Ordinal Regression Research Based on Dual Loss Function—An Example on Lumbar Vertebra Classification in CT Images
Open Access
- 21 November 2025
- journal article
- research article
- Published by MDPI AG in Diagnostics
- Vol. 15 (23) , 2949
Abstract
Background/Objectives: Some classification problems involve ordered categories (e.g., low–medium–high), which are better modeled as ordinal regression. This study aimed to propose and evaluate a dual loss framework—Ordinal Residual Dual Loss—for lumbar vertebra classification on CT images to assist L3 identification and sarcopenia detection. Methods: In this retrospective study, lumbar spine CT images were used to train a deep learning model based on a MobileNet-v3-Large network. The proposed framework combines standard cross-entropy loss for classification with an Ordinal Residual Loss defined on the difference between output probabilities and target ordinal probabilities. Results: Experimental results show that the Ordinal Residual Dual Loss approach outperforms using cross-entropy alone and also surpasses methods from previous studies in lumbar vertebra classification performance. Conclusions: Leveraging a dual loss design that incorporates ordinal information improves vertebral level classification on CT images and has potential to support more accurate automated L3 localization and sarcopenia assessment in clinical practice.Keywords
Funding Information
- Ministry of Science and Technology, Taiwan (112-2410-H-415-012-MY2, 114-2410-H-415-033-MY2)
- Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation (DTCRD 114-C-04, DTCRD 114-I-16)
This publication has 20 references indexed in Scilit:
- A Deep Learning-Based Fully Automated Vertebra Segmentation and Labeling WorkflowBritish Journal of Hospital Medicine, 2025
- Deep neural networks for rank-consistent ordinal regression based on conditional probabilitiesPattern Analysis and Applications, 2023
- Fully automated CT-based adiposity assessment: comparison of the L1 and L3 vertebral levels for opportunistic predictionAbdominal Radiology, 2022
- The use of alternate vertebral levels to L3 in computed tomography scans for skeletal muscle mass evaluation and sarcopenia assessment in patients with cancer: a systematic reviewBritish Journal of Nutrition, 2021
- Optimal body size adjustment of L3 CT skeletal muscle area for sarcopenia assessmentScientific Reports, 2021
- Rank consistent ordinal regression for neural networks with application to age estimationPattern Recognition Letters, 2020
- Automated Abdominal CT Imaging Biomarkers for Opportunistic Prediction of Future Major Osteoporotic Fractures in Asymptomatic AdultsRadiology, 2020
- Development and Evaluation of CT-to-3D Ultrasound Image Registration Algorithm in Vertebral Phantoms for Spine SurgeryAnnals of Biomedical Engineering, 2020
- Automated CT biomarkers for opportunistic prediction of future cardiovascular events and mortality in an asymptomatic screening population: a retrospective cohort studyThe Lancet Digital Health, 2020
- Approaches to Assessment of Muscle Mass and Myosteatosis on Computed Tomography: A Systematic ReviewThe Journals of Gerontology, Series A: Biological Sciences and Medical Sciences, 2019