Cross-Modality Multi-Atlas Segmentation via Deep Registration and Label Fusion

TL;DR

This paper introduces a deep learning-based cross-modality multi-atlas segmentation framework that efficiently registers atlases from one modality to segment images from another, improving accuracy and speed in medical image segmentation.

Contribution

It proposes novel deep neural networks for bi-directional registration and similarity estimation, enabling effective cross-modality segmentation with reduced computational cost.

Findings

Effective cross-modality segmentation demonstrated on ventricle and liver datasets.

Deep registration and label fusion networks outperform traditional methods.

Framework achieves high accuracy and efficiency in medical image segmentation.

Abstract

Multi-atlas segmentation (MAS) is a promising framework for medical image segmentation. Generally, MAS methods register multiple atlases, i.e., medical images with corresponding labels, to a target image; and the transformed atlas labels can be combined to generate target segmentation via label fusion schemes. Many conventional MAS methods employed the atlases from the same modality as the target image. However, the number of atlases with the same modality may be limited or even missing in many clinical applications. Besides, conventional MAS methods suffer from the computational burden of registration or label fusion procedures. In this work, we design a novel cross-modality MAS framework, which uses available atlases from a certain modality to segment a target image from another modality. To boost the computational efficiency of the framework, both the image registration and label fusion are achieved by well-designed deep neural networks. For the atlas-to-target image registration, we propose a bi-directional registration network (BiRegNet), which can efficiently align images from different modalities. For the label fusion, we design a similarity estimation network (SimNet), which estimates the fusion weight of each atlas by measuring its similarity to the target image. SimNet can learn multi-scale information for similarity estimation to improve the performance of label fusion. The proposed framework was evaluated by the left ventricle and liver segmentation tasks on the MM-WHS and CHAOS datasets, respectively. Results have shown that the framework is effective for cross-modality MAS in both registration and label fusion.