiectasia type 2 (MacTel) on optical coherence tomography (OCT) with limited labeled data.
This was a retrospective comparative study. OCT images from May 2014 to May 2019 were collected by the Lowy Medical Research Institute, La Jolla, California, and the University of Washington, Seattle, from January 2016 to October 2022. Clinical diagnoses of patients with and without MacTel were confirmed by retina specialists. Data were analyzed from January to September 2023.
Two convolutional neural networks were pretrained using the Bootstrap Your Own Latent algorithm on unlabeled training data and fine-tuned with labeled training data to predict MacTel (self-supervised method). ResNet18 and ResNet50 models were also trained using all labeled data (supervised method).
The ground truth yes vs no MacTel diagnosis is determined by retinal specialists based on spectral-domain OCT. The models' predictions were compared against human graders using accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), area under precision recall curve (AUPRC), and area under the receiver operating characteristic curve (AUROC). Uniform manifold approximation and projection was performed for dimension reduction and GradCAM visualizations for supervised and self-supervised methods.
A total of 2636 OCT scans from 780 patients with MacTel and 131 patients without MacTel were included from the MacTel Project (mean [SD] age, 60.8 [11.7] years; 63.8% female), and another 2564 from 1769 patients without MacTel from the University of Washington (mean [SD] age, 61.2 [18.1] years; 53.4% female). The self-supervised approach fine-tuned on 100% of the labeled training data with ResNet50 as the feature extractor performed the best, achieving an AUPRC of 0.971 (95% CI, 0.969-0.972), an AUROC of 0.970 (95% CI, 0.970-0.973), accuracy of 0.898%, sensitivity of 0.898, specificity of 0.949, PPV of 0.935, and NPV of 0.919. With only 419 OCT volumes (185 MacTel patients in 10% of labeled training dataset), the ResNet18 self-supervised model achieved comparable performance, with an AUPRC of 0.958 (95% CI, 0.957-0.960), an AUROC of 0.966 (95% CI, 0.964-0.967), and accuracy, sensitivity, specificity, PPV, and NPV of 90.2%, 0.884, 0.916, 0.896, and 0.906, respectively. The self-supervised models showed better agreement with the more experienced human expert graders.
The findings suggest that self-supervised learning may improve the accuracy of automated MacTel vs non-MacTel binary classification on OCT with limited labeled training data, and these approaches may be applicable to other rare diseases, although further research is warranted.
To develop a self-supervised approach for automated classification of macular telangiectasia type 2 (MacTel) on optical coherence tomography (OCT) with limited labeled data.
This was a retrospective comparative study. OCT images from May 2014 to May 2019 were collected by the Lowy Medical Research Institute, La Jolla, California, and the University of Washington, Seattle, from January 2016 to October 2022. Clinical diagnoses of patients with and without MacTel were confirmed by retina specialists. Data were analyzed from January to September 2023.
Two convolutional neural networks were pretrained using the Bootstrap Your Own Latent algorithm on unlabeled training data and fine-tuned with labeled training data to predict MacTel (self-supervised method). ResNet18 and ResNet50 models were also trained using all labeled data (supervised method).
The ground truth yes vs no MacTel diagnosis is determined by retinal specialists based on spectral-domain OCT. The models' predictions were compared against human graders using accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), area under precision recall curve (AUPRC), and area under the receiver operating characteristic curve (AUROC). Uniform manifold approximation and projection was performed for dimension reduction and GradCAM visualizations for supervised and self-supervised methods.
A total of 2636 OCT scans from 780 patients with MacTel and 131 patients without MacTel were included from the MacTel Project (mean [SD] age, 60.8 [11.7] years; 63.8% female), and another 2564 from 1769 patients without MacTel from the University of Washington (mean [SD] age, 61.2 [18.1] years; 53.4% female). The self-supervised approach fine-tuned on 100% of the labeled training data with ResNet50 as the feature extractor performed the best, achieving an AUPRC of 0.971 (95% CI, 0.969-0.972), an AUROC of 0.970 (95% CI, 0.970-0.973), accuracy of 0.898%, sensitivity of 0.898, specificity of 0.949, PPV of 0.935, and NPV of 0.919. With only 419 OCT volumes (185 MacTel patients in 10% of labeled training dataset), the ResNet18 self-supervised model achieved comparable performance, with an AUPRC of 0.958 (95% CI, 0.957-0.960), an AUROC of 0.966 (95% CI, 0.964-0.967), and accuracy, sensitivity, specificity, PPV, and NPV of 90.2%, 0.884, 0.916, 0.896, and 0.906, respectively. The self-supervised models showed better agreement with the more experienced human expert graders.
The findings suggest that self-supervised learning may improve the accuracy of automated MacTel vs non-MacTel binary classification on OCT with limited labeled training data, and these approaches may be applicable to other rare diseases, although further research is warranted.
Keywords
Humans, Female, Middle Aged, Male, Tomography, Optical Coherence/methods, Deep Learning, Retrospective Studies, Rare Diseases, Retinal Telangiectasis/diagnostic imaging, Supervised Machine Learning
Pubmed
Web of science
Create date
12/02/2024 14:46
Last modification date
26/09/2024 6:19
Usage data
