Neural Multi-Atlas Label Fusion: Application to Cardiac MR Images

TL;DR

This paper introduces a deep learning-based multi-atlas segmentation method called deep fusion net (DFN) that improves atlas selection and label fusion for cardiac MR images, achieving state-of-the-art results.

Contribution

The paper presents a novel deep learning framework that integrates feature extraction and label fusion in a single network for improved multi-atlas segmentation.

Findings

Achieved 0.833 Dice score on SATA-13 dataset

Achieved 0.95 Dice score on LV-09 dataset

Ranked highest in MICCAI 2013 SATA Segmentation Challenge

Abstract

Multi-atlas segmentation approach is one of the most widely-used image segmentation techniques in biomedical applications. There are two major challenges in this category of methods, i.e., atlas selection and label fusion. In this paper, we propose a novel multi-atlas segmentation method that formulates multi-atlas segmentation in a deep learning framework for better solving these challenges. The proposed method, dubbed deep fusion net (DFN), is a deep architecture that integrates a feature extraction subnet and a non-local patch-based label fusion (NL-PLF) subnet in a single network. The network parameters are learned by end-to-end training for automatically learning deep features that enable optimal performance in a NL-PLF framework. The learned deep features are further utilized in defining a similarity measure for atlas selection. By evaluating on two public cardiac MR datasets of SATA-13 and LV-09 for left ventricle segmentation, our approach achieved 0.833 in averaged Dice metric (ADM) on SATA-13 dataset and 0.95 in ADM for epicardium segmentation on LV-09 dataset, comparing favorably with the other automatic left ventricle segmentation methods. We also tested our approach on Cardiac Atlas Project (CAP) testing set of MICCAI 2013 SATA Segmentation Challenge, and our method achieved 0.815 in ADM, ranking highest at the time of writing.