Cross-Vendor Reproducibility of Radiomics-based Machine Learning Models for Computer-aided Diagnosis

TL;DR

This study evaluates the reproducibility of radiomics-based machine learning models for prostate cancer detection across different MRI vendors, highlighting the challenges and potential solutions for clinical robustness.

Contribution

It introduces a multimodal feature fusion approach to improve the generalizability of ML models across different MRI vendors in prostate cancer detection.

Findings

SVM model achieved AUC of 0.74 on Siemens but dropped to 0.60 on Philips.

RF model was more robust with Pyradiomics features, achieving 0.78 AUC on Philips.

Multimodal feature integration shows promise for enhancing model robustness.

Abstract

Background: The reproducibility of machine-learning models in prostate cancer detection across different MRI vendors remains a significant challenge. Methods: This study investigates Support Vector Machines (SVM) and Random Forest (RF) models trained on radiomic features extracted from T2-weighted MRI images using Pyradiomics and MRCradiomics libraries. Feature selection was performed using the maximum relevance minimum redundancy (MRMR) technique. We aimed to enhance clinical decision support through multimodal learning and feature fusion. Results: Our SVM model, utilizing combined features from Pyradiomics and MRCradiomics, achieved an AUC of 0.74 on the Multi-Improd dataset (Siemens scanner) but decreased to 0.60 on the Philips test set. The RF model showed similar trends, with notable robustness for models using Pyradiomics features alone (AUC of 0.78 on Philips). Conclusions: These findings demonstrate the potential of multimodal feature integration to improve the robustness and generalizability of machine-learning models for clinical decision support in prostate cancer detection. This study marks a significant step towards developing reliable AI-driven diagnostic tools that maintain efficacy across various imaging platforms.