Geodesic
Convolutional networks for segmentation of large vein images
Vestnik KRAUNC. Fiziko-matematičeskie nauki, Tome 31 (2020) no. 2, pp. 117-128 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

The article presents the results of work on image segmentation individual images of magnetic resonance imaging of the retroperitoneal space. The issues of detection and segmentation of objects the main veins of retroperitoneal space based on the convolutional architecture of a neural network for semantic pixel segmentation are considered. An automatic, accurate and reliable method using the convolutional neural network U-Net for extracting vein vessels from MRI images is proposed. Deep network training with a large receptive field U-Net allows you to achieve significant results even with the presence of low-quality source data, on small training samples. The data expansion strategy seems to be an effective way to reduce the degree of retraining in the recognition of medical images — veins
Mots-clés : convolutional architecture, image segmentation
Keywords: neural networks, medical data. 
@article{VKAM_2020_31_2_a7,
     author = {A. A. Egorov and S. A. Lysenkova and K. V. Mazayshvili},
     title = {Convolutional networks for segmentation of large vein images},
     journal = {Vestnik KRAUNC. Fiziko-matemati\v{c}eskie nauki},
     pages = {117--128},
     year = {2020},
     volume = {31},
     number = {2},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VKAM_2020_31_2_a7/}
}
TY  - JOUR
AU  - A. A. Egorov
AU  - S. A. Lysenkova
AU  - K. V. Mazayshvili
TI  - Convolutional networks for segmentation of large vein images
JO  - Vestnik KRAUNC. Fiziko-matematičeskie nauki
PY  - 2020
SP  - 117
EP  - 128
VL  - 31
IS  - 2
UR  - http://geodesic.mathdoc.fr/item/VKAM_2020_31_2_a7/
LA  - ru
ID  - VKAM_2020_31_2_a7
ER  - 
%0 Journal Article
%A A. A. Egorov
%A S. A. Lysenkova
%A K. V. Mazayshvili
%T Convolutional networks for segmentation of large vein images
%J Vestnik KRAUNC. Fiziko-matematičeskie nauki
%D 2020
%P 117-128
%V 31
%N 2
%U http://geodesic.mathdoc.fr/item/VKAM_2020_31_2_a7/
%G ru
%F VKAM_2020_31_2_a7
A. A. Egorov; S. A. Lysenkova; K. V. Mazayshvili. Convolutional networks for segmentation of large vein images. Vestnik KRAUNC. Fiziko-matematičeskie nauki, Tome 31 (2020) no. 2, pp. 117-128. http://geodesic.mathdoc.fr/item/VKAM_2020_31_2_a7/

[1] Mazayshvili K. V., Klimova N. V., Darvin V. V., Drozhzhin Ye. V., Shchebryakov V. V., Mamedov R. E., “Vozmozhnosti magnitno-rezonansnoy flebografii pri posttromboticheskoy patologii nizhney poloy veny i podvzdoshnykh ven”, Vestnik SurGU. Meditsina, 34:4 (2017), 11-16

[2] Krizhevsky A., Sutskever I., Hinton G.E., “Imagenet classification with deep convolutional neural networks”, NIPS, 2012, 1106-1114

[3] Chollet F., Deep learning with Python. Manning, 2018, 386 pp.

[4] Ronneberger O., Fischer P., Brox, T., “U-net: Convolutional networks for biomedical image segmentation”, MICCAI, 9351 (2015), 234-241

[5] Bertels J., Eelbode T., Berman M., Vandermeulen D., Maes F., Bisschops R., Blaschko M., Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory Practice, arXiv Preprint arXiv:1911.01685, 2019

[6] Ronneberger O., Fischer Ph., Brox Th, U-Net Convolutional Networks for Biomedical Image Segmentation, Preprint arXiv:1505.04597, 2015

[7] Ruder S., An overview of gradient descent optimization algorithms, Preprint arXiv:1609.04747, 2016

[8] Huanga O., Sun J., Ding H., Wangb X., Wanga G., “Robust liver vessel extraction using 3D U-Net with variant dice loss function”, Computersin Biologyand Medicine, 101:1 (2018), 153-162 | DOI