A magnetic resonance image-based deep learning radiomics nomogram for hepatocyte cytokeratin 7 expression: application to predict cholestasis progression in children with pancreaticobiliary maljunction
Pediatric Radiology · 2025
DOI: 10.1007/s00247-025-06225-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pediatric Radiology, 2025. Verfasst von Yang Yang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Children's Hospital of Soochow University, No. 92 Zhongnan Street, Industrial Park, Suzhou, Jiangsu Province, 215028, China. Hauptthemen laut MEDLINE: Deep Learning, Keratin-7, Magnetic Resonance Imaging, Nomograms. Die Arbeit nennt 37 Literaturangaben. Gefördert von: Scientific Research Project of Jiangsu Provincial Health Commission, Science and Technology Development Project of Suzhou, Suzhou Clinical Key Disease Diagnosis and Treatment Technology Special Project.
Themen: Kinderkrankenpflege
Abstract (Originalsprache)
BACKGROUND: Hepatocyte cytokeratin 7 (CK7) is a reliable marker for evaluating the severity of cholestasis in chronic cholestatic cholangiopathies. However, there is currently no noninvasive test available to assess the status of hepatocyte CK7 in pancreaticobiliary maljunction patients. OBJECTIVE: We aimed to develop a deep learning radiomics nomogram using magnetic resonance images (MRIs) to preoperatively identify the hepatocyte CK7 status and assess cholestasis progression in patients with pancreaticobiliary maljunction. MATERIALS AND METHODS: In total, 180 pancreaticobiliary maljunction patients were retrospectively enrolled and were randomly divided into a training cohort (n = 144) and a validation cohort (n = 36). CK7 status was determined through immunohistochemical analysis. Pyradiomics and pretrained ResNet50 were used to extract radiomics and deep learning features, respectively. To construct the radiomics and deep learning signature, feature selection methods including the minimum redundancy-maximum relevance and least absolute shrinkage and selection operator were employed. The integrated deep learning radiomics nomogram model was constructed by combining the imaging signatures and valuable clinical feature. RESULTS: The deep learning signature exhibited superior predictive performance compared with the radiomics signature, as evidenced by the higher area under the curve (AUC) values in validation cohort (0.92 vs. 0.81). Further, the deep learning radiomics nomogram, which incorporated the radiomics signature, deep learning signature, and Komi classification, demonstrated excellent predictive ability for CK7 expression, with AUC value of 0.95 in the validation cohort. CONCLUSION: The proposed deep learning radiomics nomogram exhibits promising performance in accurately identifying hepatic CK7 expression, thus facilitating prediction of cholestasis progression and perhaps earlier initiation of treatment in pancreaticobiliary maljunction children.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Children's Hospital of Soochow University, No. 92 Zhongnan Street, Industrial Park, Suzhou, Jiangsu Province, 215028, China.
- Children's Hospital of Soochow University, No. 92 Zhongnan Street, Industrial Park, Suzhou, Jiangsu Province, 215028, China. gwlsuzhou@163.com.
Förderung
- Scientific Research Project of Jiangsu Provincial Health Commission
- Science and Technology Development Project of Suzhou
- Suzhou Clinical Key Disease Diagnosis and Treatment Technology Special Project
- Soochow University Medical +X project
- Science, Education, and Health Strengthening" Key Project of Suzhou
- Science, Education, and Health Strengthening” Key Project of Suzhou
Zitieren
APA
Yang, Y., Mao, H. M., Huang, S. G., & Guo, W. L. (2025). A magnetic resonance image-based deep learning radiomics nomogram for hepatocyte cytokeratin 7 expression: application to predict cholestasis progression in children with pancreaticobiliary maljunction. Pediatric Radiology. https://doi.org/10.1007/s00247-025-06225-2
Vancouver
Yang Y, Mao HM, Huang SG, Guo WL. A magnetic resonance image-based deep learning radiomics nomogram for hepatocyte cytokeratin 7 expression: application to predict cholestasis progression in children with pancreaticobiliary maljunction. Pediatric Radiology. 2025. doi:10.1007/s00247-025-06225-2
BibTeX
@article{Yang2025,
author = {Yang, Yang and Mao, Hui-Min and Huang, Shun-Gen and Guo, Wan-Liang},
title = {A magnetic resonance image-based deep learning radiomics nomogram for hepatocyte cytokeratin 7 expression: application to predict cholestasis progression in children with pancreaticobiliary maljunction},
journal = {Pediatric Radiology},
year = {2025},
doi = {10.1007/s00247-025-06225-2}
}
EUVIMED