Assessing the clinicians’ pathway to embed artificial intelligence for assisted diagnostics of fracture detection.

Moreno-García, Carlos Francisco; Dang, Truong; Martin, Kyle; Patel, Manish; Thompson, Andrew; Leishman, Lesley; Wiratunga, Nirmalie

Abstract

Fracture detection has been a long-standingparadigm on the medical imaging community. Many algo-rithms and systems have been presented to accurately detectand classify images in terms of the presence and absence offractures in different parts of the body. While these solutionsare capable of obtaining results which even surpass humanscores, few efforts have been dedicated to evaluate how thesesystems can be embedded in the clinicians and radiologistsworking pipeline. Moreover, the reports that are included withthe radiography could also provide key information regardingthe nature and the severity of the fracture. In this paper, wepresent our first findings towards assessing how computer vi-sion, natural language processing and other systems could becorrectly embedded in the clinicians’ pathway to better aidon the fracture detection task. We present some initial exper-imental results using publicly available fracture datasets alongwith a handful of data provided by the National HealthcareSystem from the United Kingdom in a research initiative call.Results show that there is a high likelihood of applying trans-fer learning from different existing and pre-trained models tothe new records provided in the challenge, and that thereare various ways in which these techniques can be embeddedalong the clinicians’ pathway.

Citation

MORENO-GARCÍA, C.F., DANG, T., MARTIN, K., PATEL, M., THOMPSON, A., LEISHMAN, L. and WIRATUNGA, N. 2020. Assessing the clinicians’ pathway to embed artificial intelligence for assisted diagnostics of fracture detection. In Bach, K., Bunescu, R., Marling, C. and Wiratunga, N. (eds.) Knowledge discovery in healthcare data 2020: proceedings of the 5th Knowledge discovery in healthcare data international workshop 2020 (KDH 2020), co-located with 24th European Artificial intelligence conference (ECAI 2020), 29-30 August 2020, [virtual conference]. CEUR workshop proceedings, 2675. Aachen: CEUR-WS [online], pages 63-70. Available from: http://ceur-ws.org/Vol-2675/paper10.pdf

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 5th Knowldege discovery in healthcare data international workshop conference (KDH 2020), co-located with 24th European Artificial intelligence conference (ECAI 2020)
• Start Date: Aug 29, 2020
• End Date: Aug 30, 2020
• Acceptance Date: Jun 1, 2020
• Online Publication Date: Sep 18, 2020
• Publication Date: Sep 18, 2020
• Deposit Date: Sep 18, 2020
• Publicly Available Date: Sep 21, 2020
• Publisher: CEUR-WS
• Peer Reviewed: Peer Reviewed
• Pages: 63-70
• Series Title: CEUR workshop proceedings
• Series Number: 2675
• Series ISSN: 1613-0073
• Book Title: Knowledge discovery in healthcare data 2020
• Keywords: Fracture detection; Natural language processing; Convolutional neural networks; Clinicians’ pathway
• Public URL: https://rgu-repository.worktribe.com/output/968418
• Publisher URL: http://ceur-ws.org/Vol-2675/