Conference proceeding
Novel application of the attention mechanism on medical image harmonization
Vol.12464, pp.124640Y-124640Y-11
04/03/2023
DOI: 10.1117/12.2654392
Abstract
Medical image harmonization aims to transform the image ‘style’ among heterogeneous datasets while preserving the anatomical content. It enables data-sensitive learning-based approaches to fully leverage the data power of large multi-site datasets with different image acquisitions. Recently, the attention mechanism has achieved excellent performance on the image-to-image (I2I) translation of natural images. In this work, we further explore the potential of leveraging the attention mechanism to improve the performance of medical image harmonization. Here, we introduce two attention-based frameworks with outstanding performance in the natural I2I scenario in the context of cross-scanner MRI harmonization for the first time. We compare them with the existing commonly used harmonization frameworks by evaluating their ability to enhance the performance of the downstream subcortical segmentation task on T1-weighted (T1w) MRI datasets from 1.5T vs. 3T scanners. Both qualitative and quantitative results prove that the attention mechanism contributes to a noticeable improvement in harmonization ability.
Details
- Title: Subtitle
- Novel application of the attention mechanism on medical image harmonization
- Creators
- Xing Yao - Vanderbilt UniversityAnge Lou - Vanderbilt UniversityHao Li - Vanderbilt UniversityDewei Hu - Vanderbilt UniversityDaiwei Lu - Vanderbilt UniversityHan Liu - Vanderbilt UniversityJiacheng Wang - Vanderbilt UniversityZachary Stoebner - Vanderbilt UniversityHans Johnson - University of IowaJeff D. Long - The Univ. of Iowa (United States)Jane S. Paulsen - University of Wisconsin–MadisonIpek Oguz - Vanderbilt University
- Contributors
- Olivier Colliot (Editor) - Ctr. National de la Recherche Scientifique (France)Ivana Išgum (Editor) - Amsterdam University Medical Centers
- Resource Type
- Conference proceeding
- Publication Details
- Vol.12464, pp.124640Y-124640Y-11
- Publisher
- SPIE
- DOI
- 10.1117/12.2654392
- ISSN
- 1605-7422
- Language
- English
- Date published
- 04/03/2023
- Academic Unit
- Psychological and Brain Sciences; Electrical and Computer Engineering; Roy J. Carver Department of Biomedical Engineering; The Iowa Initiative for Artificial Intelligence; Iowa Informatics Initiative; Psychiatry; The Iowa Institute for Biomedical Imaging
- Record Identifier
- 9984399499702771
Metrics
19 Record Views