• Home
  • Search
  • Unsupervised domain adaptation model for lesion detection in retinal OCT images
  • Open Access IconOpen Access
  • Cite Icon12
  • https://doi.org/10.1088/1361-6560/ac2dd1Copy DOI Icon

Unsupervised domain adaptation model for lesion detection in retinal OCT images

Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Background and objective. Optical coherence tomography (OCT) is one of the most used retinal imaging modalities in the clinic as it can provide high-resolution anatomical images. The huge number of OCT images has significantly advanced the development of deep learning methods for automatic lesion detection to ease the doctor’s workload. However, it has been frequently revealed that the deep neural network model has difficulty handling the domain discrepancies, which widely exist in medical images captured from different devices. Many works have been proposed to solve the domain shift issue in deep learning tasks such as disease classification and lesion segmentation, but few works focused on lesion detection, especially for OCT images. Methods. In this work, we proposed a faster-RCNN based, unsupervised domain adaptation model to address the lesion detection task in cross-device retinal OCT images. The domain shift is minimized by reducing the image-level shift and instance-level shift at the same time. We combined a domain classifier with a Wasserstein distance critic to align the shifts at each level. Results. The model was tested on two sets of OCT image data captured from different devices, obtained an average accuracy improvement of more than 8% over the method without domain adaptation, and outperformed other comparable domain adaptation methods. Conclusion. The results demonstrate the proposed model is more effective in reducing the domain shift than advanced methods.

Loading PDF

Similar Papers
  • Research Article
  • Citations236

Attention to Lesion: Lesion-Aware Convolutional Neural Network for Retinal Optical Coherence Tomography Image Classification.

  • Feb 08, 2019
  • IEEE Transactions on Medical Imaging
  • Leyuan Fang +5
  • Conference Article
  • Citations27

Quality Improvement of Retinal Optical Coherence Tomography

  • May 21, 2021
  • A Rajani +3
  • Research Article
  • Citations25

Automatic classification of retinal three-dimensional optical coherence tomography images using principal component analysis network with composite kernels.

  • Nov 29, 2017
  • Journal of Biomedical Optics
  • Leyuan Fang +1
  • Conference Article
  • Citations3

A two-stage unsupervised domain adaptation method for OCT image segmentation

  • Apr 03, 2023
  • Shengyong Diao +5
  • Research Article
  • Citations4

A Device-Independent, Shape Preserving Retinal Optical Coherence Tomography Image Alignment Method Applying TV-Unet for RPE Layer Detection

  • Jan 01, 2022
  • IEEE Transactions on Instrumentation and Measurement
  • Narges Saeedizadeh +8
  • Research Article
  • Citations125

Signal Quality Assessment of Retinal Optical Coherence Tomography Images

  • Apr 24, 2012
  • Investigative Opthalmology & Visual Science
  • Yijun Huang +7
  • Book Chapter

Detection of DME in OCT Images Based on Histogram Descriptor

  • Jan 01, 2022
  • Puspita Dash +1
  • Research Article
  • Citations14

Application of improved homogeneity similarity-based denoising in optical coherence tomography retinal images.

  • Nov 18, 2014
  • Journal of Digital Imaging
  • Qiang Chen +3
  • Research Article
  • Citations13

Deep Learning–Based Clustering of OCT Images for Biomarker Discovery in Age-Related Macular Degeneration (PINNACLE Study Report 4)

  • May 31, 2024
  • Ophthalmology Science
  • Robbie Holland +11
  • Conference Article
  • Citations5

Shortest Path with Backtracking Based Automatic Layer Segmentation in Pathological Retinal Optical Coherence Tomography

  • Oct 01, 2018
  • Xiaoming Liu +5
  • Research Article
  • Citations20

Automatic Classification of Volumetric Optical Coherence Tomography Images via Recurrent Neural Network

  • Jul 06, 2020
  • Sensing and Imaging
  • Chong Wang +3
  • Research Article
  • Citations1

A three-dimensional multi-modal foundation model for optical coherence tomography.

  • Apr 24, 2026
  • Nature biomedical engineering
  • Zixuan Liu +11
  • Conference Article
  • Citations3

VinceptionC3D: a 3D convolutional neural network for retinal OCT image classification

  • Jul 30, 2019
  • Shuanglang Feng +5
  • Conference Article
  • Citations4

Fully automated segmentation of hyper-reflective foci in OCT images using a U-shape network

  • Mar 10, 2020
  • Liangjiu Zhu +3
  • Research Article
  • Citations1

Automated Hole and Non-hole Screening in Retinal OCT Images Using Local Binary Patterns with Support Vector Machine

  • Feb 08, 2020
  • National Academy Science Letters
  • Piyush Mishra +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.