Standard

Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke. / Dobshik, A. V.; Tulupov, A. A.; Berikov, V. B.

In: Journal of Physics: Conference Series, Vol. 2099, No. 1, 012021, 13.12.2021.

Research output: Contribution to journal › Conference article › peer-review

Harvard

Dobshik, AV, Tulupov, AA & Berikov, VB 2021, 'Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke', Journal of Physics: Conference Series, vol. 2099, no. 1, 012021. https://doi.org/10.1088/1742-6596/2099/1/012021

APA

Dobshik, A. V., Tulupov, A. A., & Berikov, V. B. (2021). Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke. Journal of Physics: Conference Series, 2099(1), [012021]. https://doi.org/10.1088/1742-6596/2099/1/012021

Vancouver

Dobshik AV, Tulupov AA, Berikov VB. Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke. Journal of Physics: Conference Series. 2021 Dec 13;2099(1):012021. doi: 10.1088/1742-6596/2099/1/012021

Author

Dobshik, A. V. ; Tulupov, A. A. ; Berikov, V. B. / Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke. In: Journal of Physics: Conference Series. 2021 ; Vol. 2099, No. 1.

BibTeX

@article{bb2aa8caa6164ee489d75efd5cc4151e,
title = "Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke",
abstract = "This paper presents an automatic algorithm for the segmentation of areas affected by an acute stroke in the non-contrast computed tomography brain images. The proposed algorithm is designed for learning in a weakly supervised scenario when some images are labeled accurately, and some images are labeled inaccurately. Wrong labels appear as a result of inaccuracy made by a radiologist in the process of manual annotation of computed tomography images. We propose methods for solving the segmentation problem in the case of inaccurately labeled training data. We use the U-Net neural network architecture with several modifications. Experiments on real computed tomography scans show that the proposed methods increase the segmentation accuracy.",
author = "Dobshik, {A. V.} and Tulupov, {A. A.} and Berikov, {V. B.}",
note = "Funding Information: The work was partly supported by RFBR grant 19-29-01175. Publisher Copyright: {\textcopyright} 2021 Institute of Physics Publishing. All rights reserved.; International Conference on Marchuk Scientific Readings 2021, MSR 2021 ; Conference date: 04-10-2021 Through 08-10-2021",
year = "2021",
month = dec,
day = "13",
doi = "10.1088/1742-6596/2099/1/012021",
language = "English",
volume = "2099",
journal = "Journal of Physics: Conference Series",
issn = "1742-6588",
publisher = "IOP Publishing Ltd.",
number = "1",

}

RIS

TY - JOUR

T1 - Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke

AU - Dobshik, A. V.

AU - Tulupov, A. A.

AU - Berikov, V. B.

N1 - Funding Information: The work was partly supported by RFBR grant 19-29-01175. Publisher Copyright: © 2021 Institute of Physics Publishing. All rights reserved.

PY - 2021/12/13

Y1 - 2021/12/13

N2 - This paper presents an automatic algorithm for the segmentation of areas affected by an acute stroke in the non-contrast computed tomography brain images. The proposed algorithm is designed for learning in a weakly supervised scenario when some images are labeled accurately, and some images are labeled inaccurately. Wrong labels appear as a result of inaccuracy made by a radiologist in the process of manual annotation of computed tomography images. We propose methods for solving the segmentation problem in the case of inaccurately labeled training data. We use the U-Net neural network architecture with several modifications. Experiments on real computed tomography scans show that the proposed methods increase the segmentation accuracy.

AB - This paper presents an automatic algorithm for the segmentation of areas affected by an acute stroke in the non-contrast computed tomography brain images. The proposed algorithm is designed for learning in a weakly supervised scenario when some images are labeled accurately, and some images are labeled inaccurately. Wrong labels appear as a result of inaccuracy made by a radiologist in the process of manual annotation of computed tomography images. We propose methods for solving the segmentation problem in the case of inaccurately labeled training data. We use the U-Net neural network architecture with several modifications. Experiments on real computed tomography scans show that the proposed methods increase the segmentation accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85123727143&partnerID=8YFLogxK

U2 - 10.1088/1742-6596/2099/1/012021

DO - 10.1088/1742-6596/2099/1/012021

M3 - Conference article

AN - SCOPUS:85123727143

VL - 2099

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

SN - 1742-6588

IS - 1

M1 - 012021

T2 - International Conference on Marchuk Scientific Readings 2021, MSR 2021

Y2 - 4 October 2021 through 8 October 2021

ER -

ID: 35377098