A study of CNN capacity applied to Left Venticle Segmentation in Cardiac MRI

  title={A study of CNN capacity applied to Left Venticle Segmentation in Cardiac MRI},
  author={Marcelo Toledo and Daniel Lima and Jos{\'e} Eduardo Krieger and Marco Antonio Gutierrez},
CNN (Convolutional Neural Network) models have been successfully used for segmentation of the left ventricle (LV) in cardiac MRI (Magnetic Resonance Imaging), providing clinical measurements. In practice, two questions arise with deployment of CNNs: 1) when is it better to use a shallow model instead of a deeper one? 2) how the size of a dataset might change the network performance? We propose a framework to answer them, by experimenting with deep and shallow versions of three U-Net families… 

Figures and Tables from this paper


Deep Learning for Cardiac Image Segmentation: A Review
A review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging, computed tomography, and ultrasound and major anatomical structures of interest.
U-Net: Convolutional Networks for Biomedical Image Segmentation
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Attention U-Net: Learning Where to Look for the Pancreas
A novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes is proposed to eliminate the necessity of using explicit external tissue/organ localisation modules of cascaded convolutional neural networks (CNNs).
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
This paper presents UNet++, a new, more powerful architecture for medical image segmentation where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways, and argues that the optimizer would deal with an easier learning task when the feature maps from the decoder and encoder networks are semantically similar.
Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy
A 3D U-Net architecture that achieves performance similar to experts in delineating a wide range of head and neck OARs is demonstrated that could improve the effectiveness of radiotherapy pathways.
Squeeze-and-Excitation Networks
This work proposes a novel architectural unit, which is term the “Squeeze-and-Excitation” (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels and shows that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets.
A collaborative resource to build consensus for automated left ventricular segmentation of cardiac MR images
The consensus segmentation based on a combination of manual and automated raters were more consistent than any particular rater, even those with manual input, and the consensus is expected to improve with the addition of new automated contributions.
Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration
Highlights • Six openly-available neural networks for prostate MR segmentation were compared, based on experiment results using 232-patient clinical imaging and label data.• Statistically significant
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
A new scaling method is proposed that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient and is demonstrated the effectiveness of this method on scaling up MobileNets and ResNet.
State of the Heart: CMR in Coronary Artery Disease
Cardiac magnetic resonance (CMR) has the ability to assess the heart comprehensively, examining cardiac morphology, ventricular function, perfusion, myocardial viability, as well as delineation and quantification of tissue constituents, and is currently the modality of choice in a number of cardiac diseases.