Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

T2-Only Prostate Cancer Prediction by Meta-Learning from Bi-Parametric MR Imaging

Weixi Yi, Yipei Wang, Natasha Thorley, Alexander Ng, Shonit Punwani, Veeru Kasivisvanathan, Dean C. Barratt, Shaheer Ullah Saeed, Yipeng Hu

TL;DR

This study investigates the potential of ML-enabled methods using only the T2w sequence as input during inference time, and proposes a novel ML formulation, where DWI sequences are only used to train a meta-learning model, which subsequently only uses T2w sequences at inference.

Abstract

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.

T2-Only Prostate Cancer Prediction by Meta-Learning from Bi-Parametric MR Imaging

TL;DR

This study investigates the potential of ML-enabled methods using only the T2w sequence as input during inference time, and proposes a novel ML formulation, where DWI sequences are only used to train a meta-learning model, which subsequently only uses T2w sequences at inference.

Abstract

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.

Paper Structure

This paper contains 17 sections, 3 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methods
  3. Modality translator: T2w-conditioned diffusion
  4. Cancer predictor for lesion segmentation
  5. MetaT2: a bi-level meta-learning algorithm
  6. Optimizing the cancer predictor
  7. Optimizing the modality translator
  8. Bi-level optimisation of the networks
  9. Experiments
  10. Dataset
  11. Evaluation Metrics
  12. Implementation Details
  13. Comparison and ablation studies
  14. Results
  15. Conclusion
  16. ...and 2 more sections

Figures (3)

  • Figure 1: Illustration of the proposed bi-level meta learning framework MetaT2. Details are described in Sec. \ref{['sec:method']}.
  • Figure 2: Samples with segmentation from the tested methods. The red and green contours represent ground truth and prediction, respectively.
  • Figure 3: Samples of T2w images, corresponding real DWI, and DWI images generated by different methods. The red contours indicate the lesion ground truth.