Efficiency-aware multi-class spinal disorder classification using CBAM-enhanced lightweight CNNS with dual-branch fusion

Gunawan, Teddy Surya and Jannah, Nurul and Kartiwi, Mira and Abdul Malik, Noreha (2026) Efficiency-aware multi-class spinal disorder classification using CBAM-enhanced lightweight CNNS with dual-branch fusion. IIUM Engineering Journal, 27 (2). pp. 278-319. ISSN 1511-788X E-ISSN 2289-7860

	PDF - Published Version Restricted to Registered users only Download (14MB) | Request a copy
Preview	PDF - Supplemental Material Download (139kB) | Preview

Abstract

Spinal X-rays are still often read through manual measurements, yet the patients who most need timely assessment cannot afford delay, inconsistency, or heavy computational pipelines. Motivated by this clinical tension, this study proposes an efficiency-aware deep learning framework for three-class spinal disorder classification that asks a practical question rarely centered in prior work: not only which model is most accurate, but which model is accurate enough, light enough, and fast enough to matter in real screening settings. Using a public dataset of 338 subjects, five lightweight backbones, CBAM-enhanced variants, and a dual-branch fusion model were evaluated through stratified 5-fold cross-validation under multiple balancing strategies, with performance measured by accuracy, precision, recall, F1-score, parameter count, FLOPs, model size, latency, and throughput. The results reveal an unexpected pattern: bigger models do not win. MobileNetV3Small delivers the strongest efficiency-performance balance, reaching an F1-score of 0.962 with only 1.0 million parameters, while the best overall result is achieved by the Fusion_MNv3_MNAS model under augmentation-only training, with an F1-score of 0.976. Ablation findings further show that attention and fusion are not universally beneficial, but become most effective when paired with sufficient data-driven regularization, and that fine-tuning about 30% of backbone parameters yields the most favorable adaptation. Taken together, these findings show that performance in spinal X-ray classification depends less on model size alone than on the fit between architecture and training strategy. The study therefore offers a concrete and clinically relevant message: lightweight, well-regularized models can match or surpass heavier alternatives while remaining more practical for scalable deployment

Item Type:	Article (Journal)
Uncontrolled Keywords:	Spinal Disorder Classification, Deep Learning, Lightweight CNN, Attention Mechanism (CBAM), Efficiency-Aware Evaluation
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices > TK7885 Computer engineering
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering > Department of Electrical and Computer Engineering Kulliyyah of Information and Communication Technology > Department of Information System Kulliyyah of Information and Communication Technology > Department of Information System
Depositing User:	Prof. Dr. Teddy Surya Gunawan
Date Deposited:	20 May 2026 09:36
Last Modified:	20 May 2026 09:36
Queue Number:	2026-05-Q3462
URI:	http://irep.iium.edu.my/id/eprint/129072

Actions (login required)

View Item