Exploring UMAP in hybrid models of entropy-based and representativeness sampling for active learning in biomedical segmentation

Abstract

In this work, we study various hybrid models of entropy-based and representativeness sampling techniques in the context of active learning in medical segmentation, in particular examining the role of UMAP (Uniform Manifold Approximation and Projection) as a technique for capturing representativeness. Although UMAP has been shown viable as a general purpose dimension reduction method in diverse areas, its role in deep learning-based medical segmentation has yet been extensively explored. Using the cardiac and prostate datasets in the Medical Segmentation Decathlon for validation, we found that a novel hybrid combination of Entropy-UMAP sampling technique achieved a statistically significant Dice score advantage over the random baseline ($3.2\%$ for cardiac, $4.5\%$ for prostate), and attained the highest Dice coefficient among the spectrum of 10 distinct active learning methodologies we examined. This provides preliminary evidence that there is an interesting synergy between entropy-based and UMAP methods when the former precedes the latter in a hybrid model of active learning.

25 pages, 6 figures

References in corpus (8)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• Three scenarios for continual learning
• Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation
• Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation
• Parting with Illusions about Deep Active Learning
• Less Is More: A Comparison of Active Learning Strategies for 3D Medical Image Segmentation
• Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization