Please use this identifier to cite or link to this item: http://elar.urfu.ru/handle/10995/101568
Title: Comparison of UNet, ENet, and BoxENet for Segmentation of Mast Cells in Scans of Histological Slices
Authors: Karimov, A.
Razumov, A.
Manbatchurina, R.
Simonova, K.
Donets, I.
Vlasova, A.
Khramtsova, Y.
Ushenin, K.
Issue Date: 2019
Publisher: Institute of Electrical and Electronics Engineers Inc.
Citation: Comparison of UNet, ENet, and BoxENet for Segmentation of Mast Cells in Scans of Histological Slices / A. Karimov, A. Razumov, R. Manbatchurina, et al. — DOI 10.1109/SIBIRCON48586.2019.8958121 // SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings. — 2019. — P. 544-547. — 8958121.
Abstract: Deep neural networks show high accuracy in the problem of semantic and instance segmentation of biomedical data. However, this approach is computationally expensive. The computational cost may be reduced with network simplification after training or choosing the proper architecture, which provides segmentation with less accuracy but does it much faster. In the present study, we analyzed the accuracy and performance of UNet and ENet architectures for the problem of semantic image segmentation. In addition, we investigated the ENet architecture by replacing of some convolution layers with box-convolution layers. The analysis performed on the original dataset consisted of histology slices with mast cells. These cells provide a region for segmentation with different types of borders, which vary from clearly visible to ragged. ENet was less accurate than UNet by only about 1-2%, but ENet performance was 8-15 times faster than UNet one. © 2019 IEEE.
Keywords: BIOMEDICAL SEGMENTATION
BOX CONVOLUTION LAYER
ENET
MAST CELLS
NEURAL NETWORK PERFORMANCE
SEMANTIC SEGMENTATION
UNET
CELLS
CONVOLUTION
CYTOLOGY
DEEP NEURAL NETWORKS
MULTILAYER NEURAL NETWORKS
NETWORK ARCHITECTURE
NEURAL NETWORKS
SEMANTICS
BOX CONVOLUTION LAYER
ENET
MAST CELLS
SEMANTIC SEGMENTATION
UNET
IMAGE SEGMENTATION
URI: http://elar.urfu.ru/handle/10995/101568
Access: info:eu-repo/semantics/openAccess
SCOPUS ID: 85079079261
PURE ID: 12233303
cd421f0d-d0f0-4add-b256-ce80791fe589
ISBN: 9781728144016
DOI: 10.1109/SIBIRCON48586.2019.8958121
Appears in Collections:Научные публикации, проиндексированные в SCOPUS и WoS CC

Files in This Item:
File Description SizeFormat 
2-s2.0-85079079261.pdf445,44 kBAdobe PDFView/Open


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