Distance-weighted Sinkhorn loss for Alzheimer's disease classification

If you need an accessible version of this item, please submit a remediation request.
Date
2024-02-12
Language
American English
Embargo Lift Date
Committee Members
Degree
Degree Year
Department
Grantor
Journal Title
Journal ISSN
Volume Title
Found At
Elsevier
Abstract

Traditional loss functions such as cross-entropy loss often quantify the penalty for each mis-classified training sample without adequately considering its distance from the ground truth class distribution in the feature space. Intuitively, the larger this distance is, the higher the penalty should be. With this observation, we propose a penalty called distance-weighted Sinkhorn (DWS) loss. For each mis-classified training sample (with predicted label A and true label B), its contribution to the DWS loss positively correlates to the distance the training sample needs to travel to reach the ground truth distribution of all the A samples. We apply the DWS framework with a neural network to classify different stages of Alzheimer's disease. Our empirical results demonstrate that the DWS framework outperforms the traditional neural network loss functions and is comparable or better to traditional machine learning methods, highlighting its potential in biomedical informatics and data science.

Description
item.page.description.tableofcontents
item.page.relation.haspart
Cite As
Wang Z, Zhan Q, Tong B, et al. Distance-weighted Sinkhorn loss for Alzheimer's disease classification. iScience. 2024;27(3):109212. Published 2024 Feb 12. doi:10.1016/j.isci.2024.109212
ISSN
Publisher
Series/Report
Sponsorship
Major
Extent
Identifier
Relation
Journal
iScience
Source
PMC
Alternative Title
Type
Article
Number
Volume
Conference Dates
Conference Host
Conference Location
Conference Name
Conference Panel
Conference Secretariat Location
Version
Final published version
Full Text Available at
This item is under embargo {{howLong}}