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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tan, H. S., Wang, Kuancheng, Mcbeth, Rafe
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914812355674112
author Tan, H. S.
Wang, Kuancheng
Mcbeth, Rafe
author_facet Tan, H. S.
Wang, Kuancheng
Mcbeth, Rafe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_10361
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Exploring UMAP in hybrid models of entropy-based and representativeness sampling for active learning in biomedical segmentation
Tan, H. S.
Wang, Kuancheng
Mcbeth, Rafe
Computer Vision and Pattern Recognition
Medical Physics
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.
title Exploring UMAP in hybrid models of entropy-based and representativeness sampling for active learning in biomedical segmentation
topic Computer Vision and Pattern Recognition
Medical Physics
url https://arxiv.org/abs/2312.10361