General Information
    • ISSN: 1793-8201 (Print), 2972-4511 (Online)
    • Abbreviated Title: Int. J. Comput. Theory Eng.
    • Frequency: Quarterly
    • DOI: 10.7763/IJCTE
    • Editor-in-Chief: Prof. Mehmet Sahinoglu
    • Associate Editor-in-Chief: Assoc. Prof. Alberto Arteta, Assoc. Prof. Engin Maşazade
    • Managing Editor: Ms. Mia Hu
    • Abstracting/Indexing: Scopus (Since 2022), INSPEC (IET), CNKI,  Google Scholar, EBSCO, etc.
    • Average Days from Submission to Acceptance: 192 days
    • APC: 800 USD
    • E-mail: ijcte@iacsitp.com
    • Journal Metrics:
    • SCImago Journal & Country Rank
Editor-in-chief
Prof. Mehmet Sahinoglu
Computer Science Department, Troy University, USA
I'm happy to take on the position of editor in chief of IJCTE. We encourage authors to submit papers concerning any branch of computer theory and engineering.

IJCTE 2022 Vol.14(3): 104-108 ISSN: 1793-8201
DOI: 10.7763/IJCTE.2022.V14.1317

Deep Learning-Based Fetal Corpus Callosum Segmentation in Ultrasonic Images

Wen Zheng, Murong Yi, Guiqun Cao, Zhuyu Zhou, and Jian Cheng*

Abstract—The corpus callosum is the largest commissural fiber in the cerebral hemisphere that lies at the bottom of the cerebral longitudinal fissure. The Agenesis of Corpus Callosum (ACC) is a congenital disease in the fetal central nervous system malformation, which means the partial or total loss of the corpus callosum during the formation and is detrimental to future development. Its symptom detection mainly depends on the ultrasonic diagnosis, but this method is highly dependent on the experience of doctors because different locations of the fetus and the resolution of the images bring difficulties to the detection of complete callosum. To solve this problem, this paper presents a fusing attention mechanism based on the deep learning method which takes in the advantages of Transformers and dual attention mechanism and realizes accurate semantic segmentation of fetal corpus callosum in ultrasonic images. This method successfully reached an Intersection over Union (IoU) of 59.4%. Besides, this paper also presents the comparison between the performances of different backbone networks and loss functions in order to provide a reference for the application of different parameters according to actual circumstances. Our work provides a reliable reference to locate corpus callosum, thus is promising for the improvement in the diagnosis of ACC and the reduction of the burden of medical workers.

Index Terms—Deep learning, fetal corpus callosum, semantic segmentation, ultrasonic images.

Wen Zheng and Murong Yi are with the University of Electronic Science and Technology of China, Chengdu, Sichuan, China (e-mail: zwence@163.com, yibayy9@gmail.com). Guiqun Cao is with Clinical Translational Innovation Center and Molecular Medicine Research Center, West China Hospital of Sichuan University, Chengdu, Sichuan, China (email: caoguiqun@126.com). Zhuyu Zhou is with Deyang People's Hospital, Deyang, Sichuan, China (e-mail: zhoujin1975@163.com). *Jian Cheng is the corresponding author and is with the University of Electronic Science and Technology of China, Chengdu, Sichuan, China (e-mail: chengjian@uestc.edu.cn).

[PDF]

Cite:Wen Zheng, Murong Yi, Guiqun Cao, Zhuyu Zhou, and Jian Cheng, "Deep Learning-Based Fetal Corpus Callosum Segmentation in Ultrasonic Images," International Journal of Computer Theory and Engineering vol. 14, no. 3, pp. 104-108, 2022.

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).


Copyright © 2008-2024. International Association of Computer Science and Information Technology. All rights reserved.