EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning‐Based Radiomics in Malignancy Prediction of Pancreatic Cystic Lesions: Evidence from Cyst Fluid Multi‐Omics

Sihang Cheng iD, Ge Hu, Shenbo Zhang, Rui Lv, Limeng Sun, Zhe Zhang, Zhengyu Jin, Yanyan Wu, Chen Huang, Lu Ye, Yunlu Feng, Zhe-Sheng Chen und 3 weitere

Advanced Science · 2025

DOI: 10.1002/advs.202409488 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, 2025. Verfasst von Sihang Cheng und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, 100730, China. Hauptthemen laut MEDLINE: Machine Learning, Pancreatic Neoplasms, Pancreatic Cyst, Cyst Fluid. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Natural Science Foundation, National Natural Science Foundation of China, National High-Level Hospital Clinical Research Funding.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The malignant potential of pancreatic cystic lesions (PCLs) varies dramatically, leading to difficulties when making clinical decisions. This study aimed to develop noninvasive clinical‐radiomic models using preoperative CT images to predict the malignant potential of PCLs. It also investigates the biological mechanisms underlying these models. Patients from two retrospective and one prospective cohort, all undergoing surgical resection for PCLs, are divided into four datasets: training, internal test, external test, and prospective application sets. Eleven machine learning classifiers are employed to construct radiomic models based on selected features. Cyst fluid from the prospective cohort is collected for proteomic and lipidomic analysis. The radiomic models demonstrated high accuracy, with area under the receiver operating characteristic curves (AUCs) > 0.93 across the training (n = 262), internal test (n = 50), and external test (n = 50) sets. AUCs ranged from 0.92 to 0.96 for the prospective cohort (n = 34). Meanwhile, differentially‐expressed proteins and lipid molecules, along with their associated signaling pathways, are identified between high and low groups of clinical‐radiomic scores. This models can effectively and accurately predict the malignant potential of PCLs, with multi‐omics evidence suggesting the biological mechanisms involving secretion function and lipid metabolism underlying clinical‐radiomic models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningPancreatic NeoplasmsPancreatic CystCyst FluidHumansMaleFemaleMiddle AgedTomography, X-Ray ComputedProspective StudiesRetrospective StudiesProteomicsAgedAdultMultiomicsRadiomics

Stichwörter der Autor:innen

artificial intelligencelipidomicpancreatic cystic lesionsproteomicradiomics

Autor:innen und Institutionen

  • Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, 100730, China.
  • Theranostics and Translational Research Center, National Infrastructures for Translational Medicine, Institute of Clinical Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking…
  • Department of Gastroenterology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, 100730, China.
  • Department of Interventional Radiology, The Affiliated Panyu Central Hospital of Guangzhou Medical University, Guangzhou, 511400, China.
  • Interventional Center, Chengdu First People's Hospital, Chengdu, 610041, China.
  • Department of Pharmaceutical Sciences, College of Pharmacy and Health Sciences, St. John's University, Queens, NY, 11439, USA.

ORCID-Profile: Sihang Cheng

Förderung

  • Beijing Natural Science Foundation
  • National Natural Science Foundation of China
  • National High-Level Hospital Clinical Research Funding
  • CAMS Innovation Fund for Medical Sciences (CIFMS)
  • Peking Union Medical College Hospital Young Reserve Talent Development Program
  • Non-profit Central Research Institute Fund of Chinese Academy of Medical Sciences
  • Natural Science Foundation of Beijing Municipality

Zitieren

APA

Cheng, S., Hu, G., Zhang, S., Lv, R., Sun, L., Zhang, Z., Jin, Z., Wu, Y., Huang, C., Ye, L., Feng, Y., Chen, Z. S., Wang, Z., Xue, H., & Yang, A. (2025). Machine Learning‐Based Radiomics in Malignancy Prediction of Pancreatic Cystic Lesions: Evidence from Cyst Fluid Multi‐Omics. Advanced Science. https://doi.org/10.1002/advs.202409488

Vancouver

Cheng S, Hu G, Zhang S, Lv R, Sun L, Zhang Z, et al. Machine Learning‐Based Radiomics in Malignancy Prediction of Pancreatic Cystic Lesions: Evidence from Cyst Fluid Multi‐Omics. Advanced Science. 2025. doi:10.1002/advs.202409488

BibTeX
@article{Cheng2025,
  author = {Cheng, Sihang and Hu, Ge and Zhang, Shenbo and Lv, Rui and Sun, Limeng and Zhang, Zhe and Jin, Zhengyu and Wu, Yanyan and Huang, Chen and Ye, Lu and Feng, Yunlu and Chen, Zhe-Sheng and Wang, Zhiwei and Xue, Huadan and Yang, Aiming},
  title = {Machine Learning‐Based Radiomics in Malignancy Prediction of Pancreatic Cystic Lesions: Evidence from Cyst Fluid Multi‐Omics},
  journal = {Advanced Science},
  year = {2025},
  doi = {10.1002/advs.202409488}
}
Kostenlos starten →