Is attention all you need in medical image analysis? A review

Giorgos Papanastasiou, Nikolaos Dikaios, Jiahao Huang, Chengjia Wang, Guang Yang

Research output: Contribution to journalArticlepeer-review

6 Downloads (Pure)

Abstract

Medical imaging is a key component in clinical diagnosis, treatment planning and clinical trial design, accounting for almost 90% of all healthcare data. CNNs achieved performance gains in medical image analysis (MIA) over the last years. CNNs can efficiently model local pixel interactions and be trained on small-scale MI data. Despite their important advances, typical CNN have relatively limited capabilities in modelling “global” pixel interactions, which restricts their generalisation ability to understand out-of-distribution data with different “global” information. The recent progress of Artificial Intelligence gave rise to Transformers, which can learn global relationships from data. However, full Transformer models need to be trained on large-scale data and involve tremendous computational complexity. Attention and Transformer compartments (“Transf/Attention”) which can well maintain properties for modelling global relationships, have been proposed as lighter alternatives of full Transformers. Recently, there is an increasing trend to co-pollinate complementary local-global properties from CNN and Transf/Attention architectures, which led to a new era of hybrid models. The past years have witnessed substantial growth in hybrid CNN-Transf/Attention models across diverse MIA problems. In this systematic review, we survey existing hybrid CNN-Transf/Attention models, review and unravel key architectural designs, analyse breakthroughs, and evaluate current and future opportunities as well as challenges. We also introduced an analysis framework on generalisation opportunities of scientific and clinical impact, based on which new data-driven domain generalisation and adaptation methods can be stimulated.
Original languageEnglish
Pages (from-to)1-14
Number of pages14
JournalIEEE Journal of Biomedical and Health Informatics
DOIs
Publication statusE-pub ahead of print - 29 Dec 2023

Keywords

  • Analytical models
  • Attention
  • Computational modeling
  • Computed tomography
  • Convolutional neural networks
  • Data models
  • Imaging
  • Magnetic resonance imaging
  • Medical image analysis
  • Positron emission tomography
  • Retinal imaging
  • Transformers

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics
  • Electrical and Electronic Engineering
  • Health Information Management

Fingerprint

Dive into the research topics of 'Is attention all you need in medical image analysis? A review'. Together they form a unique fingerprint.

Cite this