PHiSeg: Capturing Uncertainty in Medical Image Segmentation

Baumgartner, Christian F.; Tezcan, Kerem Can; Chaitanya, Krishna; Hötker, Andreas M.; Muehlematter, Urs J.; Schawkat, Khoschy; Becker, Anton S.; Donati, Olivio F.; Konukoğlu, Ender

doi:10.1007/978-3-030-32245-8_14

Cited by 143 publications

(142 citation statements)

References 6 publications

(9 reference statements)

Supporting

Mentioning

138

Contrasting

Order By: Relevance

“…Third, we used a selection of commonly used uncertainty estimation methods. Hence, we cannot claim that these findings apply to other, recently proposed techniques (e.g., Baumgartner et al, 2019;Jena and Awate, 2019;Wang et al, 2019). Also, we analyzed the different uncertainty estimation methods independently of their expressed uncertainty (e.g., model uncertainty, data uncertainty).…”

Section: Discussionmentioning

confidence: 91%

Analyzing the Quality and Challenges of Uncertainty Estimations for Brain Tumor Segmentation

2020

View full text Add to dashboard Cite

Automatic segmentation of brain tumors has the potential to enable volumetric measures and high-throughput analysis in the clinical setting. Reaching this potential seems almost achieved, considering the steady increase in segmentation accuracy. However, despite segmentation accuracy, the current methods still do not meet the robustness levels required for patient-centered clinical use. In this regard, uncertainty estimates are a promising direction to improve the robustness of automated segmentation systems. Different uncertainty estimation methods have been proposed, but little is known about their usefulness and limitations for brain tumor segmentation. In this study, we present an analysis of the most commonly used uncertainty estimation methods in regards to benefits and challenges for brain tumor segmentation. We evaluated their quality in terms of calibration, segmentation error localization, and segmentation failure detection. Our results show that the uncertainty methods are typically well-calibrated when evaluated at the dataset level. Evaluated at the subject level, we found notable miscalibrations and limited segmentation error localization (e.g., for correcting segmentations), which hinder the direct use of the voxel-wise uncertainties. Nevertheless, voxel-wise uncertainty showed value to detect failed segmentations when uncertainty estimates are aggregated at the subject level. Therefore, we suggest a careful usage of voxel-wise uncertainty measures and highlight the importance of developing solutions that address the subject-level requirements on calibration and segmentation error localization.

show abstract

Section: Discussionmentioning

confidence: 91%

Analyzing the Quality and Challenges of Uncertainty Estimations for Brain Tumor Segmentation

2020

View full text Add to dashboard Cite

show abstract

“…In this work, we used a Probabilistic Hierarchical Segmentation (PHiSeg) network [1], a recently proposed deep learning network with Bayesian inference for segmentation of the LV blood pool, LV myocardium and RV blood pool from T 1 mapping images (Fig. 1).…”

Section: Deep Neural Network With Bayesian Inference For Segmentationmentioning

confidence: 99%

“…The PHiSeg network [1] models the probability distribution p(S|X) of plausible segmentations S for a given input image X at multiple scales from fine to coarse. Performing inference in this model using a conditional variational autoencoder approach results in a network architecture resembling the commonly used U-Net.…”

Section: Deep Neural Network With Bayesian Inference For Segmentationmentioning

confidence: 99%

“…This may be used to identify segmentations which are very unlikely given an input image. A detailed description of the method, as well as the network architecture can be found in [1].…”

Section: Deep Neural Network With Bayesian Inference For Segmentationmentioning

confidence: 99%

“…In this paper, we develop a tool for automated segmentation and analysis of T 1 maps. We use the Probabilistic Hierarchical Segmentation (PHiSeg) network [1] to segment the images, and additionally use the generated uncertainty information in a novel QC process to identify uncertain (and potentially inaccurate) segmentations. To the best of our knowledge this is the first time that segmentation uncertainty information has been used for QC in medical image segmentation.…”

Section: Background/introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Puyol‐Antón

Ruijsink

Baumgartner

et al. 2020

Journal of Cardiovascular Magnetic Resonance

Self Cite

View full text Add to dashboard Cite

Background: Tissue characterisation with cardiovascular magnetic resonance (CMR) parametric mapping has the potential to detect and quantify both focal and diffuse alterations in myocardial structure not assessable by late gadolinium enhancement. Native T 1 mapping in particular has shown promise as a useful biomarker to support diagnostic, therapeutic and prognostic decision-making in ischaemic and non-ischaemic cardiomyopathies. Methods: Convolutional neural networks (CNNs) with Bayesian inference are a category of artificial neural networks which model the uncertainty of the network output. This study presents an automated framework for tissue characterisation from native shortened modified Look-Locker inversion recovery ShMOLLI T 1 mapping at 1.5 T using a Probabilistic Hierarchical Segmentation (PHiSeg) network (PHCUMIS 119-127, 2019). In addition, we use the uncertainty information provided by the PHiSeg network in a novel automated quality control (QC) step to identify uncertain T 1 values. The PHiSeg network and QC were validated against manual analysis on a cohort of the UK Biobank containing healthy subjects and chronic cardiomyopathy patients (N=100 for the PHiSeg network and N=700 for the QC). We used the proposed method to obtain reference T 1 ranges for the left ventricular (LV) myocardium in healthy subjects as well as common clinical cardiac conditions. Results: T 1 values computed from automatic and manual segmentations were highly correlated (r=0.97). Bland-Altman analysis showed good agreement between the automated and manual measurements. The average Dice metric was 0.84 for the LV myocardium. The sensitivity of detection of erroneous outputs was 91%. Finally, T 1 values were automatically derived from 11,882 CMR exams from the UK Biobank. For the healthy cohort, the mean (SD) corrected T 1 values were 926.61 (45.26), 934.39 (43.25) and 927.56 (50.36) for global, interventricular septum and free-wall respectively.

show abstract

Prospective Deployment of Deep Learning in MRI: A Framework for Important Considerations, Challenges, and Recommendations for Best Practices

Chaudhari

Sandino

Cole

et al. 2020

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Artificial intelligence algorithms based on principles of deep learning (DL) have made a large impact on the acquisition, reconstruction, and interpretation of MRI data. Despite the large number of retrospective studies using DL, there are fewer applications of DL in the clinic on a routine basis. To address this large translational gap, we review the recent publications to determine three major use cases that DL can have in MRI, namely, that of model-free image synthesis, model-based image reconstruction, and image or pixel-level classification. For each of these three areas, we provide a framework for important considerations that consist of appropriate model training paradigms, evaluation of model robustness, downstream clinical utility, opportunities for future advances, as well recommendations for best current practices. We draw inspiration for this framework from advances in computer vision in natural imaging as well as additional healthcare fields. We further emphasize the need for reproducibility of research studies through the sharing of datasets and software. Level of Evidence: 5 Technical Efficacy Stage: 2

show abstract

PHiSeg: Capturing Uncertainty in Medical Image Segmentation

Cited by 143 publications

References 6 publications

Analyzing the Quality and Challenges of Uncertainty Estimations for Brain Tumor Segmentation

Analyzing the Quality and Challenges of Uncertainty Estimations for Brain Tumor Segmentation

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

Prospective Deployment of Deep Learning in MRI: A Framework for Important Considerations, Challenges, and Recommendations for Best Practices

Contact Info

Product

Resources

About