Modified U-Net Architecture for Ischemic Stroke Lesion Segmentation and Detection

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Citations (Scopus)

Abstract

In this paper, to improve the accuracy of detection and segmentation, we modify U-Net architecture to address ischemic stroke segmentation and detection, from ISLES 2018 dataset. In this dataset, CT images (in five modalities) and corresponding ground truth created by combining manual annotations are provided. We use shortcut connections in the architecture, which performs as a residual block. In the meantime, to reduce the overfitting caused by the scarcity of training data, we use elementwise-sum and concatenation in the network. We also use the dice coefficient and the Jaccard index to assess our model. Our architecture can be applied to ischemic segmentation and detection of CT images easily by choosing suitable hyperparameters. Experiment results show that our model can segment ischemic stroke accurately, with the dice coefficient between the segmentation given by our network and ground truth is about 0.77 while the dice coefficient of U-Net is about 0.74.

Original languageEnglish
Title of host publicationProceedings of 2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2019
EditorsBing Xu, Kefen Mou
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1068-1071
Number of pages4
ISBN (Electronic)9781728119076
DOIs
Publication statusPublished - Dec 2019
Event4th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2019 - Chengdu, China
Duration: 20 Dec 201922 Dec 2019

Publication series

NameProceedings of 2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2019

Conference

Conference4th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2019
Country/TerritoryChina
CityChengdu
Period20/12/1922/12/19

Keywords

  • Elementwise-sum
  • ISLES 2018
  • Res-Block
  • U-Net

Fingerprint

Dive into the research topics of 'Modified U-Net Architecture for Ischemic Stroke Lesion Segmentation and Detection'. Together they form a unique fingerprint.

Cite this