Radiological and Biological Dictionary of Radiomics Features: Addressing Understandable AI Issues in Personalized Breast Cancer; Dictionary Version BM1.0

TL;DR

This study introduces a dual-dictionary framework linking radiomics features to BI-RADS descriptors, improving interpretability of AI models for breast cancer diagnosis and validating known and novel imaging biomarkers.

Contribution

It presents a novel dual-dictionary approach that maps radiomics features to clinical descriptors, enhancing AI transparency in breast cancer imaging.

Findings

Best model achieved 83% accuracy in classifying TNBC.

Key features like Sphericity and Busyness correlated with TNBC.

Framework confirmed known and uncovered new imaging biomarkers.

Abstract

Radiomics-based AI models show promise for breast cancer diagnosis but often lack interpretability, limiting clinical adoption. This study addresses the gap between radiomic features (RF) and the standardized BI-RADS lexicon by proposing a dual-dictionary framework. First, a Clinically-Informed Feature Interpretation Dictionary (CIFID) was created by mapping 56 RFs to BI-RADS descriptors (shape, margin, internal enhancement) through literature and expert review. The framework was applied to classify triple-negative breast cancer (TNBC) versus non-TNBC using dynamic contrast-enhanced MRI from a multi-institutional cohort of 1,549 patients. We trained 27 machine learning classifiers with 27 feature selection methods. SHapley Additive exPlanations (SHAP) were used to interpret predictions and generate a complementary Data-Driven Feature Interpretation Dictionary (DDFID) for 52 additional RFs. The best model, combining Variance Inflation Factor (VIF) selection with Extra Trees Classifier, achieved an average cross-validation accuracy of 0.83. Key predictive RFs aligned with clinical knowledge: higher Sphericity (round/oval shape) and lower Busyness (more homogeneous enhancement) were associated with TNBC. The framework confirmed known imaging biomarkers and uncovered novel, interpretable associations. This dual-dictionary approach (BM1.0) enhances AI model transparency and supports the integration of RFs into routine breast cancer diagnosis and personalized care.