Automatic segmentation with detection of local segmentation failures in cardiac MRI

by   Jörg Sander, et al.

Segmentation of cardiac anatomical structures in cardiac magnetic resonance images (CMRI) is a prerequisite for automatic diagnosis and prognosis of cardiovascular diseases. To increase robustness and performance of segmentation methods this study combines automatic segmentation and assessment of segmentation uncertainty in CMRI to detect image regions containing local segmentation failures. Three state-of-the-art convolutional neural networks (CNN) were trained to automatically segment cardiac anatomical structures and obtain two measures of predictive uncertainty: entropy and a measure derived by MC-dropout. Thereafter, using the uncertainties another CNN was trained to detect local segmentation failures that potentially need correction by an expert. Finally, manual correction of the detected regions was simulated. Using publicly available CMR scans from the MICCAI 2017 ACDC challenge, the impact of CNN architecture and loss function for segmentation, and the uncertainty measure was investigated. Performance was evaluated using the Dice coefficient and 3D Hausdorff distance between manual and automatic segmentation. The experiments reveal that combining automatic segmentation with simulated manual correction of detected segmentation failures leads to statistically significant performance increase.


page 1

page 4

page 12

page 13


2D-3D Fully Convolutional Neural Networks for Cardiac MR Segmentation

In this paper, we develop a 2D and 3D segmentation pipelines for fully a...

Towards increased trustworthiness of deep learning segmentation methods on cardiac MRI

Current state-of-the-art deep learning segmentation methods have not yet...

Accuracy, Uncertainty, and Adaptability of Automatic Myocardial ASL Segmentation using Deep CNN

PURPOSE: To apply deep convolutional neural networks (CNN) to the left v...

Learning correspondences of cardiac motion from images using biomechanics-informed modeling

Learning spatial-temporal correspondences in cardiac motion from images ...

Pixel-wise Segmentation of Right Ventricle of Heart

One of the first steps in the diagnosis of most cardiac diseases, such a...

Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNets

Automatic and accurate whole-heart and great vessel segmentation from 3D...

Please sign up or login with your details

Forgot password? Click here to reset