Sciact
  • EN
  • RU

Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke Научная публикация

Конференция International Conference «Marchuk Scientific Readings
04-08 окт. 2021 , Новосибирск
Журнал Journal of Physics: Conference Series
ISSN: 1742-6588 , E-ISSN: 1742-6596
Вых. Данные Год: 2021, Том: 2099, Номер: 1, Номер статьи : 012021, Страниц : DOI: 10.1088/1742-6596/2099/1/012021
Авторы Dobshik A.V. 1 , Tulupov A.A. 1,2 , Berikov V.B. 1,3
Организации
1 Novosibirsk State University, Pirogova str. 1, Novosibirsk, 630090, Russian Federation
2 International Tomography Center Sb Ras, Institutskaya str. 3a, Novosibirsk, 630090, Russian Federation
3 Sobolev Institute of Mathematics Sb Ras, Ac. Koptuga ave. 4, Novosibirsk, 630090, Russian Federation

Информация о финансировании (1)

1 Российский фонд фундаментальных исследований 19-29-01175

Реферат: 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. © 2021 Institute of Physics Publishing. All rights reserved.
Библиографическая ссылка: Dobshik A.V. , Tulupov A.A. , Berikov V.B.
Weakly supervised semantic segmentation of tomographic images in the diagnosis of stroke
Journal of Physics: Conference Series. 2021. V.2099. N1. 012021 . DOI: 10.1088/1742-6596/2099/1/012021 Scopus OpenAlex
Идентификаторы БД:
Scopus: 2-s2.0-85123727143
OpenAlex: W3197468198
Цитирование в БД:
БД Цитирований
Scopus 1
OpenAlex 1
Альметрики: