EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Super-resolution deep learning reconstruction improves the depiction of peripancreatic arteries and image quality in pancreatic cancer CT

Rin Tsujimoto, Koichiro Yasaka, Takatoshi Kubo, Satoru Kamio, Akira Katayama, Yusuke Asari, Ako Negishi, Osamu Abe

Abdominal Radiology · 13.06.2026 · 51 (12) · 6561-6571

DOI: 10.1007/s00261-026-05596-w ↗

Kurz gefasst

Fachartikel in der Zeitschrift Abdominal Radiology, online erschienen am 13.06.2026. Verfasst von Rin Tsujimoto und 7 weiteren Autor:innen. Beteiligte Einrichtung: The University of Tokyo, Tokyo, Japan. Hauptthemen laut MEDLINE: Pancreatic Neoplasms, Deep Learning, Tomography, X-Ray Computed, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The University of Tokyo.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Accurate identification of peripancreatic arteries in pancreatic ductal adenocarcinoma (PDAC) is essential for determining surgical strategy and prognosis. This study compared super-resolution deep learning reconstruction (SR-DLR) with normal-resolution deep learning reconstruction (NR-DLR) and hybrid iterative reconstruction (HIR) in the depiction of peripancreatic arteries in patients with PDAC undergoing pancreatic dynamic CT.

Methods

This retrospective study included 40 patients (mean age, 70.8 ± 9.3 years) with pathologically confirmed PDAC who underwent pancreatic dynamic CT. Images were reconstructed using SR-DLR, NR-DLR, and HIR. In quantitative image analyses, CT attenuation, image noise, contrast-to-noise ratio (CNR), edge rise slope (ERS), and edge rise distance (ERD) were assessed. In qualitative image analyses, five radiologists independently evaluated arterial depiction of major arteries and small peripancreatic arteries, tumor–vessel interface, image noise, image sharpness, diagnostic acceptability, and tumor conspicuity. Statistical analyses were performed using paired t -tests and the Wilcoxon signed-rank test with Bonferroni correction.

Results

SR-DLR showed higher CT attenuation, lower image noise, and higher CNR than NR-DLR and HIR (all p < 0.001). For both the superior mesenteric artery and pancreatic parenchyma, ERS was higher with SR-DLR than with NR-DLR and HIR (all p ≤ 0.002), whereas ERD was lower than with NR-DLR and HIR (all p ≤ 0.001). In qualitative image analyses, SR-DLR achieved the highest scores for small peripancreatic arteries and all qualitative items except for the depiction of major peripancreatic arteries ( p < 0.001).

Conclusion

SR-DLR improved quantitative image quality and enhanced the qualitative depiction of small peripancreatic arteries and the tumor–vessel interface in pancreatic dynamic CT for patients with PDAC.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pancreatic NeoplasmsDeep LearningTomography, X-Ray ComputedRadiographic Image Interpretation, Computer-AssistedCarcinoma, Pancreatic DuctalHumansFemaleMaleRetrospective StudiesAgedPancreasMiddle AgedContrast Media

Stichwörter der Autor:innen

ArteriesComputer-assistedDeep learningImage processingPancreatic neoplasmsTomographyX-ray computed

Substanzen

Contrast Media

Autor:innen und Institutionen

  • The University of Tokyo, Tokyo, Japan.
  • The University of Tokyo, Tokyo, Japan. koyasaka@gmail.com.

Förderung

  • The University of Tokyo

Zitieren

APA

Tsujimoto, R., Yasaka, K., Kubo, T., Kamio, S., Katayama, A., Asari, Y., Negishi, A., & Abe, O. (2026). Super-resolution deep learning reconstruction improves the depiction of peripancreatic arteries and image quality in pancreatic cancer CT. Abdominal Radiology, 51(12), 6561-6571. https://doi.org/10.1007/s00261-026-05596-w

Vancouver

Tsujimoto R, Yasaka K, Kubo T, Kamio S, Katayama A, Asari Y, et al. Super-resolution deep learning reconstruction improves the depiction of peripancreatic arteries and image quality in pancreatic cancer CT. Abdominal Radiology. 2026;51(12):6561-6571. doi:10.1007/s00261-026-05596-w

BibTeX
@article{Tsujimoto2026,
  author = {Tsujimoto, Rin and Yasaka, Koichiro and Kubo, Takatoshi and Kamio, Satoru and Katayama, Akira and Asari, Yusuke and Negishi, Ako and Abe, Osamu},
  title = {Super-resolution deep learning reconstruction improves the depiction of peripancreatic arteries and image quality in pancreatic cancer CT},
  journal = {Abdominal Radiology},
  year = {2026},
  volume = {51},
  number = {12},
  pages = {6561--6571},
  doi = {10.1007/s00261-026-05596-w}
}
Kostenlos starten →