M D B S Tam1, T Dyer2, G Dissez2, T Naunton Morgan2, M Hughes2, J Illes3, R Rasalingham2, S Rasalingham2. 1. Mid and South Essex University Hospitals Group, Southend Hospital, Department of Radiology, Prittlewell Chase, Westcliff-on-Sea, SS0 0RY, UK. Electronic address: matthewtam2005@gmail.com. 2. Behold.ai, 180 Borough High St, London SE1 1LB, UK. 3. Dorset County Hospital Foundation Trust, Williams Ave, Dorchester, DT1 2JY, UK.
Abstract
AIM: To evaluate the role that artificial intelligence (AI) could play in assisting radiologists as the first reader of chest radiographs (CXRs), to increase the accuracy and efficiency of lung cancer diagnosis by flagging positive cases before passing the remaining examinations to standard reporting. MATERIALS AND METHODS: A dataset of 400 CXRs including 200 difficult lung cancer cases was curated. Examinations were reviewed by three FRCR radiologists and an AI algorithm to establish performance in tumour identification. AI and radiologist labels were combined retrospectively to simulate the proposed AI triage workflow. RESULTS: When used as a standalone algorithm, AI classification was equivalent to the average radiologist performance. The best overall performances were achieved when AI was combined with radiologists, with an average reduction of missed cancers of 60%. Combination with AI also standardised the performance of radiologists. The greatest improvements were observed when common sources of errors were present, such as distracting findings. DISCUSSION: The proposed AI implementation pathway stands to reduce radiologist errors and improve clinician reporting performance. Furthermore, taking a radiologist-centric approach in the development of clinical AI holds promise for catching systematically missed lung cancers. This represents a tremendous opportunity to improve patient outcomes for lung cancer diagnosis.
AIM: To evaluate the role that artificial intelligence (AI) could play in assisting radiologists as the first reader of chest radiographs (CXRs), to increase the accuracy and efficiency of lung cancer diagnosis by flagging positive cases before passing the remaining examinations to standard reporting. MATERIALS AND METHODS: A dataset of 400 CXRs including 200 difficult lung cancer cases was curated. Examinations were reviewed by three FRCR radiologists and an AI algorithm to establish performance in tumour identification. AI and radiologist labels were combined retrospectively to simulate the proposed AI triage workflow. RESULTS: When used as a standalone algorithm, AI classification was equivalent to the average radiologist performance. The best overall performances were achieved when AI was combined with radiologists, with an average reduction of missed cancers of 60%. Combination with AI also standardised the performance of radiologists. The greatest improvements were observed when common sources of errors were present, such as distracting findings. DISCUSSION: The proposed AI implementation pathway stands to reduce radiologist errors and improve clinician reporting performance. Furthermore, taking a radiologist-centric approach in the development of clinical AI holds promise for catching systematically missed lung cancers. This represents a tremendous opportunity to improve patient outcomes for lung cancer diagnosis.