Adaptive feature squeeze network for nuclear cataract classification in AS-OCT image

Xiaoqing Zhang, Zunjie Xiao, Risa Higashita, Yan Hu, Wan Chen, Jin Yuan, Jiang Liu

Research output: Journal PublicationArticlepeer-review

3 Citations (Scopus)

Abstract

Nuclear cataract (NC) is an age-related cataract disease. Cataract surgery is an effective method to improve the vision and life quality of NC patients. Anterior segment optical coherence tomography (AS-OCT) images are noninvasive, reproductive, and easy-measured, which can capture opacity clearly on the lens nucleus region. However, automatic AS-OCT-based NC classification research has not been extensively studied. This paper proposes a novel convolutional neural network (CNN) framework named Adaptive Feature Squeeze Network (AFSNet) to classify NC severity levels automatically. In the AFSNet, we construct an adaptive feature squeeze module to dynamically squeeze local feature representations and update the relative importance of global feature representations, which is comprised of a squeeze block and a global adaptive pooling operation. We conduct comprehensive experiments on a clinical AS-OCT image dataset and a public OCT images dataset, and results demonstrate our method's effectiveness and superiority over strong baselines and previous state-of-the-art methods. Furthermore, this paper also demonstrates that CNNs achieve better NC classification results on the nucleus region than the lens region. We also adopt the class activation mapping (CAM) technique to localize the discriminative regions that CNN models learned, which enhances the interpretability of classification results.

Original languageEnglish
Article number104037
JournalJournal of Biomedical Informatics
Volume128
DOIs
Publication statusPublished - Apr 2022
Externally publishedYes

Keywords

  • AS-OCT image
  • Adaptive feature squeeze network
  • Global adaptive pooling
  • Nuclear cataract classification
  • Squeeze block

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Fingerprint

Dive into the research topics of 'Adaptive feature squeeze network for nuclear cataract classification in AS-OCT image'. Together they form a unique fingerprint.

Cite this