PurposeTo compare the variability of quantitative values from lung adenocarcinoma CT images independently assessed by two radiologists and AI-based software under different display conditions, and to identify predictors of pathological lymph node metastasis (LNM), disease-free survival (DFS), and overall survival (OS). MethodsPreoperative CT images of 307 patients were displayed under four conditions: lung-1, lung-2, mediastinum-1, and mediastinum-2. Two radiologists (R1, R2) measured total diameter (tD) and the longest solid diameter (sD) under each condition. The AI-based software automatically detected lung nodules, providing tD, sD, total volume (tV), and solid volume (sV). ResultsAll measurements by R1 and R2 with AI-based software were identical. Four out of the eight measurements showed significant variation between R1 and R2. For LNM, multivariate logistic regression identified significant indicators including sD at mediastinum-2 of R1, sD at mediastinum-1 and mediastinum-2 of R2, tV, and the proportion of sV to tV (sV/tV) of AI-based software. For DFS, multivariate Cox regression identified sD at lung-1 of R1, the proportions of sD to tD at lung-2 of R1, sD at lung-2 and mediastinum-1 of R2, tV, and sV/tV of AI-based software as significant. For OS, multivariate Cox regression identified sD at lung-1 and mediastinum-2 of R1, tD at lung-2 of R2, sD at mediastinum-1 of R2, sV, and sV/tV of AI-based software as significant. ConclusionRadiologists’ CT measurements were significant predictors of LNM and prognosis, but variability existed among radiologists and display conditions. AI-based software can provide accurate and reproducible indicators for predicting LNM and prognosis.Micro-abstract: Accurate measurement of lung adenocarcinoma is crucial for determining treatment plan and predicting prognosis. However, inter-observer variability and display conditions can affect these measurements. We compared tumor size measurements between radiologists and commercially available AI-based software using preoperative CT images from 307 cases and evaluated their predictive value for lymph node metastasis, disease-free survival, and overall survival. We concluded that while radiologist measurements showed inter-observer variability, AI-based software provided accurate and reproducible prognostic indicators.
Read full abstract