CondenseUNet: A Memory-Efficient Condensely-Connected Architecture for Bi-ventricular Blood Pool and Myocardium Segmentation
This work addresses the need for fast and accurate automatic segmentation of heart structures to aid in pre-operative planning for cardiac procedures, though it is incremental as it modifies existing architectures.
The paper tackled the problem of accurate and memory-efficient segmentation of cardiac structures from CMR images by proposing CondenseUNet, a modified CNN architecture. It achieved dice scores of 96.78% for LV blood-pool, 93.46% for RV blood-pool, and 90.1% for LV-myocardium while using 50% less memory than DenseNet and 92% less than U-Net.
With the advent of Cardiac Cine Magnetic Resonance (CMR) Imaging, there has been a paradigm shift in medical technology, thanks to its capability of imaging different structures within the heart without ionizing radiation. However, it is very challenging to conduct pre-operative planning of minimally invasive cardiac procedures without accurate segmentation and identification of the left ventricle (LV), right ventricle (RV) blood-pool, and LV-myocardium. Manual segmentation of those structures, nevertheless, is time-consuming and often prone to error and biased outcomes. Hence, automatic and computationally efficient segmentation techniques are paramount. In this work, we propose a novel memory-efficient Convolutional Neural Network (CNN) architecture as a modification of both CondenseNet, as well as DenseNet for ventricular blood-pool segmentation by introducing a bottleneck block and an upsampling path. Our experiments show that the proposed architecture runs on the Automated Cardiac Diagnosis Challenge (ACDC) dataset using half (50%) the memory requirement of DenseNet and one-twelfth (~ 8%) of the memory requirements of U-Net, while still maintaining excellent accuracy of cardiac segmentation. We validated the framework on the ACDC dataset featuring one healthy and four pathology groups whose heart images were acquired throughout the cardiac cycle and achieved the mean dice scores of 96.78% (LV blood-pool), 93.46% (RV blood-pool) and 90.1% (LV-Myocardium). These results are promising and promote the proposed methods as a competitive tool for cardiac image segmentation and clinical parameter estimation that has the potential to provide fast and accurate results, as needed for pre-procedural planning and/or pre-operative applications.