Towards Interpretable AI in Personalized Medicine: A Radiological-Biological Radiomics Dictionary Connecting Semantic Lung-RADS and imaging Radiomics Features; Dictionary LC 1.0

TL;DR

This paper introduces a radiological-biological dictionary linking Lung-RADS semantic descriptors with radiomic features, enhancing interpretability and explainability of AI models in lung cancer CT screening.

Contribution

It develops and validates a dictionary that maps Lung-RADS descriptors to radiomic features, integrating semi-supervised learning and interpretability methods for improved clinical AI.

Findings

Optimal classifier achieved 79% validation accuracy.

SHAP analysis identified key radiomic features linked to Lung-RADS semantics.

Dictionary supports explainable AI in lung cancer screening.

Abstract

Lung cancer remains the leading cause of cancer-related mortality worldwide, with survival strongly dependent on early detection. Standard-dose computed tomography (CT) screening using the Lung Imaging Reporting and Data System (Lung-RADS) standardizes pulmonary nodule assessment but is limited by inter-reader variability and reliance on qualitative descriptors, while radiomics offers quantitative biomarkers that often lack clinical interpretability. To bridge this gap, we propose a radiological-biological dictionary that aligns radiomic features (RFs) with Lung-RADS semantic categories. A clinically informed dictionary translating ten Lung-RADS descriptors into radiomic proxies was developed through literature curation and validated by eight expert reviewers. As a proof of concept, imaging and clinical data from 977 patients across 12 collections in The Cancer Imaging Archive (TCIA) were analyzed; following preprocessing and manual segmentation, 110 RFs per nodule were extracted using PyRadiomics in compliance with the Image Biomarker Standardization Initiative (IBSI). A semi-supervised learning framework incorporating 499 labeled and 478 unlabeled cases was applied to improve generalizability, evaluating seven feature selection methods and ten interpretable classifiers. The optimal pipeline (ANOVA feature selection with a support vector machine) achieved a mean validation accuracy of 0.79. SHapley Additive exPlanations (SHAP) analysis identified key RFs corresponding to Lung-RADS semantics such as attenuation, margin irregularity, and spiculation, supporting the validity of the proposed mapping. Overall, this dictionary provides an interpretable framework linking radiomics and Lung-RADS semantics, advancing explainable artificial intelligence for CT-based lung cancer screening.