Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation

Abstract

Active learning is a unique abstraction of machine learning techniques where the model/algorithm could guide users for annotation of a set of data points that would be beneficial to the model, unlike passive machine learning. The primary advantage being that active learning frameworks select data points that can accelerate the learning process of a model and can reduce the amount of data needed to achieve full accuracy as compared to a model trained on a randomly acquired data set. Multiple frameworks for active learning combined with deep learning have been proposed, and the majority of them are dedicated to classification tasks. Herein, we explore active learning for the task of segmentation of medical imaging data sets. We investigate our proposed framework using two datasets: 1.) MRI scans of the hippocampus, 2.) CT scans of pancreas and tumors. This work presents a query-by-committee approach for active learning where a joint optimizer is used for the committee. At the same time, we propose three new strategies for active learning: 1.) increasing frequency of uncertain data to bias the training data set; 2.) Using mutual information among the input images as a regularizer for acquisition to ensure diversity in the training dataset; 3.) adaptation of Dice log-likelihood for Stein variational gradient descent (SVGD). The results indicate an improvement in terms of data reduction by achieving full accuracy while only using 22.69 % and 48.85 % of the available data for each dataset, respectively.

arXiv comment19 pages, 13 figures, Transactions of Medical Imaging

References in corpus (15)

• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• On Calibration of Modern Neural Networks
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• 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
• Deep Bayesian Active Learning with Image Data
• Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
• Bayesian Model-Agnostic Meta-Learning
• On Warm-Starting Neural Network Training
• Learning how to Active Learn: A Deep Reinforcement Learning Approach
• Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation
• Active Learning for Segmentation by Optimizing Content Information for Maximal Entropy
• Large-Scale Visual Active Learning with Deep Probabilistic Ensembles

Cited by in corpus (6)

• MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images
• Exploring UMAP in hybrid models of entropy-based and representativeness sampling for active learning in biomedical segmentation
• A Comprehensive Study on Medical Image Segmentation using Deep Neural Networks
• Advances in Medical Image Segmentation: A Comprehensive Survey with a Focus on Lumbar Spine Applications
• Improve Cross-Modality Segmentation by Treating T1-Weighted MRI Images as Inverted CT Scans
• The Power of Proxy Data and Proxy Networks for Hyper-Parameter Optimization in Medical Image Segmentation