Recurrent Fully Convolutional Neural Networks for Multi-slice MRI Cardiac Segmentation

TL;DR

This paper introduces a recurrent fully convolutional neural network that effectively segments the heart in multi-slice MRI by leveraging inter-slice dependencies, achieving state-of-the-art accuracy and potential for real-time cardiac imaging applications.

Contribution

The paper presents a novel RFCN architecture that combines detection and segmentation in an end-to-end trainable model, improving efficiency and accuracy over existing methods.

Findings

RFCN achieves state-of-the-art segmentation accuracy.

The model improves contour delineation near the heart apex.

It demonstrates potential for real-time cardiac MRI analysis.

Abstract

In cardiac magnetic resonance imaging, fully-automatic segmentation of the heart enables precise structural and functional measurements to be taken, e.g. from short-axis MR images of the left-ventricle. In this work we propose a recurrent fully-convolutional network (RFCN) that learns image representations from the full stack of 2D slices and has the ability to leverage inter-slice spatial dependences through internal memory units. RFCN combines anatomical detection and segmentation into a single architecture that is trained end-to-end thus significantly reducing computational time, simplifying the segmentation pipeline, and potentially enabling real-time applications. We report on an investigation of RFCN using two datasets, including the publicly available MICCAI 2009 Challenge dataset. Comparisons have been carried out between fully convolutional networks and deep restricted Boltzmann machines, including a recurrent version that leverages inter-slice spatial correlation. Our studies suggest that RFCN produces state-of-the-art results and can substantially improve the delineation of contours near the apex of the heart.