A Fully Convolutional Neural Network for Cardiac Segmentation in Short-Axis MRI

Abstract

Automated cardiac segmentation from magnetic resonance imaging datasets is an essential step in the timely diagnosis and management of cardiac pathologies. We propose to tackle the problem of automated left and right ventricle segmentation through the application of a deep fully convolutional neural network architecture. Our model is efficiently trained end-to-end in a single learning stage from whole-image inputs and ground truths to make inference at every pixel. To our knowledge, this is the first application of a fully convolutional neural network architecture for pixel-wise labeling in cardiac magnetic resonance imaging. Numerical experiments demonstrate that our model is robust to outperform previous fully automated methods across multiple evaluation measures on a range of cardiac datasets. Moreover, our model is fast and can leverage commodity compute resources such as the graphics processing unit to enable state-of-the-art cardiac segmentation at massive scales. The models and code are available at https://github.com/vuptran/cardiac-segmentation

Initial Technical Report; Include link to models and code

References in corpus (1)

• Deep Residual Learning for Image Recognition

Cited by in corpus (32)

• A Survey on Deep Learning in Medical Image Analysis
• A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
• Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation
• The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches
• A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis
• Adapting Mask-RCNN for Automatic Nucleus Segmentation
• Direct Multitype Cardiac Indices Estimation via Joint Representation and Regression Learning
• Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain Specific Features
• Estimation of the volume of the left ventricle from MRI images using deep neural networks
• Segmentation of histological images and fibrosis identification with a convolutional neural network
• Fully Convolutional Networks for Chip-wise Defect Detection Employing Photoluminescence Images
• Automatic segmentation method of pelvic floor levator hiatus in ultrasound using a self-normalising neural network
• SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation
• Left Ventricle Segmentation and Volume Estimation on Cardiac MRI using Deep Learning
• Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi-task deep learning approach
• ModelHub.AI: Dissemination Platform for Deep Learning Models
• Automatic Segmentation and Disease Classification Using Cardiac Cine MR Images
• PCA-aided Fully Convolutional Networks for Semantic Segmentation of Multi-channel fMRI
• A multi-level convolutional LSTM model for the segmentation of left ventricle myocardium in infarcted porcine cine MR images
• A Generative Adversarial Model for Right Ventricle Segmentation
• 3D Consistent & Robust Segmentation of Cardiac Images by Deep Learning with Spatial Propagation
• Automated cardiovascular magnetic resonance image analysis with fully convolutional networks
• Two Deep Learning Approaches for Automated Segmentation of Left Ventricle in Cine Cardiac MRI
• 3D Consistent Biventricular Myocardial Segmentation Using Deep Learning for Mesh Generation
• Improving Image co-segmentation via Deep Metric Learning
• FastVentricle: Cardiac Segmentation with ENet
• Deep learning for image segmentation: veritable or overhyped?
• Pixel-wise Segmentation of Right Ventricle of Heart
• Rethinking Fully Convolutional Networks for the Analysis of Photoluminescence Wafer Images
• L-CO-Net: Learned Condensation-Optimization Network for Clinical Parameter Estimation from Cardiac Cine MRI
• Deep Diagnostics: Applying Convolutional Neural Networks for Vessels Defects Detection
• Sparsely Activated Networks: A new method for decomposing and compressing data