arXiv (Cornell University) · 2017 · 72 citations · 6 references
ComputingBiomedical EngineeringComputer ScienceComputer VisionDiagnostic ImagingMachine LearningActive LearningDeep LearningImage SegmentationMedical Image AnalysisMedical ImagingSemantic SegmentationActive Learning With Deep Neural NetworksConvolutional Neural Network SegmentationConvolutional Neural NetworksMonte Carlo Dropout
We propose a novel Active Learning framework capable to train effectively a convolutional neural network for semantic segmentation of medical imaging, with a limited amount of training labeled data. Our contribution is a practical Cost-Effective Active Learning approach using dropout at test time as Monte Carlo sampling to model the pixel-wise uncertainty and to analyze the image information to improve the training performance. The source code of this project is available at https://marc-gorriz.github.io/CEAL-Medical-Image-Segmentation/ .
6