Charting the potential of brain computed tomography deep learning systems. (May 2022)

• Record Type: Journal Article
• Authors: Buchlak, Quinlan D.; Milne, Michael R.; Seah, Jarrel; Johnson, Andrew; Samarasinghe, Gihan; Hachey, Ben; Esmaili, Nazanin; Tran, Aengus; Leveque, Jean-Christophe; Farrokhi, Farrokh; Goldschlager, Tony; Edelstein, Simon; Brotchie, Peter
• Is Part Of: Journal of clinical neuroscience. Volume 99(2022)
• Page Start: 217
• Page End: 223
• Publication Date: 2022-05
• Subjects: Brain computed tomography -- Machine learning -- Deep learning -- Patient safety -- Clinical decision making; Brain -- Surgery -- Periodicals; Neurosciences -- Periodicals; Nervous system -- Surgery -- Periodicals; Brain -- surgery -- Periodicals; Neurosurgical Procedures -- Periodicals; Neurosciences -- Periodicals; Electronic journals; 616.8
• DOI: 10.1016/j.jocn.2022.03.014
• Languages: English
• ISSNs: 0967-5868

Abstract

Highlights: The application of machine learning to brain computed tomography (CTB) data shows promise for improving diagnostic accuracy and triage. Most existing CTB machine learning models lack clinical comprehensiveness and sufficient external validation. There is an opportunity to develop comprehensive, low-bias CTB classification systems that demonstrate greater clinical utility. Comprehensive systems promise to improve diagnosis, decision making, treatment timeliness, clinical audits, and education at scale. Abstract: Brain computed tomography (CTB) scans are widely used to evaluate intracranial pathology. The implementation and adoption of CTB has led to clinical improvements. However, interpretation errors occur and may have substantial morbidity and mortality implications for patients. Deep learning has shown promise for facilitating improved diagnostic accuracy and triage. This research charts the potential of deep learning applied to the analysis of CTB scans. It draws on the experience of practicing clinicians and technologists involved in development and implementation of deep learning-based clinical decision support systems. We consider the past, present and future of the CTB, along with limitations of existing systems as well as untapped beneficial use cases. Implementing deep learning CTB interpretation systems and effectively navigating development and implementation risks can deliver many benefits to clinicians and patients, ultimately improving efficiency and safety in healthcare.