Efficient Model Monitoring for Quality Control in Cardiac Image Segmentation (2021-04-12T00:00:00.000000Z)

TL;DR

This work presents a novel learning framework to monitor the performance of heart segmentation models in the absence of ground truth, formulated as an anomaly detection problem, that allows deriving surrogate quality measures for a segmentation and allows flagging suspicious results.

Abstract

Deep learning methods have reached state-of-the-art performance in cardiac image segmentation. Currently, the main bottleneck towards their effective translation into clinics requires assuring continuous high model performance and segmentation results. In this work, we present a novel learning framework to monitor the performance of heart segmentation models in the absence of ground truth. Formulated as an anomaly detection problem, the monitoring framework allows deriving surrogate quality measures for a segmentation and allows flagging suspicious results. We propose two different types of quality measures, a global score and a pixel-wise map. We demonstrate their use by reproducing the final rankings of a cardiac segmentation challenge in the absence of ground truth. Results show that our framework is accurate, fast, and scalable, confirming it is a viable option for quality control monitoring in clinical practice and large population studies.

Authors

Maria A. Zuluaga

3 papers

Francesco Galati

1 papers

Efficient Model Monitoring for Quality Control in Cardiac Image Segmentation

TL;DR

Abstract

Authors

References23 items

USAD: UnSupervised Anomaly Detection on Multivariate Time Series

Automated quantification of myocardial tissue characteristics from native T1 mapping using neural networks with uncertainty-based quality-control

Fully Automated, Quality-Controlled Cardiac Analysis From CMR: Validation and Large-Scale Application to Characterize Cardiac Function

Cardiac Segmentation With Strong Anatomical Guarantees

Cardiac Segmentation from LGE MRI Using Deep Neural Network Incorporating Shape and Spatial Priors

Automated quality control in image segmentation: application to the UK Biobank cardiovascular magnetic resonance imaging study

Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders

Real-time Prediction of Segmentation Quality

Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

Automated cardiovascular magnetic resonance image analysis with fully convolutional networks

Densely Connected Fully Convolutional Network for Short-Axis Cardiac Cine MR Image Segmentation and Heart Diagnosis Using Random Forest

Class-Balanced Deep Neural Network for Automatic Ventricular Structure Segmentation

An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation

Fast Fully-Automatic Cardiac Segmentation in MRI Using MRF Model Optimization, Substructures Tracking and B-Spline Smoothing

Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations

Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation

Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth

Hidden Technical Debt in Machine Learning Systems

Voxelwise atlas rating for computer assisted diagnosis: Application to congenital heart diseases of the great arteries

Multi-atlas Propagation Whole Heart Segmentation from MRI and CTA Using a Local Normalised Correlation Coefficient Criterion

Evaluating Segmentation Error without Ground Truth

Quality control.

Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges

Field of Study

Venue Information

Name

Type

URL

Alternate Names