EUVIMEDEUVIMED entdecken
Multizentrische Studie

Deep learning model to differentiate Crohn’s disease from intestinal tuberculosis using histopathological whole slide images from intestinal specimens

Xinning Liu, Fei Li, Jie Xu, Jinting Ma, Xiaoyu Duan, Ren Mao, Minhu Chen, Zhihui Chen, Yan Huang, Jingyi Jiang, Bingsheng Huang, Ziyin Ye

Virchows Archiv · 2024

DOI: 10.1007/s00428-024-03740-9 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Virchows Archiv, 2024. Verfasst von Xinning Liu und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology, The First Affiliated Hospital, Sun Yat-sen University, No. 58 Zhongshan Road 2, Guangzhou, 510080, Guangdong, People's Repub…. Hauptthemen laut MEDLINE: Crohn Disease, Deep Learning, Tuberculosis, Gastrointestinal. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Guangdong Basic and Applied Basic Research Foundation, National Natural Science Foundation of China, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Crohn's disease (CD) and intestinal tuberculosis (ITB) share similar histopathological characteristics, and differential diagnosis can be a dilemma for pathologists. This study aimed to apply deep learning (DL) to analyze whole slide images (WSI) of surgical resection specimens to distinguish CD from ITB. Overall, 1973 WSI from 85 cases from 3 centers were obtained. The DL model was established in internal training and validated in external test cohort, evaluated by area under receiver operator characteristic curve (AUC). Diagnostic results of pathologists were compared with those of the DL model using DeLong's test. DL model had case level AUC of 0.886, 0.893 and slide level AUC of 0.954, 0.827 in training and test cohorts. Attention maps highlighted discriminative areas and top 10 features were extracted from CD and ITB. DL model's diagnostic efficiency (AUC = 0.886) was better than junior pathologists (*1 AUC = 0.701, P = 0.088; *2 AUC = 0.861, P = 0.788) and inferior to senior GI pathologists (*3 AUC = 0.910, P = 0.800; *4 AUC = 0.946, P = 0.507) in training cohort. In the test cohort, model (AUC = 0.893) outperformed senior non-GI pathologists (*5 AUC = 0.782, P = 0.327; *6 AUC = 0.821, P = 0.516). We developed a DL model for the classification of CD and ITB, improving pathological diagnosis accuracy effectively.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Crohn DiseaseDeep LearningTuberculosis, GastrointestinalHumansDiagnosis, DifferentialMaleFemaleAdultMiddle AgedReproducibility of ResultsImage Interpretation, Computer-AssistedIntestinesPredictive Value of TestsYoung Adult

Stichwörter der Autor:innen

Crohn’s diseaseDeep learningIntestinal tuberculosisPathological diagnosis

Autor:innen und Institutionen

  • Department of Pathology, The First Affiliated Hospital, Sun Yat-sen University, No. 58 Zhongshan Road 2, Guangzhou, 510080, Guangdong, People's Republic of China.
  • Department of Pathology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong, People's Republic of China.
  • Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, 1066 Xueyuan Avenue, Shenzhen, 518000, Guangdong, People's Republic of China.
  • Department of Pathology, The Seventh Affiliated Hospital, Sun Yat-sen University, Shenzhen, Guangdong, People's Republic of China.
  • Department of Gastroenterology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, People's Republic of China.
  • Department of Gastrointestinal and Pancreatic Surgery, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, People's Republic of China.

Förderung

  • Guangdong Basic and Applied Basic Research Foundation
  • National Natural Science Foundation of China
  • Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions
  • Key-Area Research and Development Program of Guangdong Province
  • Guangdong Provincial Clinical Research Center for Digestive Diseases
  • National Key R&D Program of China

Zitieren

APA

Liu, X., Li, F., Xu, J., Ma, J., Duan, X., Mao, R., Chen, M., Chen, Z., Huang, Y., Jiang, J., Huang, B., & Ye, Z. (2024). Deep learning model to differentiate Crohn’s disease from intestinal tuberculosis using histopathological whole slide images from intestinal specimens. Virchows Archiv. https://doi.org/10.1007/s00428-024-03740-9

Vancouver

Liu X, Li F, Xu J, Ma J, Duan X, Mao R, et al. Deep learning model to differentiate Crohn’s disease from intestinal tuberculosis using histopathological whole slide images from intestinal specimens. Virchows Archiv. 2024. doi:10.1007/s00428-024-03740-9

BibTeX
@article{Liu2024,
  author = {Liu, Xinning and Li, Fei and Xu, Jie and Ma, Jinting and Duan, Xiaoyu and Mao, Ren and Chen, Minhu and Chen, Zhihui and Huang, Yan and Jiang, Jingyi and Huang, Bingsheng and Ye, Ziyin},
  title = {Deep learning model to differentiate Crohn’s disease from intestinal tuberculosis using histopathological whole slide images from intestinal specimens},
  journal = {Virchows Archiv},
  year = {2024},
  doi = {10.1007/s00428-024-03740-9}
}
Kostenlos starten →