Feasibility of AI as first reader in the 4-IN-THE-LUNG-RUN lung cancer screening trial: impact on negative-misclassifications and clinical referral rate

Abstract

Background

Lung cancer screening (LCS) with low-dose CT (LDCT) reduces lung-cancer-related mortality in high-risk individuals. AI can potentially reduce radiologist workload as first-read-filter by ruling-out negative cases. The feasibility of AI as first reader was evaluated in the European 4-IN-THE-LUNG-RUN (4ITLR) trial, comparing its negative-misclassifications (NMs) to those of radiologists and the impact on referral rates.

Methods

NMs were collected from 3678 baseline LDCTs of the 4ITLR-dataset. LDCTs were read independently by radiologists and dedicated AI software (AVIEW-LCS, v1.1.42.92, Coreline-Soft, Seoul, Korea). A case was designated as NM when nodules > 100 mm³ were present and either radiologist or AI gave a negative-classification (only nodules <100 mm³ or no nodules), with an expert-panel as reference standard. A distinction was made between an indeterminate (100–300mm³), and positive (>300 mm³) classification, warranting referral for clinical-workup. Overall, there were 102 referrals (2.8 %) at baseline.

Results

Of the 3678 baseline scans, 438 NMs (11.9 %) were identified (age individuals: 68 (IQR: 64–73) years, 241 men); 31 (0.8 %) by AI and 407 (11.1 %) by radiologists. Among the 31 AI-NMs, 3 were classified positive and 28 indeterminate. Among the 407 radiologist-NMs, 4 were classified positive, and 403 were indeterminate, of which 8 were classified positive after receiving a three-month follow-up CT. Radiologists, as first reader, would have led to 12/102 (11.8 %) missed referrals, higher than the 3/102 (2.9 %) of AI.

Conclusion

This study showed AI outperforms radiologists with significantly less NMs and therefore shows promise as first reader in a LCS program at baseline, by independently ruling-out negative cases without substantially increasing the risk of missed clinical referrals.