Precision-medicine-toolbox: An open-source python package for facilitation of quantitative medical imaging and radiomics analysis

TL;DR

The paper tackles the lack of standardized data curation and preprocessing in radiomics by introducing the precision-medicine-toolbox, an open-source Python package for end-to-end data curation, image pre-processing, and IBSI-compliant handcrafted radiomics feature extraction via PyRadiomics, plus feature exploration. It presents a modular, open implementation with base classes for imaging and features, organized into ToolBox and AnalysisBox components, demonstrated on the Lung1 NSCLC dataset with comprehensive documentation and tutorials. The toolbox addresses reproducibility and interoperability challenges in radiomics, enabling rapid data quality checks, consistent preprocessing, feature extraction, and exploratory analysis, while inviting community contributions. Practically, it provides a reusable, extendable workflow that can serve researchers with varying programming expertise and supports broader adoption of quantitative medical imaging in precision medicine.

Abstract

Medical image analysis plays a key role in precision medicine as it allows the clinicians to identify anatomical abnormalities and it is routinely used in clinical assessment. Data curation and pre-processing of medical images are critical steps in the quantitative medical image analysis that can have a significant impact on the resulting model performance. In this paper, we introduce a precision-medicine-toolbox that allows researchers to perform data curation, image pre-processing and handcrafted radiomics extraction (via Pyradiomics) and feature exploration tasks with Python. With this open-source solution, we aim to address the data preparation and exploration problem, bridge the gap between the currently existing packages, and improve the reproducibility of quantitative medical imaging research.