Header

UZH-Logo

Maintenance Infos

Active learning for segmentation based on Bayesian sample queries


Ozdemir, Firat; Peng, Z; Fürnstahl, P; Tanner, C; Goksel, O (2021). Active learning for segmentation based on Bayesian sample queries. Knowledge-Based Systems, 214:106531.

Abstract

Segmentation of anatomical structures is a fundamental image analysis task for many applications in the medical field. Deep learning methods have been shown to perform well, but for this purpose large numbers of manual annotations are needed in the first place, which necessitate prohibitive levels of resources that are often unavailable. In an active learning framework of selecting informed samples for manual labeling, expert clinician time for manual annotation can be optimally utilized, enabling the establishment of large labeled datasets for machine learning. In this paper, we propose a novel method that combines representativeness with uncertainty in order to estimate ideal samples to be annotated, iteratively from a given dataset. Our novel representativeness metric is based on Bayesian sampling, by using information-maximizing autoencoders. We conduct experiments on a shoulder magnetic resonance imaging (MRI) dataset for the segmentation of four musculoskeletal tissue classes. Quantitative results show that the annotation of representative samples selected by our proposed querying method yields an improved segmentation performance at each active learning iteration, compared to a baseline method that also employs uncertainty and representativeness metrics. For instance, with only 10% of the dataset annotated, our method reaches within 5% of Dice score expected from the upper bound scenario of all the dataset given as annotated (an impractical scenario due to resource constraints), and this gap drops down to a mere 2% when less than a fifth of the dataset samples are annotated. Such active learning approach to selecting samples to annotate enables an optimal use of the expert clinician time, being often the bottleneck in realizing machine learning solutions in medicine.

Abstract

Segmentation of anatomical structures is a fundamental image analysis task for many applications in the medical field. Deep learning methods have been shown to perform well, but for this purpose large numbers of manual annotations are needed in the first place, which necessitate prohibitive levels of resources that are often unavailable. In an active learning framework of selecting informed samples for manual labeling, expert clinician time for manual annotation can be optimally utilized, enabling the establishment of large labeled datasets for machine learning. In this paper, we propose a novel method that combines representativeness with uncertainty in order to estimate ideal samples to be annotated, iteratively from a given dataset. Our novel representativeness metric is based on Bayesian sampling, by using information-maximizing autoencoders. We conduct experiments on a shoulder magnetic resonance imaging (MRI) dataset for the segmentation of four musculoskeletal tissue classes. Quantitative results show that the annotation of representative samples selected by our proposed querying method yields an improved segmentation performance at each active learning iteration, compared to a baseline method that also employs uncertainty and representativeness metrics. For instance, with only 10% of the dataset annotated, our method reaches within 5% of Dice score expected from the upper bound scenario of all the dataset given as annotated (an impractical scenario due to resource constraints), and this gap drops down to a mere 2% when less than a fifth of the dataset samples are annotated. Such active learning approach to selecting samples to annotate enables an optimal use of the expert clinician time, being often the bottleneck in realizing machine learning solutions in medicine.

Statistics

Citations

Dimensions.ai Metrics
8 citations in Web of Science®
10 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

2 downloads since deposited on 09 Mar 2021
0 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > Balgrist University Hospital, Swiss Spinal Cord Injury Center
Dewey Decimal Classification:610 Medicine & health
Scopus Subject Areas:Social Sciences & Humanities > Management Information Systems
Physical Sciences > Software
Social Sciences & Humanities > Information Systems and Management
Physical Sciences > Artificial Intelligence
Language:English
Date:26 November 2021
Deposited On:09 Mar 2021 14:03
Last Modified:25 May 2024 01:49
Publisher:Elsevier
ISSN:0950-7051
OA Status:Closed
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.1016/j.knosys.2020.106531