Oncologic Applications of Artificial Intelligence and Deep Learning Methods in CT Spine Imaging-A Systematic Review

• Published in: Cancers Vol. 16; no. 17; p. 2988
• Main Authors: Ong, Wilson, Lee, Aric, Tan, Wei Chuan, Fong, Kuan Ting Dominic, Lai, Daoyong David, Tan, Yi Liang, Low, Xi Zhen, Ge, Shuliang, Makmur, Andrew, Ong, Shao Jin, Ting, Yong Han, Tan, Jiong Hao, Kumar, Naresh, Hallinan, James Thomas Patrick Decourcy
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 28-08-2024
• Subjects: Accuracy; Algorithms; Artificial intelligence; Classification; Computed tomography; Datasets; Decision making; Deep learning; Fractures; Machine learning; Malignancy; Medical imaging; Metastasis; Neural networks; Oncology; Radiomics; Systematic review; Tumors; spinal oncology; deep learning; computed tomography imaging; machine learning; artificial intelligence; applications
• ISSN: 2072-6694; 2072-6694
• DOI: 10.3390/cancers16172988

In spinal oncology, integrating deep learning with computed tomography (CT) imaging has shown promise in enhancing diagnostic accuracy, treatment planning, and patient outcomes. This systematic review synthesizes evidence on artificial intelligence (AI) applications in CT imaging for spinal tumors. A PRISMA-guided search identified 33 studies: 12 (36.4%) focused on detecting spinal malignancies, 11 (33.3%) on classification, 6 (18.2%) on prognostication, 3 (9.1%) on treatment planning, and 1 (3.0%) on both detection and classification. Of the classification studies, 7 (21.2%) used machine learning to distinguish between benign and malignant lesions, 3 (9.1%) evaluated tumor stage or grade, and 2 (6.1%) employed radiomics for biomarker classification. Prognostic studies included three (9.1%) that predicted complications such as pathological fractures and three (9.1%) that predicted treatment outcomes. AI's potential for improving workflow efficiency, aiding decision-making, and reducing complications is discussed, along with its limitations in generalizability, interpretability, and clinical integration. Future directions for AI in spinal oncology are also explored. In conclusion, while AI technologies in CT imaging are promising, further research is necessary to validate their clinical effectiveness and optimize their integration into routine practice.