Open-radiomics: A Collection of Standardized Datasets and a Technical Protocol for Reproducible Radiomics Machine Learning Pipelines

TL;DR

This paper introduces open-radiomics, a standardized collection of datasets and a protocol to enhance reproducibility in radiomics machine learning pipelines, demonstrating how variability sources affect model performance.

Contribution

It provides a comprehensive, standardized radiomics dataset collection and a technical protocol to improve reproducibility and understand variability sources in radiomics ML pipelines.

Findings

Tumor subregion and imaging sequence significantly impact model performance.

Highest AUROC achieved was 0.951 with specific MRI sequence and tumor subregion.

Superficial perfect performances are often irreproducible due to variability sources.

Abstract

Background: As an important branch of machine learning pipelines in medical imaging, radiomics faces two major challenges namely reproducibility and accessibility. In this work, we introduce open-radiomics, a set of radiomics datasets along with a comprehensive radiomics pipeline based on our proposed technical protocol to improve the reproducibility of the results. Methods: We curated large-scale radiomics datasets based on three open-source datasets; BraTS 2020 for high-grade glioma (HGG) versus low-grade glioma (LGG) classification and survival analysis, BraTS 2023 for O6-methylguanine-DNA methyltransferase classification, and non-small cell lung cancer survival analysis from the Cancer Imaging Archive. Using BraTS 2020 Magnetic Resonance Imaging (MRI) dataset, we applied our protocol to 369 brain tumor patients (76 LGG, 293 HGG). Leveraging PyRadiomics for LGG vs. HGG classification, we generated 288 datasets from 4 MRI sequences, 3 binWidths, 6 normalization methods, and 4 tumor subregions. Random Forest classifiers were trained and validated (60%,20%,20%) across 100 different data splits (28,800 test results), evaluating Area Under the Receiver Operating Characteristic Curve (AUROC). Results: Unlike binWidth and image normalization, tumor subregion and imaging sequence significantly affected performance of the models. T1 contrast-enhanced sequence and the union of Necrotic and the non-enhancing tumor core subregions resulted in the highest AUROCs (average test AUROC 0.951, 95% confidence interval of (0.949, 0.952)). Although several settings and data splits (28 out of 28800) yielded test AUROC of 1, they were irreproducible. Conclusion: Our experiments demonstrate the sources of variability in radiomics pipelines (e.g., tumor subregion) can have a significant impact on the results, which may lead to superficial perfect performances that are irreproducible.