T2-Only Prostate Cancer Prediction by Meta-Learning from Bi-Parametric MR Imaging
This work addresses the challenge of time-consuming and artifact-prone DWI sequences in prostate cancer imaging, offering a more efficient diagnostic approach for clinicians, though it is incremental as it builds on existing machine learning methods.
This study tackled the problem of reducing reliance on diffusion-weighted imaging (DWI) for prostate cancer diagnosis by developing a meta-learning model that uses only T2-weighted (T2w) sequences during inference, achieving superior or comparable performance in localizing cancer compared to models using T2-only or both sequences across datasets from over 3,000 patients.
Current imaging-based prostate cancer diagnosis requires both MR T2-weighted (T2w) and diffusion-weighted imaging (DWI) sequences, with additional sequences for potentially greater accuracy improvement. However, measuring diffusion patterns in DWI sequences can be time-consuming, prone to artifacts and sensitive to imaging parameters. While machine learning (ML) models have demonstrated radiologist-level accuracy in detecting prostate cancer from these two sequences, this study investigates the potential of ML-enabled methods using only the T2w sequence as input during inference time. We first discuss the technical feasibility of such a T2-only approach, and then propose a novel ML formulation, where DWI sequences - readily available for training purposes - are only used to train a meta-learning model, which subsequently only uses T2w sequences at inference. Using multiple datasets from more than 3,000 prostate cancer patients, we report superior or comparable performance in localising radiologist-identified prostate cancer using our proposed T2-only models, compared with alternative models using T2-only or both sequences as input. Real patient cases are presented and discussed to demonstrate, for the first time, the exclusively true-positive cases from models with different input sequences.