Machine learning for automatic construction of pseudo-realistic pediatric abdominal phantoms

TL;DR

This paper introduces a machine learning-based method to automatically create individualized pediatric abdominal phantoms from limited patient data, improving the realism and specificity of virtual models used in radiation therapy simulations.

Contribution

The study presents a novel ML approach that combines imaging data and patient features to automatically generate personalized phantoms, enhancing current simple heuristic-based methods.

Findings

ML-based phantoms are more representative of actual patient anatomy.

GP-GOMEA algorithm provides the best performance and interpretability.

Approach significantly improves the realism of pediatric abdominal phantoms.

Abstract

Machine Learning (ML) is proving extremely beneficial in many healthcare applications. In pediatric oncology, retrospective studies that investigate the relationship between treatment and late adverse effects still rely on simple heuristics. To assess the effects of radiation therapy, treatment plans are typically simulated on phantoms, i.e., virtual surrogates of patient anatomy. Currently, phantoms are built according to reasonable, yet simple, human-designed criteria. This often results in a lack of individualization. We present a novel approach that combines imaging and ML to build individualized phantoms automatically. Given the features of a patient treated historically (only 2D radiographs available), and a database of 3D Computed Tomography (CT) imaging with organ segmentations and relative patient features, our approach uses ML to predict how to assemble a patient-specific phantom automatically. Experiments on 60 abdominal CTs of pediatric patients show that our approach constructs significantly more representative phantoms than using current phantom building criteria, in terms of location and shape of the abdomen and of two considered organs, the liver and the spleen. Among several ML algorithms considered, the Gene-pool Optimal Mixing Evolutionary Algorithm for Genetic Programming (GP-GOMEA) is found to deliver the best performing models, which are, moreover, transparent and interpretable mathematical expressions.