Automatic quality control framework for more reliable integration of machine learning-based image segmentation into medical workflows
Not on the map. Why?
Abstract (arXiv)
Machine learning algorithms underpin modern diagnostic-aiding software, which has proved valuable in clinical practice, particularly in radiology. However, inaccuracies, mainly due to the limited availability of clinical samples for training these algorithms, hamper their wider applicability, acceptance, and recognition amongst clinicians. We present an analysis of state-of-the-art automatic quality control (QC) approaches that can be implemented within these algorithms to estimate the certainty of their outputs. We validated the most promising approaches on a brain image segmentation task identifying white matter hyperintensities (WMH) in magnetic resonance imaging data. WMH are a correlate of small vessel disease common in mid-to-late adulthood and are particularly challenging to segment due to their varied size, and distributional patterns. Our results show that the aggregation of uncertainty and Dice prediction were most effective in failure detection for this task. Both methods independently improved mean Dice from 0.82 to 0.84. Our work reveals how QC methods can help to detect failed segmentation cases and therefore make automatic segmentation more reliable and suitable for clinical practice.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 6 Dec 2021.
Builds on
24 of 37 references.
References · 24
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
- 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 281
- 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 278
- 2018Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentationcited by 146
- 2019Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challengecited by 115
- 2017CNN-based Segmentation of Medical Imaging Datacited by 48
- 2018Leveraging Uncertainty Estimates for Predicting Segmentation Qualitycited by 44
- 2019Supervised Uncertainty Quantification for Segmentation with Multiple Annotationscited by 42
- 2018Bayesian QuickNAT: Model Uncertainty in Deep Whole-Brain Segmentation for Structure-wise Quality Controlcited by 39
- 2020Uncertainty Estimation Using a Single Deep Deterministic Neural Networkcited by 37
- 2017Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truthcited by 35
12 more
- 2018Towards safe deep learning: accurately quantifying biomarker uncertainty in neural network predictionscited by 25
- 2018Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR Imagescited by 16
- 2018Towards increased trustworthiness of deep learning segmentation methods on cardiac MRIcited by 16
- 2021Challenges for machine learning in clinical translation of big data imaging studiescited by 15
- 2018Uncertainty-driven Sanity Check: Application to Postoperative Brain Tumor Cavity Segmentationcited by 11
- 2019An Alarm System For Segmentation Algorithm Based On Shape Modelcited by 8
- 2018Accuracy, Uncertainty, and Adaptability of Automatic Myocardial ASL Segmentation using Deep CNNcited by 3
- 2019Prostate Segmentation from 3D MRI Using a Two-Stage Model and Variable-Input Based Uncertainty Measurecited by 3
- 2019A Fine-Grain Error Map Prediction and Segmentation Quality Assessment Framework for Whole-Heart Segmentationcited by 3
- 2020A deep learning-based pipeline for error detection and quality control of brain MRI segmentation resultscited by 2
- 2020Collaborative Boundary-aware Context Encoding Networks for Error Map Predictioncited by 2
- 2019Robust Image Segmentation Quality Assessmentcited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.