SCOL: Supervised contrastive ordinal loss for abdominal aortic calcification scoring on vertebral fracture assessment scans

Document Type

Conference Proceeding

Publication Title

Medical Image Computing and Computer Assisted Intervention – MICCAI 2023

Volume

14225 LNCS

First Page

273

Last Page

283

Publisher

Springer

School

Graduate Research School / School of Science / Nutrition and Health Innovation Research Institute / Centre for Artificial Intelligence and Machine Learning (CAIML)

RAS ID

62735

Funders

National Health and Medical Research Council / Rady Innovation Fund, Rady Faculty of Health Sciences, University of Manitoba / National Heart Foundation of Australia Future Leader Fellowship / Raine Medical Research Foundation

Grant Number

ARC Number : APP1183570

Comments

Saleem, A., Ilyas, Z., Suter, D., Hassan, G. M. Reid, S., Schousboe, J. T., . . . Gilani, S. Z. (2023). SCOL: Supervised contrastive ordinal loss for abdominal aortic calcification scoring on vertebral fracture assessment scans. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2023 (pp. 273-283). Springer, Cham. https://doi.org/10.1007/978-3-031-43987-2_27

Abstract

Abdominal Aortic Calcification (AAC) is a known marker of asymptomatic Atherosclerotic Cardiovascular Diseases (ASCVDs). AAC can be observed on Vertebral Fracture Assessment (VFA) scans acquired using Dual-Energy X-ray Absorptiometry (DXA) machines. Thus, the automatic quantification of AAC on VFA DXA scans may be used to screen for CVD risks, allowing early interventions. In this research, we formulate the quantification of AAC as an ordinal regression problem. We propose a novel Supervised Contrastive Ordinal Loss (SCOL) by incorporating a label-dependent distance metric with existing supervised contrastive loss to leverage the ordinal information inherent in discrete AAC regression labels. We develop a Dual-encoder Contrastive Ordinal Learning (DCOL) framework that learns the contrastive ordinal representation at global and local levels to improve the feature separability and class diversity in latent space among the AAC-24 genera. We evaluate the performance of the proposed framework using two clinical VFA DXA scan datasets and compare our work with state-of-the-art methods. Furthermore, for predicted AAC scores, we provide a clinical analysis to predict the future risk of a Major Acute Cardiovascular Event (MACE). Our results demonstrate that this learning enhances inter-class separability and strengthens intra-class consistency, which results in predicting the high-risk AAC classes with high sensitivity and high accuracy.

DOI

10.1007/978-3-031-43987-2_27

Access Rights

subscription content

Link to Full Text

Share

 
COinS