Imbalanced histopathology image classification using deep feature graph attention network

Cong Cong, Yixing Yang, Sidong Liu, Maurice Pagnucco, Yang Song

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

3 Citations (Scopus)

Abstract

Recent deep learning studies have shown great progress in metastasis detection over histopathology whole slide images (WSIs). As WSIs are extremely large, most of existing studies adopt patch level analysis, leveraging spatial context to enhance patch-wise classification. However, class imbalance in patch distribution may result in an exceedingly large number of false-negatives, thereby worsening the WSI level classification performance. In this paper, we propose a novel framework for classification in class imbalanced datasets, which adopts a graph attention network to capture feature dependent interactions and a minority preferred inference mechanism for patch-level classification. Our experiments on CAMELYON16 show that the proposed method substantially improves detection of the minority class (tumour) under a highly imbalanced class distribution.
Original languageEnglish
Title of host publicationIEEE ISBI 2022 Proceedings
Subtitle of host publication2022 IEEE International Symposium on Biomedical Imaging
Place of PublicationKolkata
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1-4
Number of pages4
ISBN (Electronic)9781665429238
ISBN (Print)9781665429245
DOIs
Publication statusPublished - 28 Mar 2022
Event19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 - Kolkata, India
Duration: 28 Mar 202231 Mar 2022

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2022-March
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference19th IEEE International Symposium on Biomedical Imaging, ISBI 2022
Country/TerritoryIndia
CityKolkata
Period28/03/2231/03/22

Keywords

  • Graph Attention Networks
  • Intra-Class Feature Enhancement
  • Metastasis Detection

Fingerprint

Dive into the research topics of 'Imbalanced histopathology image classification using deep feature graph attention network'. Together they form a unique fingerprint.

Cite this