CardiacNET: Segmentation of Left Atrium and Proximal Pulmonary Veins from MRI Using Multi-View CNN

TL;DR

CardiacNET introduces a multi-view CNN with an adaptive fusion strategy and novel loss function for accurate, efficient segmentation of the left atrium and pulmonary veins from MRI, aiding cardiac disease management.

Contribution

This work presents a new deep learning segmentation method using multi-view CNN with adaptive fusion and a novel loss function, achieving state-of-the-art results on cardiac MRI data.

Findings

Achieved 90% sensitivity and 99% specificity.

Segmentation completed in 10 seconds on GPU.

Outperformed existing methods on the STACOM 2013 benchmark.

Abstract

Anatomical and biophysical modeling of left atrium (LA) and proximal pulmonary veins (PPVs) is important for clinical management of several cardiac diseases. Magnetic resonance imaging (MRI) allows qualitative assessment of LA and PPVs through visualization. However, there is a strong need for an advanced image segmentation method to be applied to cardiac MRI for quantitative analysis of LA and PPVs. In this study, we address this unmet clinical need by exploring a new deep learning-based segmentation strategy for quantification of LA and PPVs with high accuracy and heightened efficiency. Our approach is based on a multi-view convolutional neural network (CNN) with an adaptive fusion strategy and a new loss function that allows fast and more accurate convergence of the backpropagation based optimization. After training our network from scratch by using more than 60K 2D MRI images (slices), we have evaluated our segmentation strategy to the STACOM 2013 cardiac segmentation challenge benchmark. Qualitative and quantitative evaluations, obtained from the segmentation challenge, indicate that the proposed method achieved the state-of-the-art sensitivity (90%), specificity (99%), precision (94%), and efficiency levels (10 seconds in GPU, and 7.5 minutes in CPU).