EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

An artificial intelligence‐based recognition model of colorectal liver metastases in intraoperative ultrasonography with improved accuracy through algorithm integration

Maho Takayama, Kyoji Ito, Kenji Karako, Yuichiro Mihara, Shu Sasaki, Akihiko Ichida, Takeshi Takamoto, Nobuhisa Akamatsu iD, Yoshikuni Kawaguchi iD, Kiyoshi Hasegawa iD

Journal of Hepato-Biliary-Pancreatic Sciences · 2025

DOI: 10.1002/jhbp.12089 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Hepato-Biliary-Pancreatic Sciences, 2025. Verfasst von Maho Takayama und 9 weiteren Autor:innen. Beteiligte Einrichtung: Hepato-Biliary-Pancreatic Surgery Division, Artificial Organ and Transplantation Division, Department of Surgery, Graduate School of Medicine, The Un…. Hauptthemen laut MEDLINE: Colorectal Neoplasms, Liver Neoplasms, Artificial Intelligence, Algorithms. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Japan Society for the Promotion of Science, Japan Surgical Society.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Purpose Contrast‐enhanced intraoperative ultrasonography (CE‐IOUS) is crucial for detecting colorectal liver metastases (CLM) during surgery. Although artificial intelligence shows potential in diagnostic systems, its application in CE‐IOUS is limited.

Methods

This study aimed to develop an automatic tumor detection model using Mask region‐based convolutional neural network (Mask R‐CNN) for CE‐IOUS images. CE‐IOUS videos of the CLM from 121 patients were collected, generating ground truth data. A total of 2659 images were obtained. Two models were developed: the basic recognition model (BRM), which was trained on CE‐mode images, and the subtraction model (SM), which used images created by a subtraction algorithm that highlighted the differences in pixel values between the basic‐mode and CE‐mode images. The subtraction algorithm focuses on echogenicity differences. These two models were combined into a combination model (CM), which assessed outcomes using the prediction probabilities from both models.

Results

The optimal epochs were determined by the maximum area under the curve (AUC), and the thresholds were calculated accordingly. BRM, SM, and CM achieved 89.4%, 86.6%, and 96.5% accuracy, respectively. CM outperformed the individual models, achieving an AUC of 0.99.

Conclusions

A novel automated recognition model was developed for accurate CLM detection in CE‐IOUS by integrating image‐ and algorithm‐based models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Colorectal NeoplasmsLiver NeoplasmsArtificial IntelligenceAlgorithmsHumansMaleFemaleMiddle AgedAgedUltrasonographyNeural Networks, ComputerContrast Media

Stichwörter der Autor:innen

colorectal cancercomputer‐assisted diagnosisliver resectionmachine learningultrasonography

Substanzen

Contrast Media

Autor:innen und Institutionen

  • Hepato-Biliary-Pancreatic Surgery Division, Artificial Organ and Transplantation Division, Department of Surgery, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.

ORCID-Profile: Nobuhisa Akamatsu, Yoshikuni Kawaguchi, Kiyoshi Hasegawa

Förderung

  • Japan Society for the Promotion of Science
  • Japan Surgical Society

Zitieren

APA

Takayama, M., Ito, K., Karako, K., Mihara, Y., Sasaki, S., Ichida, A., Takamoto, T., Akamatsu, N., Kawaguchi, Y., & Hasegawa, K. (2025). An artificial intelligence‐based recognition model of colorectal liver metastases in intraoperative ultrasonography with improved accuracy through algorithm integration. Journal of Hepato-Biliary-Pancreatic Sciences. https://doi.org/10.1002/jhbp.12089

Vancouver

Takayama M, Ito K, Karako K, Mihara Y, Sasaki S, Ichida A, et al. An artificial intelligence‐based recognition model of colorectal liver metastases in intraoperative ultrasonography with improved accuracy through algorithm integration. Journal of Hepato-Biliary-Pancreatic Sciences. 2025. doi:10.1002/jhbp.12089

BibTeX
@article{Takayama2025,
  author = {Takayama, Maho and Ito, Kyoji and Karako, Kenji and Mihara, Yuichiro and Sasaki, Shu and Ichida, Akihiko and Takamoto, Takeshi and Akamatsu, Nobuhisa and Kawaguchi, Yoshikuni and Hasegawa, Kiyoshi},
  title = {An artificial intelligence‐based recognition model of colorectal liver metastases in intraoperative ultrasonography with improved accuracy through algorithm integration},
  journal = {Journal of Hepato-Biliary-Pancreatic Sciences},
  year = {2025},
  doi = {10.1002/jhbp.12089}
}
Kostenlos starten →