Towards increased trustworthiness of deep learning segmentation methods on cardiac MRI

Current state-of-the-art deep learning segmentation methods have not yet made a broad entrance into the clinical setting in spite of high demand for such automatic methods. One important reason is the lack of reliability caused by models that fail unnoticed and often locally produce anatomically implausible results that medical experts would not make. This paper presents an automatic image segmentation method based on (Bayesian) dilated convolutional networks (DCNN) that generate segmentation masks and spatial uncertainty maps for the input image at hand. The method was trained and evaluated using segmentation of the left ventricle (LV) cavity, right ventricle (RV) endocardium and myocardium (Myo) at end-diastole (ED) and end-systole (ES) in 100 cardiac 2D MR scans from the MICCAI 2017 Challenge (ACDC). Combining segmentations and uncertainty maps and employing a human-in-the-loop setting, we provide evidence that image areas indicated as highly uncertain, regarding the obtained segmentation, almost entirely cover regions of incorrect segmentations. The fused information can be harnessed to increase segmentation performance. Our results reveal that we can obtain valuable spatial uncertainty maps with low computational effort using DCNNs.

[1]  Kilian Q. Weinberger,et al.  Snapshot Ensembles: Train 1, get M for free , 2017, ICLR.

[2]  Graham W. Taylor,et al.  Learning Confidence for Out-of-Distribution Detection in Neural Networks , 2018, ArXiv.

[3]  Max A. Viergever,et al.  Automatic Segmentation and Disease Classification Using Cardiac Cine MR Images , 2017, STACOM@MICCAI.

[4]  Charles Blundell,et al.  Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles , 2016, NIPS.

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Myunghee Cho Paik,et al.  Uncertainty quantification using Bayesian neural networks in classification: Application to ischemic stroke lesion segmentation , 2018 .

[7]  G. Brier.  VERIFICATION OF FORECASTS EXPRESSED IN TERMS OF PROBABILITY , 1950 .

[8]  Benjamin Woodward,et al.  Propagating Uncertainty in Multi-Stage Bayesian Convolutional Neural Networks with Application to Pulmonary Nodule Detection , 2017, ArXiv.

[9]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[10]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[11]  Xin Yang,et al.  Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? , 2018, IEEE Transactions on Medical Imaging.

[12]  Philipp Berens,et al.  Test-time Data Augmentation for Estimation of Heteroscedastic Aleatoric Uncertainty in Deep Neural Networks , 2018 .

[13]  Stephen E. Fienberg,et al.  The Comparison and Evaluation of Forecasters. , 1983 .

[14]  Siegfried Wahl,et al.  Leveraging uncertainty information from deep neural networks for disease detection , 2016, Scientific Reports.