Effective 3D Humerus and Scapula Extraction using Low-contrast and High-shape-variability MR Data

TL;DR

This paper introduces a deep learning method for segmenting humerus and scapula bones from low-contrast, high-variability 3D MR images, using self-reinforced learning to improve accuracy on scarce data.

Contribution

It presents a novel joint segmentation network with a self-reinforced learning strategy tailored for low-resolution, high-variability MR data.

Findings

Outperforms classical multi-atlas methods in accuracy.

Effective in low-contrast, high-shape-variability scenarios.

Improves bone mask quality with limited data.

Abstract

For the initial shoulder preoperative diagnosis, it is essential to obtain a three-dimensional (3D) bone mask from medical images, e.g., magnetic resonance (MR). However, obtaining high-resolution and dense medical scans is both costly and time-consuming. In addition, the imaging parameters for each 3D scan may vary from time to time and thus increase the variance between images. Therefore, it is practical to consider the bone extraction on low-resolution data which may influence imaging contrast and make the segmentation work difficult. In this paper, we present a joint segmentation for the humerus and scapula bones on a small dataset with low-contrast and high-shape-variability 3D MR images. The proposed network has a deep end-to-end architecture to obtain the initial 3D bone masks. Because the existing scarce and inaccurate human-labeled ground truth, we design a self-reinforced learning strategy to increase performance. By comparing with the non-reinforced segmentation and a classical multi-atlas method with joint label fusion, the proposed approach obtains better results.