What type of study is this?

This is a Quantitative Study study.

September 17, 2025

Improved Prostate Luminal Water Fraction Estimation from Radial Turbo Spin-Echo Imaging Using ANN-WGAN

Key Points

ANN-WGAN significantly improves luminal water fraction (LWF) estimation for prostate MRI, enhancing diagnostic accuracy.
The study shows that ANN-WGAN outperforms NNLS by providing reliable LWF predictions in both volunteer scans and patient data.
A novel method utilizing ANN and WGAN generates training data closely matching T2 decay signals, improving estimation robustness.
Improved LWF estimation may enhance lesion differentiation in prostate cancer imaging, reducing reliance on predefined data.

Abstract

Motivation: Traditional Luminal Water Fraction (LWF) estimation models, such as NNLS, are prone to noise and may underestimate LWF in low-value regions. Goal(s): This study aims to improve LWF estimation by integrating a Wasserstein Generative Adversarial Network (WGAN) and an artificial neural networks (ANN). Approach: The ANN-WGAN model generates training data that closely matches real T2 decay signals, which is used to train the ANN for more reliable LWF predictions. Performance is compared with NNLS-based models. Results: ANN-WGAN outperforms NNLS-based model in simulations, volunteer scans, and patient data, offering enhanced accuracy and robustness in LWF estimation. Impact: This work introduces a more robust method for Luminal Water Fraction (LWF) estimation in prostate MRI, enhancing lesion differentiation and reducing reliance on predefined training data. It improves LWF consistency and reliability, potentially aiding in prostate cancer imaging and diagnosis.

Mark Helpful

Bookmark

Relay