Improved segmentation of hepatic vascular networks in ultrasound volumes using 3D U-Net with intensity transformation-based data augmentation
Medical & Biological Engineering & Computing · 2025-07 · 63 (7) · 2133-2144
DOI: 10.1007/s11517-025-03320-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, online erschienen am 13.02.2025. Verfasst von Yukino Takahashi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Tokyo University of Agriculture and Technology, Tokyo, Japan. Hauptthemen laut MEDLINE: Liver, Imaging, Three-Dimensional. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science, Research Center for Biomedical Engineering.
Abstract (Originalsprache)
Accurate three-dimensional (3D) segmentation of hepatic vascular networks is crucial for supporting ultrasound-mediated theranostics for liver diseases. Despite advancements in deep learning techniques, accurate segmentation remains challenging due to ultrasound image quality issues, including intensity and contrast fluctuations. This study introduces intensity transformation-based data augmentation methods to improve deep convolutional neural network-based segmentation of hepatic vascular networks. We employed a 3D U-Net, which leverages spatial contextual information, as the baseline. To address intensity and contrast fluctuations and improve 3D U-Net performance, we implemented data augmentation using high-contrast intensity transformation with S-shaped tone curves and low-contrast intensity transformation with Gamma and inverse S-shaped tone curves. We conducted validation experiments on 78 ultrasound volumes to evaluate the effect of both geometric and intensity transformation-based data augmentations. We found that high-contrast intensity transformation-based data augmentation decreased segmentation accuracy, while low-contrast intensity transformation-based data augmentation significantly improved Recall and Dice. Additionally, combining geometric and low-contrast intensity transformation-based data augmentations, through an OR operation on their results, further enhanced segmentation accuracy, achieving improvements of 9.7% in Recall and 3.3% in Dice. This study demonstrated the effectiveness of low-contrast intensity transformation-based data augmentation in improving volumetric segmentation of hepatic vascular networks from ultrasound volumes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Engineering, Tokyo University of Agriculture and Technology, Tokyo, Japan.
- Department of Biomedical Informatics, Laboratory for Biomaterials and Bioengineering, Institute of Integrated Research, Institute of Science Tokyo, Tokyo, Japan. sugino.bmi@tmd.ac.jp.
- Department of Biomedical Informatics, Laboratory for Biomaterials and Bioengineering, Institute of Integrated Research, Institute of Science Tokyo, Tokyo, Japan.
Förderung
- Japan Society for the Promotion of Science
- Research Center for Biomedical Engineering
Zitieren
APA
Takahashi, Y., Sugino, T., Onogi, S., Nakajima, Y., & Masuda, K. (2025). Improved segmentation of hepatic vascular networks in ultrasound volumes using 3D U-Net with intensity transformation-based data augmentation. Medical & Biological Engineering & Computing, 63(7), 2133-2144. https://doi.org/10.1007/s11517-025-03320-2
Vancouver
Takahashi Y, Sugino T, Onogi S, Nakajima Y, Masuda K. Improved segmentation of hepatic vascular networks in ultrasound volumes using 3D U-Net with intensity transformation-based data augmentation. Medical & Biological Engineering & Computing. 2025;63(7):2133-2144. doi:10.1007/s11517-025-03320-2
BibTeX
@article{Takahashi2025,
author = {Takahashi, Yukino and Sugino, Takaaki and Onogi, Shinya and Nakajima, Yoshikazu and Masuda, Kohji},
title = {Improved segmentation of hepatic vascular networks in ultrasound volumes using 3D U-Net with intensity transformation-based data augmentation},
journal = {Medical & Biological Engineering & Computing},
year = {2025},
volume = {63},
number = {7},
pages = {2133--2144},
doi = {10.1007/s11517-025-03320-2}
}
EUVIMED