Citation

Ahmad, Muhammad Shahrul Zaim and Aziz, Nor Azlina Ab. and Siong, Lim Heng (2025) Scoping Review on Deep and Transfer Learning for Spinal Image Analysis. In: 2025 Multimedia University Engineering Conference, MECON 2025, 21 July 2025 - 23 July 2025, Cyberjaya, Malaysia.

Text 470.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

Deep learning is widely applied in various sectors, including medical image analysis. The spine is one of the most important musculoskeletal structures of humans, enabling proper posture and supporting the whole body weight. Deep learning can be applied to a wide variety of applications for spine-related analysis. There is limited research that discusses the recent trends in the current development of the spine-related deep learning system. This scoping review aims to discover and map the application areas, algorithms of choice, and future directions of deep learning research in spinal medical image analysis. Articles focusing on deep learning applications in spine-related medical imaging are reviewed. The most common application of deep learning observed is vertebral compression fracture, and classification is the most common analysis method using deep learning. Several articles also reported the lack of data issues, which may impact the performance of the deep learning algorithms. While there is an upward trend in recent years for spine-related analysis, challenges remain in the dataset size and the integration of the deep learning-based system in real-world settings.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	spine, artificial intelligence, deep learning, transfer learning, medical image.
Subjects:	T Technology > TR Photography > TR624-835 Applied photography Including artistic, commercial, medical photography, photocopying processes
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	19 Mar 2026 00:50
Last Modified:	19 Mar 2026 00:50
URII:	http://shdl.mmu.edu.my/id/eprint/15500

Downloads

Edit (login required)