Improving prostate whole gland segmentation in t2-weighted MRI with synthetically generated data

TL;DR

This paper introduces a GAN-based pipeline to generate synthetic prostate MRI data and segmentation masks, enhancing deep learning model performance for whole gland segmentation compared to traditional augmentation methods.

Contribution

The study presents a novel GAN-driven data augmentation approach for prostate MRI segmentation, improving model accuracy over standard techniques.

Findings

Synthetic data improved segmentation accuracy

GAN-based augmentation outperformed traditional methods

Enhanced model robustness with synthetic data

Abstract

Whole gland (WG) segmentation of the prostate plays a crucial role in detection, staging and treatment planning of prostate cancer (PCa). Despite promise shown by deep learning (DL) methods, they rely on the availability of a considerable amount of annotated data. Augmentation techniques such as translation and rotation of images present an alternative to increase data availability. Nevertheless, the amount of information provided by the transformed data is limited due to the correlation between the generated data and the original. Based on the recent success of generative adversarial networks (GAN) in producing synthetic images for other domains as well as in the medical domain, we present a pipeline to generate WG segmentation masks and synthesize T2-weighted MRI of the prostate based on a publicly available multi-center dataset. Following, we use the generated data as a form of data augmentation. Results show an improvement in the quality of the WG segmentation when compared to standard augmentation techniques.