Sciact
  • EN
  • RU

Mask Correction in 3-D Tomography Brain Images for Weakly Supervised Segmentation of Acute Ischemic Stroke Full article

Conference International Russian Smart Industry Conference 2024
25-29 Mar 2024 , Сочи
Source 2024 International Russian Smart Industry Conference (SmartIndustryCon), Sochi, Russian Federation, 2024
Compilation, IEEE. 2024. 1015 c. ISBN 979-8-3503-9504-4.
Output data Year: 2024, Pages: 796-801 Pages count : 6 DOI: 10.1109/smartindustrycon61328.2024.10515449
Tags 3D image segmentation, convolutional neural networks, inexact labeling, ischemic stroke, weak supervision
Authors Mikhailapov Denis 1 , Tulupov Andrey 2 , Berikov Vladimir 1
Affiliations
1 Sobolev Institute of Mathematics SB RAS,Data Analysis Laboratory,Novosibirsk,Russia
2 International Tomography Center SB RAS,MRT Technology Laboratory,Novosibirsk,Russia

Funding (1)

1 Russian Science Foundation 24-21-00195

Abstract: In this paper we propose a method for weakly supervised segmentation of 3-D computed tomography brain images of acute ischemic stroke using convolutional neural nets. To improve the segmentation quality of stroke areas, the concepts of a distance map and weight map are introduced. The maps are utilized to correct the predictions of the model at the boundaries of the affected areas. Additionally, a smoothing method is introduced for segmentation masks to reduce labeling defects. The study uses two sets of data: the primary set that includes labeling made by a single radiologist, and the auxiliary set of smaller size with several variants of labeling made by different radiologists. The latter set is analyzed to reveal the basic characteristics of labeling discrepancies which arise due to complex nature of analyzed images. The 3D U-Net model is employed for the primary set segmentation. DICE loss and Focal loss are used to train the model, and DICE score is utilized to evaluate the quality of forecasts. The results of experiments demonstrate the effectiveness of the proposed method.
Cite: Mikhailapov D. , Tulupov A. , Berikov V.
Mask Correction in 3-D Tomography Brain Images for Weakly Supervised Segmentation of Acute Ischemic Stroke
In compilation 2024 International Russian Smart Industry Conference (SmartIndustryCon), Sochi, Russian Federation, 2024. – IEEE., 2024. – C.796-801. – ISBN 979-8-3503-9504-4. DOI: 10.1109/smartindustrycon61328.2024.10515449 Scopus OpenAlex
Dates:
Published print: May 8, 2024
Published online: May 8, 2024
Identifiers:
Scopus: 2-s2.0-85193300409
OpenAlex: W4396731520
Citing: Пока нет цитирований
Altmetrics: