Research on ventricular segmentation based on deep learning

DOI

10.2991/978-94-6463-300-9_7How to use a DOI?

Keywords

UNet; deep learning; ventricular segmentation; magnetic resonance images

Abstract

Pattern recognition algorithms have achieved great success in medical image analysis, especially in terms of lesion area segmentation in magnetic resonance images. Different from the labor-intensive manual segmentation and diagnosis, image segmentation technology based on deep learning has made breakthroughs in the accuracy and speed of lesion area recognition in recent years. Focusing on the task of left ventricle segmentation from magnetic resonance images, this paper utilizes the powerful feature representation ability of the convolutional neural network to complete accurate and automatic left ventricle segmentation. For example, the left ventricle is segmented from the heart image based on MRI(Magnetic Resonance Imaging) through UNet, which is based on Convolutional neural network Meanwhile, the evaluation indicators and the process of data set preprocessing are explained. On this basis, the influence of changing the parameters of basic UNet is further studied, and the experimental analysis is carried out from three aspects: changing the batch size, changing the number of initial extracted features and changing the number of network layers. Finally, Dice coefficients of 0.9331, 0.9316 and 0.8416 were obtained on the test set, verification set and training set respectively, and good style results were obtained. At last, the further improvement was explained.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Xuefeng Peng
PY  - 2023
DA  - 2023/11/27
TI  - Research on ventricular segmentation based on deep learning
BT  - Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)
PB  - Atlantis Press
SP  - 57
EP  - 72
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-300-9_7
DO  - 10.2991/978-94-6463-300-9_7
ID  - Peng2023
ER  -