EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Brain tumor segmentation based on the U-NET+⁣+ network with efficientnet encoder

Yunyi Chen, Lan Quan, Chao Long, Yuxuan Chen, Li Zu, Chenxi Huang

Technology and Health Care · 31.05.2024 · 32 · 183-195

DOI: 10.3233/thc-248016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technology and Health Care, erschienen am 31.05.2024. Verfasst von Yunyi Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Key Open Project of Key Laboratory of Data Science and Intelligence Education, Hainan Normal University, Haikou, Hainan, China. Hauptthemen laut MEDLINE: Brain Neoplasms, Magnetic Resonance Imaging, Neural Networks, Computer. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 8 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Brain tumor is a highly destructive, aggressive, and fatal disease. The presence of brain tumors can disrupt the brain’s ability to control body movements, consciousness, sensations, thoughts, speech, and memory. Brain tumors are often accompanied by symptoms like epilepsy, headaches, and sensory loss, leading to varying degrees of cognitive impairment in affected patients. OBJECTIVE: The study goal is to develop an effective method to detect and segment brain tumor with high accurancy. METHODS: This paper proposes a novel U-Net+⁣+ network using EfficientNet as the encoder to segment brain tumors based on MRI images. We adjust the original U-Net+⁣+ model by removing the dense skip connections between sub-networks to simplify computational complexity and improve model efficiency, while the connections of feature maps at the same resolution level are retained to bridge the semantic gap. RESULTS: The proposed segmentation model is trained and tested on Kaggle’s LGG brain tumor dataset, which obtains a satisfying performance with a Dice coefficient of 0.9180. CONCLUSION: This paper conducts research on brain tumor segmentation, using the U-Net+⁣+ network with EfficientNet as an encoder to segment brain tumors based on MRI images. We adjust the original U-Net+⁣+ model to simplify calculations and maintains rich semantic spatial features at the same time. Multiple loss functions are compared in this study and their effectiveness are discussed. The experimental results shows the model achieves a high segmention result with Dice coefficient of 0.9180.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Brain NeoplasmsMagnetic Resonance ImagingNeural Networks, ComputerHumansAlgorithms

Stichwörter der Autor:innen

Brain tumor segmentationEfficientNet encoderU-Net+⁣+ framework

Autor:innen und Institutionen

  • Key Open Project of Key Laboratory of Data Science and Intelligence Education, Hainan Normal University, Haikou, Hainan, China.
  • Department of Software Engineering, School of Informatics, Xiamen University, Xiamen, Fujian, China.
  • Department of Neurology and Department of Neuroscience, The First Affiliated Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China.
  • Xiamen Key Laboratory of Brain Center, Xiamen, Fujian, China.
  • School of Graduate Studies, La Consolacion University Philippines, Malolos, Philippines.
  • College of Mathematics and Statistics, Hainan Normal University, Haikou, Hainan, China.

Zitieren

APA

Chen, Y., Quan, L., Long, C., Chen, Y., Zu, L., & Huang, C. (2024). Brain tumor segmentation based on the U-NET+⁣+ network with efficientnet encoder. Technology and Health Care, 32, 183-195. https://doi.org/10.3233/thc-248016

Vancouver

Chen Y, Quan L, Long C, Chen Y, Zu L, Huang C. Brain tumor segmentation based on the U-NET+⁣+ network with efficientnet encoder. Technology and Health Care. 2024;32:183-195. doi:10.3233/thc-248016

BibTeX
@article{Chen2024,
  author = {Chen, Yunyi and Quan, Lan and Long, Chao and Chen, Yuxuan and Zu, Li and Huang, Chenxi},
  title = {Brain tumor segmentation based on the U-NET+⁣+ network with efficientnet encoder},
  journal = {Technology and Health Care},
  year = {2024},
  volume = {32},
  pages = {183--195},
  doi = {10.3233/thc-248016}
}
Kostenlos starten →