June 2023
Volume 64, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2023
Developing continual learning based optical coherence tomography deep learning model for retinal pathologies
Author Affiliations & Notes
  • Liyuan Jin
    Duke-NUS Medical School, Singapore, Singapore
  • Tanvi Verma
    Institute of High Performance Computing, Singapore, Singapore
  • Jun Zhou
    Institute of High Performance Computing, Singapore, Singapore
  • Jia Huang
    Institute of High Performance Computing, Singapore, Singapore
  • Mingrui Tan
    Institute of High Performance Computing, Singapore, Singapore
  • Benjamin Chen Ming Choong
    Institute of High Performance Computing, Singapore, Singapore
  • Xinxing Xu
    Singapore National Eye Centre, Singapore, Singapore, Singapore
  • Liu Yong
    Institute of High Performance Computing, Singapore, Singapore
  • Nan Liu
    Duke-NUS Medical School, Singapore, Singapore
  • Daniel SW Ting
    Singapore National Eye Centre, Singapore, Singapore, Singapore
    Duke-NUS Medical School, Singapore, Singapore
  • Footnotes
    Commercial Relationships   Liyuan Jin None; Tanvi Verma None; Jun Zhou None; Jia Huang None; Mingrui Tan None; Benjamin Chen Ming Choong None; Xinxing Xu None; Liu Yong None; Nan Liu None; Daniel Ting None
  • Footnotes
    Support  NMRC/HSRG/0087/2018; Duke-NUS/RSF/2021/0018; A20H4g2141
Investigative Ophthalmology & Visual Science June 2023, Vol.64, 3370. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Liyuan Jin, Tanvi Verma, Jun Zhou, Jia Huang, Mingrui Tan, Benjamin Chen Ming Choong, Xinxing Xu, Liu Yong, Nan Liu, Daniel SW Ting; Developing continual learning based optical coherence tomography deep learning model for retinal pathologies. Invest. Ophthalmol. Vis. Sci. 2023;64(8):3370.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Deep learning based optical coherence tomography (OCT) model needs continuous updates in practical deployment to learn new diseases and improve performance. However, continuous conventional training suffers from catastrophic forgetting of old classes and violates patient privacy by storing data. We performed a translational study to test the hypothesis that non-storage privacy-preserving continual learning (CL) OCT model can continuously learn and maintain learned classes performance for retinal pathologies such as drusen, diabetic macula edema (DME), choroidal neovascularization (CNV).

Methods : We tested 11 CL algorithms among three main CL methodologies, such as regularization, expansion and replay, on the public OCT dataset. This dataset contains over 84,495 OCT images, including normal (31.1%), drusen (10.2%), CNV (44%), DME (13.4%). There are 250 testing images (1.1%) for each class. Because most CL algorithms are developed from non-medical dataset CIFAR10, it is included as the benchmark. It consists of 60,000 images in 10 daily classes, such as cat and truck. There are 5,000 training images (83.3%) and 1,000 testing images (16.6%) per class. Convolutional neural networks (CNN), specifically EfficientNetB4, and ResNet18, were used. In OCT training, CNV and normal were trained in the first task, DME was trained in the second task and drusen was trained in the third task. For CIFAR10 dataset, 4 classes were trained in the first task, and 3 classes were trained in the second and the third task. After the last task, all classes accuracies were measured. The conventional deep learning model was sequentially trained, and the centralized model of all classes was trained together as control.

Results : Among all CL OCT models, the expansion based Efficient Feature Transformations (EFT) algorithm shows the best result with 51.72%, 78.64% and 60.47% accuracy respectively. While the conventional deep learning model showed a completely dropped performance on all previous tasks. Similarly, EFT algorithm performs best on CIFAR10 dataset.

Conclusions : Our study is consistent with our hypothesis that privacy-preserving CL application in OCT shows better old classes performance compared to the conventional machine learning model. Further improvement in CL accuracy would be beneficial for future OCT AI model deployment in primary care settings

This abstract was presented at the 2023 ARVO Annual Meeting, held in New Orleans, LA, April 23-27, 2023.

 

Final CL model accuracy

Final CL model accuracy

 

Average task accuracy

Average task accuracy

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×