EUVIMEDEUVIMED entdecken
Multizentrische Studie

nnU-Net-based CT segmentation of perigastric varices in sinistral portal hypertension: a multicenter study

Wenkai Wei, Chenggang Wu, Lin Wang, Jianbin Yin, Jia Liu, Kun Zhang, Lei Cui

Abdominal Radiology · 16.06.2026 · 51 (12) · 6572-6583

DOI: 10.1007/s00261-026-05545-7 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Abdominal Radiology, online erschienen am 16.06.2026. Verfasst von Wenkai Wei und 6 weiteren Autor:innen. Beteiligte Einrichtung: Radiology Department, Nantong First People's Hospital, Southeast University, Nantong, Jiangsu, China. Hauptthemen laut MEDLINE: Deep Learning, Esophageal and Gastric Varices, Radiographic Image Interpretation, Computer-Assisted, Sinistral Portal Hypertension. Die Arbeit nennt 21 Literaturangaben. Gefördert von: Southeast University Affiliated Nantong First People's Hospital, Southeast University Affiliated Nantong First People’s Hospital.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: To develop a deep learning model based on nnU-Net for automated segmentation of all perigastric veins on contrast-enhanced CT images in patients with sinistral portal hypertension (SPH). METHODS: Retrospectively including contrast-enhanced computed tomography (CT) portal venous phase images from 172 pancreatic cancer patients with SPH across three hospitals in Nantong. The patients were divided into the training dataset (n = 99), model optimization dataset (n = 22), internal testing dataset (n = 22), and external testing dataset (n = 29). The self-configuring nnU-Net model was trained on the manually segmented training dataset. Evaluation metrics on the testing datasets included Dice similarity coefficient (DSC), recall, precision and Hausdorff distance (HD). Pearson correlation and Bland-Altman analyses were conducted between the reference standard and predicted diameters. Intraclass correlation coefficients (ICCs) were used to assess inter-rater agreement and reproducibility of radiomic features. RESULTS: The nnU-Net model achieved a DSC of 0.784 (95% CI 0.710, 0.857) on the internal testing dataset and 0.780 (95% CI 0.705, 0.856) on the external testing dataset, outperforming the comparative models. Predicted diameters correlated strongly with the reference standard in both testing datasets, notably for the gastric coronary vein (r = 0.967), with all perigastric varices achieving correlations > 0.770 (p < 0.001). High intra-rater (ICC = 0.852; 95% CI 0.806, 0.897) and inter-rater agreement (ICC = 0.839; 95% CI 0.793, 0.885) were observed, and feature reproducibility remained robust in both the internal (ICC = 0.853; 95% CI 0.827, 0.879) and external testing datasets (ICC = 0.870; 95% CI 0.833, 0.906). CONCLUSION: The nnU-Net model provides promising segmentation performance for perigastric varices in SPH.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningEsophageal and Gastric VaricesRadiographic Image Interpretation, Computer-AssistedSinistral Portal HypertensionTomography, X-Ray ComputedAgedFemaleHumansMaleMiddle AgedContrast MediaReproducibility of ResultsRetrospective Studies

Stichwörter der Autor:innen

Artificial intelligenceDeep learningPancreatic cancerSinistral portal hypertension

Substanzen

Contrast Media

Autor:innen und Institutionen

  • Radiology Department, Nantong First People's Hospital, Southeast University, Nantong, Jiangsu, China.
  • Radiology Department, Affiliated Nantong Clinical College of Nantong University, Nantong First People's Hospital, Nantong, Jiangsu, China.
  • School of Electrical Engineering and Automation, Nantong University, Nantong, Jiangsu, China.
  • Radiology Department, Nantong First People's Hospital, Southeast University, Nantong, Jiangsu, China. cuigeleili@126.com.
  • Radiology Department, Affiliated Nantong Clinical College of Nantong University, Nantong First People's Hospital, Nantong, Jiangsu, China. cuigeleili@126.com.

Förderung

  • Southeast University Affiliated Nantong First People's Hospital
  • Southeast University Affiliated Nantong First People’s Hospital

Zitieren

APA

Wei, W., Wu, C., Wang, L., Yin, J., Liu, J., Zhang, K., & Cui, L. (2026). nnU-Net-based CT segmentation of perigastric varices in sinistral portal hypertension: a multicenter study. Abdominal Radiology, 51(12), 6572-6583. https://doi.org/10.1007/s00261-026-05545-7

Vancouver

Wei W, Wu C, Wang L, Yin J, Liu J, Zhang K, et al. nnU-Net-based CT segmentation of perigastric varices in sinistral portal hypertension: a multicenter study. Abdominal Radiology. 2026;51(12):6572-6583. doi:10.1007/s00261-026-05545-7

BibTeX
@article{Wei2026,
  author = {Wei, Wenkai and Wu, Chenggang and Wang, Lin and Yin, Jianbin and Liu, Jia and Zhang, Kun and Cui, Lei},
  title = {nnU-Net-based CT segmentation of perigastric varices in sinistral portal hypertension: a multicenter study},
  journal = {Abdominal Radiology},
  year = {2026},
  volume = {51},
  number = {12},
  pages = {6572--6583},
  doi = {10.1007/s00261-026-05545-7}
}
Kostenlos starten →