Uncertainty-Guided Efficient Interactive Refinement of Fetal Brain Segmentation from Stacks of MRI Slices

Abstract

Segmentation of the fetal brain from stacks of motion-corrupted fetal MRI slices is important for motion correction and high-resolution volume reconstruction. Although Convolutional Neural Networks (CNNs) have been widely used for automatic segmentation of the fetal brain, their results may still benefit from interactive refinement for challenging slices. To improve the efficiency of interactive refinement process, we propose an Uncertainty-Guided Interactive Refinement (UGIR) framework. We first propose a grouped convolution-based CNN to obtain multiple automatic segmentation predictions with uncertainty estimation in a single forward pass, then guide the user to provide interactions only in a subset of slices with the highest uncertainty. A novel interactive level set method is also proposed to obtain a refined result given the initial segmentation and user interactions. Experimental results show that: (1) our proposed CNN obtains uncertainty estimation in real time which correlates well with mis-segmentations, (2) the proposed interactive level set is effective and efficient for refinement, (3) UGIR obtains accurate refinement results with around 30% improvement of efficiency by using uncertainty to guide user interactions. Our code is available online.

10 pages, 4 figures, Accepted by MICCAI 2020

References in corpus (6)

• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation
• Real-Time Automatic Fetal Brain Extraction in Fetal MRI by Deep Learning

Cited by in corpus (7)

• MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning
• Efficient Semi-Supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistency
• Multimodal Interactive Lung Lesion Segmentation: A Framework for Annotating PET/CT Images based on Physiological and Anatomical Cues
• Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss
• Interactive Segmentation via Deep Learning and B-Spline Explicit Active Surfaces
• Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation
• Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models