Meeting Banner
Abstract #1396

Explainable Radiomics-Based ML for Predicting Clinically Significant Prostate Cancer in Biparametric MRI

Mahmoud Morafegh1,2, Gelareh Valizadeh1, Farzan Moodi1,3, Mahyar Ghafoori4, Ahmad Mostaar2, and Hamidreza Saligheh Rad1,5
1Quantitative MR Imaging and Spectroscopy Group (QMISG, Tehran University of Medical Sciences, Tehran, Iran (Islamic Republic of), 2Department of Medical Physics and Biomedical Engineering, Shahid Beheshti University of Medical Sciences, Tehran, Iran (Islamic Republic of), 3School of Medicine, Iran University of Medical Sciences, Tehran, Iran (Islamic Republic of), 4Department of Radiology, School of Medicine, Hazrat Rasoul Akram Hospital, Iran University of Medical Sciences, Tehran, Iran (Islamic Republic of), 5Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran (Islamic Republic of)

Synopsis

Keywords: Diagnosis/Prediction, Machine Learning/Artificial Intelligence

Motivation: Prostate MRI interpretation is complex and subjective, facing challenges in diagnosis Prostate Cancer (PCa). Interpretable AI models are needed to aid diagnostic process.

Goal(s): To develop explainable Machine Learning (ML) models using MRI-derived radiomic features to classify clinically significant prostate cancer (csPCa).

Approach: A retrospective study using MRI exams of 344 patients was conducted. Radiomic features were extracted from T2-weighted and Apparent diffusion coefficient maps. ML classifiers were trained and evaluated, with SHapley Additive exPlanations (SHAP) analysis used for interpretability.

Results: Random Forest model achieved an AUC of 0.85, with SHAP analysis clarifying radiomic feature contributions and enhancing model transparency.

Impact: The development of explainable ML models using biparametric MRI radiomic features enhances csPCa classification, proposing a framework that connects prediction and interpretability. This approach can lead further research into transparent AI tools, benefiting clinical decision-making.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords