Citation

Zaim Ahmad, Muhammad Shahrul and Ab Aziz, Nor Azlina and Lim, Heng Siong and Ghazali, Anith Khairunnisa (2024) Datasets for Artificial Intelligence-based Spine Analysis: A Scoping Review. JOIV : International Journal on Informatics Visualization, 8 (4). p. 2511. ISSN 2549-9610

Text Microsoft Word - Zaim 3042-CIT-AAP.pdf - Published Version Restricted to Repository staff only Download (3MB)

Abstract

The advancement of artificial intelligence (AI) and intense learning is key to automating the diagnosis and inspection of spinal-related pathologies. This automation reduces the need for human manual analysis. Reducing the burden on the healthcare system and the risk of human error. Spine medical images have several modalities, such as X-rays, computed tomography (CT), and magnetic resonance imaging (MRI). Each modality captured the vertebral features differently. The choice of modality affects the performance of the applied algorithms. It is also important to note that a large amount of data is better for training AI algorithms, profound learning algorithms. However, medical images are often limited owing to privacy concerns and the lack of open-source databases. Therefore, it is essential to identify data sources to ensure the success of AI projects for spine analysis. This review discusses available datasets and their characteristics, such as modality, size, and labels. Additionally, the demographics and applications of the data were also discussed. The platform utilized to obtain related literature in this study is Lens. A scoping review was used in this study to extract information from related literature. The number of literature included in this study is 39. A total of 43 datasets, which include 32 private and 11 public datasets, are discussed in this review. This work will benefit researchers and developers developing an AI-based spinal analysis system.

Item Type:	Article
Uncontrolled Keywords:	Artificial intelligence
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	20 Feb 2025 06:38
Last Modified:	20 Feb 2025 07:51
URII:	http://shdl.mmu.edu.my/id/eprint/13518

Downloads

Edit (login required)