EUVIMEDEUVIMED entdecken
Crossref

A Multi-Task Segmentation and Classification Network Based on Ultrasound Images for Predicting the Grading of Ascites in the Abdominal Cavity

Feng Xie iD, Le Tao, Hejing Huang, Chengcheng Liu iD, Dean Ta iD

Ultrasonic Imaging · 23.06.2026

DOI: 10.1177/01617346261450223 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ultrasonic Imaging, online erschienen am 23.06.2026. Verfasst von Feng Xie und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Biomedical Engineering, Fudan University, Shanghai, China. Die Arbeit nennt 42 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Abdominal trauma with bleeding is a leading cause of post-traumatic death, and detecting free fluid in the abdomen or hemoperitoneum can provide critical guidance for clinical management. Rapid and accurate diagnosis of abdominal bleeding using ultrasound is significant for making decisions regarding the need for surgical intervention. This study introduces a multi-task network for the segmentation and classification of ascites in ultrasound images. The network utilizes a U-Net backbone with a ResNext encoder as the basic architecture for the segmentation and classification models. The segmentation network includes a Frequency Channel Attention (FCA) attention module, which effectively broadens the range of captured information and enhances the robustness of channel representation. Furthermore, an Enhanced Channel Attention Multi Feature Fusion (EMFF) was used to extract the interdependencies between feature channels by combining high-order and low-order feature mappings, thereby improving segmentation accuracy. Lastly, a classification branch was created to classify ascites by sharing encoder features. Experiments on the collected ascites ultrasound dataset demonstrated that the proposed method achieved a segmentation Dice of 85.28% and a classification accuracy of 86.18%. It outperformed the leading multi-task SOTA method by 0.7% in Dice and 2.03% in accuracy, establishing a new benchmark for simultaneous ascites assessment. This study showed that the proposed network is valuable for the preliminary diagnosis of ascites in ultrasound and can serve as a potential auxiliary tool for clinical ascites examination in emergency situations.

Schlagwörter

Stichwörter der Autor:innen

abdominal ascitesattention mechanismdeep learningmulti-task learningultrasound image

Autor:innen und Institutionen

  • College of Biomedical Engineering, Fudan University, Shanghai, China.
  • Department of Ultrasound, Second Affiliated Hospital of Naval Medical University, Shanghai, China.

ORCID-Profile: Feng Xie, Chengcheng Liu, Dean Ta

Zitieren

APA

Xie, F., Tao, L., Huang, H., Liu, C., & Ta, D. (2026). A Multi-Task Segmentation and Classification Network Based on Ultrasound Images for Predicting the Grading of Ascites in the Abdominal Cavity. Ultrasonic Imaging. https://doi.org/10.1177/01617346261450223

Vancouver

Xie F, Tao L, Huang H, Liu C, Ta D. A Multi-Task Segmentation and Classification Network Based on Ultrasound Images for Predicting the Grading of Ascites in the Abdominal Cavity. Ultrasonic Imaging. 2026. doi:10.1177/01617346261450223

BibTeX
@article{Xie2026,
  author = {Xie, Feng and Tao, Le and Huang, Hejing and Liu, Chengcheng and Ta, Dean},
  title = {A Multi-Task Segmentation and Classification Network Based on Ultrasound Images for Predicting the Grading of Ascites in the Abdominal Cavity},
  journal = {Ultrasonic Imaging},
  year = {2026},
  doi = {10.1177/01617346261450223}
}
Kostenlos starten →