mlsanityData to 7 Oct 2026

Temporal Uncertainty Localization to Enable Human-in-the-loop Analysis of Dynamic Contrast-enhanced Cardiac MRI Datasets

arXiv 2308.13488 ↗First posted 25 Aug 2023eess.IV cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Dynamic contrast-enhanced (DCE) cardiac magnetic resonance imaging (CMRI) is a widely used modality for diagnosing myocardial blood flow (perfusion) abnormalities. During a typical free-breathing DCE-CMRI scan, close to 300 time-resolved images of myocardial perfusion are acquired at various contrast "wash in/out" phases. Manual segmentation of myocardial contours in each time-frame of a DCE image series can be tedious and time-consuming, particularly when non-rigid motion correction has failed or is unavailable. While deep neural networks (DNNs) have shown promise for analyzing DCE-CMRI datasets, a "dynamic quality control" (dQC) technique for reliably detecting failed segmentations is lacking. Here we propose a new space-time uncertainty metric as a dQC tool for DNN-based segmentation of free-breathing DCE-CMRI datasets by validating the proposed metric on an external dataset and establishing a human-in-the-loop framework to improve the segmentation results. In the proposed approach, we referred the top 10% most uncertain segmentations as detected by our dQC tool to the human expert for refinement. This approach resulted in a significant increase in the Dice score (p<0.001) and a notable decrease in the number of images with failed segmentation (16.2% to 11.3%) whereas the alternative approach of randomly selecting the same number of segmentations for human referral did not achieve any significant improvement. Our results suggest that the proposed dQC framework has the potential to accurately identify poor-quality segmentations and may enable efficient DNN-based analysis of DCE-CMRI in a human-in-the-loop pipeline for clinical interpretation and reporting of dynamic CMRI datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 30 references that are in the map. First posted on arXiv 25 Aug 2023.

Builds on

15 of 30 references.

References · 15

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  3. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
  4. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 278
  5. 2020Consistent Estimators for Learning to Defer to an Expertcited by 262
  6. 2019Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentationcited by 162
  7. 2015Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classificationcited by 159
  8. 2019A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysiscited by 150
  9. 2018Leveraging Uncertainty Estimates for Predicting Segmentation Qualitycited by 44
  10. 2018Bayesian QuickNAT: Model Uncertainty in Deep Whole-Brain Segmentation for Structure-wise Quality Controlcited by 39
  11. 2019Improving the generalizability of convolutional neural network-based segmentation on CMR imagescited by 25
  12. 2020Estimating Uncertainty in Neural Networks for Cardiac MRI Segmentation: A Benchmark Studycited by 19
3 more
  1. 2020Automatic segmentation with detection of local segmentation failures in cardiac MRIcited by 10
  2. 2020Automated quantification of myocardial tissue characteristics from native T1 mapping using neural networks with Bayesian inference for uncertainty-based quality-controlcited by 6
  3. 2019Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learningcited by 1

Built on by

Not cited yet.