Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Efficient Segmentation for Left Atrium With Convolution Neural Network Based on Active Learning in Late Gadolinium Enhancement Magnetic Resonance Imagingopen accessEfficient Segmentation for Left Atrium With Convolution Neural Network Based on Active Learning in Late Gadolinium Enhancement Magnetic Resonance Imaging

Other Titles
Efficient Segmentation for Left Atrium With Convolution Neural Network Based on Active Learning in Late Gadolinium Enhancement Magnetic Resonance Imaging
Authors
Cho, YongwonCho, HyungjoonShim, JaeminChoi, Jong-IlKim, Young-HoonKim, NamkugOh, Yu-WhanHwang, Sung Ho
Issue Date
19-9월-2022
Publisher
KOREAN ACAD MEDICAL SCIENCES
Keywords
Active Learning; Cardiac Image Analysis; Convolutional Neural Network; Deep Learning; Human-in-the-Loop; Magnetic Resonance Images
Citation
JOURNAL OF KOREAN MEDICAL SCIENCE, v.37, no.36, pp.1 - 12
Indexed
SCIE
SCOPUS
KCI
Journal Title
JOURNAL OF KOREAN MEDICAL SCIENCE
Volume
37
Number
36
Start Page
1
End Page
12
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/145744
DOI
10.3346/jkms.2022.37.e271
ISSN
1011-8934
Abstract
Background: To propose fully automatic segmentation of left atrium using active learning with limited dataset in late gadolinium enhancement in cardiac magnetic resonance imaging (LGE-CMRI).Methods: An active learning framework was developed to segment the left atrium in cardiac LGE-CMRI. Patients (n = 98) with atrial fibrillation from the Korea University Anam Hospital were enrolled. First, 20 cases were delineated for ground truths by two experts and used for training a draft model. Second, the 20 cases from the first step and 50 new cases, corrected in a human-in-the-loop manner after predicting using the draft model, were used to train the next model; all 98 cases (70 cases from the second step and 28 new cases) were trained. An additional 20 LGE-CMRI were evaluated in each step.Results: The Dice coefficients for the three steps were 0.85 +/- 0.06, 0.89 +/- 0.02, and 0.90 +/- 0.02, respectively. The biases (95% confidence interval) in the Bland-Altman plots of each step were 6.36% (-14.90-27.61), 6.21% (-9.62-22.03), and 2.68% (-8.57-13.93). Deep active learning-based annotation times were 218 +/- 31 seconds, 36.70 +/- 18 seconds, and 36.56 +/- 15 seconds, respectively.Conclusion: Deep active learning reduced annotation time and enabled efficient training on limited LGE-CMRI.
Files in This Item
There are no files associated with this item.
Appears in
Collections
Graduate School > Department of Biomedical Sciences > 1. Journal Articles
College of Medicine > Department of Medical Science > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Choi, Jong il photo

Choi, Jong il
의과학과
Read more

Altmetrics

Total Views & Downloads

BROWSE