Learning under Distributed Weak Supervision

Abstract

The availability of training data for supervision is a frequently encountered bottleneck of medical image analysis methods. While typically established by a clinical expert rater, the increase in acquired imaging data renders traditional pixel-wise segmentations less feasible. In this paper, we examine the use of a crowdsourcing platform for the distribution of super-pixel weak annotation tasks and collect such annotations from a crowd of non-expert raters. The crowd annotations are subsequently used for training a fully convolutional neural network to address the problem of fetal brain segmentation in T2-weighted MR images. Using this approach we report encouraging results compared to highly targeted, fully supervised methods and potentially address a frequent problem impeding image analysis research.

References in corpus (4)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks

Cited by in corpus (10)

• A Survey on Deep Learning in Medical Image Analysis
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis
• Constrained-CNN losses for weakly supervised segmentation
• A Survey on Deep Learning for Skin Lesion Segmentation
• Artificial Intelligence in Glioma Imaging: Challenges and Advances
• Employing Weak Annotations for Medical Image Analysis Problems
• 3D Reconstruction in Canonical Co-ordinate Space from Arbitrarily Oriented 2D Images
• Color Recognition for Rubik's Cube Robot
• Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach