Training Set Augmentation and Biology-Aware Harmonization Improve Radiomic Models for Lung Cancer Prediction in Indeterminate Nodules

Abstract

CT radiomics-based machine learning has potential to predict lung cancer in pulmonary nodules (PNs) earlier than standard-of-care methods. Low malignancy rates in early-development PNs and variable image acquisition hinder development of radiomic models for diagnosing these PNs. To address these challenges, we augmented training using later-development PNs and harmonized for acquisition effects. We examine early-development benign and malignant PNs (n=106) below the sensitivity of standard-of-care diagnosis. Classifiers predicting malignancy performed near chance when trained on ComBat-harmonized radiomic features from only early-development PNs. We then augmented training with later-development benign and malignant PNs (n=225). We evaluated whether harmonization must incorporate biology that impacts acquisition effects in added training data. To correct variability from four acquisition protocols, we compared: 1) biology-unaware harmonization, 2) harmonizing with a covariate distinguishing early-development, later-development benign, later-development malignant datasets, 3) harmonizing each dataset separately. Models trained using augmentation, but biology-unaware harmonization, failed to improve consistently. Augmented training data harmonized with a covariate (ROC-AUC 0.74 [0.69-0.79]) or separately (ROC-AUC 0.71 [0.66-0.77]) yielded higher test ROC-AUC (Delong, p<=0.05) and PR-AUC (Wilcoxon, p<=0.05). In a proof-of-principle methodological study, we demonstrate with a small single-center dataset that combining radiomic features from later-development benign and malignant PNs requires biology-aware harmonization.