Combating Uncertainty with Novel Losses for Automatic Left Atrium Segmentation

Abstract

Segmenting left atrium in MR volume holds great potentials in promoting the treatment of atrial fibrillation. However, the varying anatomies, artifacts and low contrasts among tissues hinder the advance of both manual and automated solutions. In this paper, we propose a fully-automated framework to segment left atrium in gadoliniumenhanced MR volumes. The region of left atrium is firstly automatically localized by a detection module. Our framework then originates with a customized 3D deep neural network to fully explore the spatial dependency in the region for segmentation. To alleviate the risk of low training efficiency and potential overfitting, we enhance our deep network with the transfer learning and deep supervision strategy. Main contribution of our network design lies in the composite loss function to combat the boundary ambiguity and hard examples. We firstly adopt the Overlap loss to encourage network reduce the overlap between the foreground and background and thus sharpen the predictions on boundary. We then propose a novel Focal Positive loss to guide the learning of voxel-specific threshold and emphasize the foreground to improve classification sensitivity. Further improvement is obtained with an recursive training scheme. With ablation studies, all the introduced modules prove to be effective. The proposed framework achieves an average Dice of 92.24% in segmenting left atrium with pulmonary veins on 20 testing volumes.

Evaluation of algorithms for Multi-Modality Whole Heart Segmentation: An open-access grand challenge

“…Yang et al. (2017b) apply a general and fully automatic framework based on a 3D fully convolutional network (FCN).…”

Mini Review: Deep Learning for Atrial Segmentation From Late Gadolinium-Enhanced MRIs

“…As a result, the learning process was entirely focused on a smaller region of interest (ROI), allowing better representation of the LA features. Based on a similar principle, other researchers (55)(56)(57), pushed this idea a step further by using a multi-CNN approach for atrial segmentation ( Figure 3A). In their approaches, two consecutive networks were employed instead.…”

3D Bounding Box Detection in Volumetric Medical Image Data: A Systematic Literature Review

“…A common approach is to use a single 2D CNN or a combination (2.5D) of several (usually three) 2D CNNs for slice wise detection in either one or all three orthogonal viewing plane directions. A single 2D CNN can be implemented to analyze exactly one of the three image plane stacks [27], [28], [29], [30]. Adjacent slices as additional channels [31] or dimensions [32] help to capture contextual information.…”