EUVIMEDEUVIMED entdecken
Crossref

Machine Learning Models Based on CT Enterography for Differentiating Between Ulcerative Colitis and Colonic Crohn’s Disease Using Intestinal Wall, Mesenteric Fat, and Visceral Fat Features

Xia Wang, Xingwei Wang, Jie Lei, Chang Rong, Xiaomin Zheng, Shuai Li, Yankun Gao, Xingwang Wu

Academic Radiology · 2025

DOI: 10.1016/j.acra.2025.06.005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Radiology, 2025. Verfasst von Xia Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230022, China (X.W., X.W., J.L., C.R., X.Z., S.L., …. Hauptthemen laut MEDLINE: Crohn Disease, Machine Learning, Colitis, Ulcerative, Tomography, X-Ray Computed. Die Arbeit nennt 29 Literaturangaben. Gefördert von: Anhui Provincial Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: This study aimed to develop radiomic-based machine learning models using computed tomography enterography (CTE) features derived from the intestinal wall, mesenteric fat, and visceral fat to differentiate between ulcerative colitis (UC) and colonic Crohn's disease (CD). METHODS: Clinical and imaging data from 116 patients with inflammatory bowel disease (IBD) (68 with UC and 48 with colonic CD) were retrospectively collected. Radiomic features were extracted from venous-phase CTE images. Feature selection was performed via the intraclass correlation coefficient (ICC), correlation analysis, SelectKBest, and least absolute shrinkage and selection operator (LASSO) regression. Support vector machine models were constructed using features from individual and combined regions, with model performance evaluated using the area under the ROC curve (AUC). RESULTS: The combined radiomic model, integrating features from all three regions, exhibited superior classification performance (AUC= 0.857, 95% CI, 0.732-0.982), with a sensitivity of 0.762 (95% CI, 0.547-0.903) and specificity of 0.857 (95% CI, 0.601-0.960) in the testing cohort. The models based on features from the intestinal wall, mesenteric fat, and visceral fat achieved AUCs of 0.847 (95% CI, 0.710-0.984), 0.707 (95% CI, 0.526-0.889), and 0.731 (95% CI, 0.553-0.910), respectively, in the testing cohort. The intestinal wall model demonstrated the best calibration. CONCLUSION: This study demonstrated the feasibility of constructing machine learning models based on radiomic features of the intestinal wall, mesenteric fat, and visceral fat to distinguish between UC and colonic CD.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Crohn DiseaseMachine LearningColitis, UlcerativeTomography, X-Ray ComputedIntra-Abdominal FatHumansMaleFemaleRetrospective StudiesAdultDiagnosis, DifferentialMiddle AgedSensitivity and SpecificityMesenteryRadiographic Image Interpretation, Computer-AssistedIntestinesAged

Stichwörter der Autor:innen

Colonic Crohn’s diseaseComputed tomography enterographyMachine learningRadiomicsUlcerative colitis

Autor:innen und Institutionen

  • Department of Radiology, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230022, China (X.W., X.W., J.L., C.R., X.Z., S.L., Y.G., X.W.).
  • Department of Radiology, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230022, China (X.W., X.W., J.L., C.R., X.Z., S.L., Y.G., X.W.); Department of Radiology, Hefei BOE Hospital, Hefei, Anhui…
  • Department of Radiology, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230022, China (X.W., X.W., J.L., C.R., X.Z., S.L., Y.G., X.W.). Electronic address: duobi2004@126.com.

Förderung

  • Anhui Provincial Natural Science Foundation

Zitieren

APA

Wang, X., Wang, X., Lei, J., Rong, C., Zheng, X., Li, S., Gao, Y., & Wu, X. (2025). Machine Learning Models Based on CT Enterography for Differentiating Between Ulcerative Colitis and Colonic Crohn’s Disease Using Intestinal Wall, Mesenteric Fat, and Visceral Fat Features. Academic Radiology. https://doi.org/10.1016/j.acra.2025.06.005

Vancouver

Wang X, Wang X, Lei J, Rong C, Zheng X, Li S, et al. Machine Learning Models Based on CT Enterography for Differentiating Between Ulcerative Colitis and Colonic Crohn’s Disease Using Intestinal Wall, Mesenteric Fat, and Visceral Fat Features. Academic Radiology. 2025. doi:10.1016/j.acra.2025.06.005

BibTeX
@article{Wang2025,
  author = {Wang, Xia and Wang, Xingwei and Lei, Jie and Rong, Chang and Zheng, Xiaomin and Li, Shuai and Gao, Yankun and Wu, Xingwang},
  title = {Machine Learning Models Based on CT Enterography for Differentiating Between Ulcerative Colitis and Colonic Crohn’s Disease Using Intestinal Wall, Mesenteric Fat, and Visceral Fat Features},
  journal = {Academic Radiology},
  year = {2025},
  doi = {10.1016/j.acra.2025.06.005}
}
Kostenlos starten →