OASIS: One-pass aligned Atlas Set for Image Segmentation

TL;DR

OASIS introduces a deep learning-based one-pass aligned atlas set framework for efficient and accurate medical image segmentation, reducing registration time and focusing on relevant regions to improve performance.

Contribution

The paper presents a novel deep learning approach for one-pass image registration and a label fusion strategy, enhancing atlas-based segmentation efficiency and accuracy.

Findings

Significantly improved prostate MR segmentation accuracy

Reduced registration time compared to iterative methods

Effective focus on regions of interest during registration

Abstract

Medical image segmentation is a fundamental task in medical image analysis. Despite that deep convolutional neural networks have gained stellar performance in this challenging task, they typically rely on large labeled datasets, which have limited their extension to customized applications. By revisiting the superiority of atlas based segmentation methods, we present a new framework of One-pass aligned Atlas Set for Images Segmentation (OASIS). To address the problem of time-consuming iterative image registration used for atlas warping, the proposed method takes advantage of the power of deep learning to achieve one-pass image registration. In addition, by applying label constraint, OASIS also makes the registration process to be focused on the regions to be segmented for improving the performance of segmentation. Furthermore, instead of using image based similarity for label fusion, which can be distracted by the large background areas, we propose a novel strategy to compute the label similarity based weights for label fusion. Our experimental results on the challenging task of prostate MR image segmentation demonstrate that OASIS is able to significantly increase the segmentation performance compared to other state-of-the-art methods.