FEW-SHOT Image Segmentation for Cross-Institution Male Pelvic Organs Using Registration-Assisted Prototypical Learning

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

4 Scopus Citations
View graph of relations

Author(s)

  • Yiwen Li
  • Yunguan Fu
  • Qianye Yang
  • Zhe Min
  • Henkjan Huisman
  • Dean Barratt
  • Victor Adrian Prisacariu
  • Yipeng Hu

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings of the 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)
PublisherIEEE
Number of pages5
ISBN (Electronic)9781665429238
ISBN (Print)978-1-6654-2924-5
Publication statusPublished - 2022

Publication series

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

Conference

Title19th IEEE International Symposium on Biomedical Imaging (ISBI 2022)
LocationITC Royal Bengal (virtual)
PlaceIndia
CityKolkata
Period28 - 31 March 2022

Abstract

The ability to adapt medical image segmentation networks for a novel class such as an unseen anatomical or pathological structure, when only a few labelled examples of this class are available from local healthcare providers, is sought-after. This potentially addresses two widely recognised limitations in deploying modern deep learning models to clinical practice, expertise-and-labour-intensive labelling and cross-institution generalisation. This work presents the first 3D few-shot interclass segmentation network for medical images, using a labelled multi-institution dataset from prostate cancer patients with eight regions of interest. We propose an image alignment module registering the predicted segmentation of both query and support data, in a standard prototypical learning algorithm, to a reference atlas space. The built-in registration mechanism can effectively utilise the prior knowledge of consistent anatomy between subjects, regardless whether they are from the same institution or not. Experimental results demonstrated that the proposed registration-assisted prototypical learning significantly improved segmentation accuracy (p-values<0.01) on query data from a holdout institution, with varying availability of support data from multiple institutions. We also report the additional benefits of the proposed 3D networks with 75% fewer parameters and an arguably simpler implementation, compared with existing 2D few-shot approaches that segment 2D slices of volumetric medical images.

Citation Format(s)

FEW-SHOT Image Segmentation for Cross-Institution Male Pelvic Organs Using Registration-Assisted Prototypical Learning. / Li, Yiwen; Fu, Yunguan; Yang, Qianye et al.
Proceedings of the 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI). IEEE, 2022. (Proceedings - International Symposium on Biomedical Imaging).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review