Segmentation method of magnetic resonance imaging brain tumor images based on improved UNet network
Translational Cancer Research · 2024-03 · 13 (3) · 1567-1583
DOI: 10.21037/tcr-23-1858 ↗Kurz gefasst
Fachartikel in der Zeitschrift Translational Cancer Research, 2024-03. Verfasst von Yang Yang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurosurgery, Xiangyang Central Hospital (Hospital of Hubei University of Arts and Science), Xiangyang, China. Die Arbeit wurde bisher 15-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Glioma is a primary malignant craniocerebral tumor commonly found in the central nervous system. According to research, preoperative diagnosis of glioma and a full understanding of its imaging features are very significant. Still, the traditional segmentation methods of image dispensation and machine wisdom are not acceptable in glioma segmentation. This analysis explores the potential of magnetic resonance imaging (MRI) brain tumor images as an effective segmentation method of glioma.
Methods
This study used 200 MRI images from the affiliated hospital and applied the 2-dimensional residual block UNet (2DResUNet). Features were extracted from input images using a 2×2 kernel size (64-kernel) 1-step 2D convolution (Conv) layer. The 2DDenseUNet model implemented in this study incorporates a ResBlock mechanism within the UNet architecture, as well as a Gaussian noise layer for data augmentation at the input stage, and a pooling layer for replacing the conventional 2D convolutional layers. Finally, the performance of the proposed protocol and its effective measures in glioma segmentation were verified.
Results
The outcomes of the 5-fold cross-validation evaluation show that the proposed 2DResUNet and 2DDenseUNet structure has a high sensitivity despite the slightly lower evaluation result on the Dice score. At the same time, compared with other models used in the experiment, the DM-DA-UNet model proposed in this paper was significantly improved in various indicators, increasing the reliability of the model and providing a reference and basis for the accurate formulation of clinical treatment strategies. The method used in this study showed stronger feature extraction ability than the UNet model. In addition, our findings demonstrated that using generalized die harm and prejudiced cross entropy as loss functions in the training process effectively alleviated the class imbalance of glioma data and effectively segmented glioma.
Conclusions
The method based on the improved UNet network has obvious advantages in the MRI brain tumor portrait segmentation procedure. The result showed that we developed a 2D residual block UNet, which can improve the incorporation of glioma segmentation into the clinical process.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurosurgery, Xiangyang Central Hospital (Hospital of Hubei University of Arts and Science), Xiangyang, China.
- Imaging della Svizzera Italiana (IIMSI), Ente Ospedaliero Cantonale (EOC), Lugano, Switzerland.
- Faculty of Biomedical Sciences, Università della Svizzera italiana, Lugano, Switzerland.
Zitieren
APA
Yang, Y., Wang, P., Yang, Z., Zeng, Y., Chen, F., Wang, Z., & Rizzo, S. (2024). Segmentation method of magnetic resonance imaging brain tumor images based on improved UNet network. Translational Cancer Research, 13(3), 1567-1583. https://doi.org/10.21037/tcr-23-1858
Vancouver
Yang Y, Wang P, Yang Z, Zeng Y, Chen F, Wang Z, et al. Segmentation method of magnetic resonance imaging brain tumor images based on improved UNet network. Translational Cancer Research. 2024;13(3):1567-1583. doi:10.21037/tcr-23-1858
BibTeX
@article{Yang2024,
author = {Yang, Yang and Wang, Peng and Yang, Zhenyu and Zeng, Yuecheng and Chen, Feng and Wang, Zhiyong and Rizzo, Stefania},
title = {Segmentation method of magnetic resonance imaging brain tumor images based on improved UNet network},
journal = {Translational Cancer Research},
year = {2024},
volume = {13},
number = {3},
pages = {1567--1583},
doi = {10.21037/tcr-23-1858}
}
EUVIMED