Pelvic floor MRI segmentation based on semi-supervised deep learning

TL;DR

This paper introduces a semi-supervised deep learning framework for pelvic floor MRI segmentation that effectively utilizes unlabeled data to improve segmentation accuracy and geometric reconstruction of pelvic organs.

Contribution

The proposed semi-supervised framework combines self-supervised pre-training and pseudo-labeling to enhance pelvic organ segmentation with limited labeled data.

Findings

Dice coefficient increased by 2.65% on average

Segmentation accuracy for difficult organs improved by up to 3.70%

Effective use of unlabeled data enhances segmentation performance

Abstract

The semantic segmentation of pelvic organs via MRI has important clinical significance. Recently, deep learning-enabled semantic segmentation has facilitated the three-dimensional geometric reconstruction of pelvic floor organs, providing clinicians with accurate and intuitive diagnostic results. However, the task of labeling pelvic floor MRI segmentation, typically performed by clinicians, is labor-intensive and costly, leading to a scarcity of labels. Insufficient segmentation labels limit the precise segmentation and reconstruction of pelvic floor organs. To address these issues, we propose a semi-supervised framework for pelvic organ segmentation. The implementation of this framework comprises two stages. In the first stage, it performs self-supervised pre-training using image restoration tasks. Subsequently, fine-tuning of the self-supervised model is performed, using labeled data to train the segmentation model. In the second stage, the self-supervised segmentation model is used to generate pseudo labels for unlabeled data. Ultimately, both labeled and unlabeled data are utilized in semi-supervised training. Upon evaluation, our method significantly enhances the performance in the semantic segmentation and geometric reconstruction of pelvic organs, Dice coefficient can increase by 2.65% averagely. Especially for organs that are difficult to segment, such as the uterus, the accuracy of semantic segmentation can be improved by up to 3.70%.