Self-supervised patient-specific features learning for OCT image classification

Deep learning’s great success in image classification is heavily reliant on large-scale annotated datasets. However, obtaining labels for optical coherence tomography (OCT) data requires the significant effort of professional ophthalmologists, which hinders the application of deep learning in OCT im...

Full description

Saved in:
Bibliographic Details
Published in:Medical & biological engineering & computing 2022-10, Vol.60 (10), p.2851-2863
Main Authors: Fang, Leyuan, Guo, Jiahuan, He, Xingxin, Li, Muxing
Format: Article
Language:English
Subjects:
Biomedical and Life Sciences
Biomedical Engineering and Bioengineering
Biomedicine
Classification
Cognitive tasks
Computer Applications
Datasets
Deep learning
Human Physiology
Image classification
Imaging
Labels
Machine learning
Medical imaging
Optical Coherence Tomography
Original Article
Radiology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning’s great success in image classification is heavily reliant on large-scale annotated datasets. However, obtaining labels for optical coherence tomography (OCT) data requires the significant effort of professional ophthalmologists, which hinders the application of deep learning in OCT image classification. In this paper, we propose a self-supervised patient-specific features learning (SSPSF) method to reduce the amount of data required for well OCT image classification results. Specifically, the SSPSF consists of a self-supervised learning phase and a downstream OCT image classification learning phase. The self-supervised learning phase contains two self-supervised patient-specific features learning tasks. One is to learn to discriminate an OCT scan which belongs to a specific patient. The other task is to learn the invariant features related to patients. In addition, our proposed self-supervised learning model can learn inherent representations from the OCT images without any manual labels, which provides well initialization parameters for the downstream OCT image classification model. The proposed SSPSF achieves classification accuracy of 97.74% and 98.94% on the public RETOUCH dataset and AI Challenger dataset, respectively. The experimental results on two public OCT datasets show the effectiveness of the proposed method compared with other well-known OCT image classification methods with less annotated data. Graphical abstract
ISSN:0140-0118
1741-0444
DOI:10.1007/s11517-022-02627-8