EUVIMEDEUVIMED entdecken
Crossref

Development of a lightweight deep learning model for accurate assessment of liver fibrosis in biliary atresia

Qianhui Yang, Yuqiang Chen, Yu Meng, Xizhe Luo, Li Zhao, Xiaodan Xu, Jichang Guo, Shufang Zhang, Jianghua Zhan

Pediatric Surgery International · 09.02.2026 · 42 (1)

DOI: 10.1007/s00383-026-06296-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pediatric Surgery International, online erschienen am 09.02.2026. Verfasst von Qianhui Yang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Clinical School of Pediatrics, Tianjin Medical University, Tianjin, China. Hauptthemen laut MEDLINE: Biliary Atresia, Deep Learning, Liver Cirrhosis. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Gefördert von: Tianjin Applied Basic Research Project, Tianjin Key Medical Discipline(Specialty) Construction Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Given the lack of research on deep learning for evaluating liver fibrosis in biliary atresia (BA), and the challenge of balancing accuracy and efficiency in lightweight models, this study aims to develop a liver fibrosis assessment model utilizing Dynamic SpatialLite-EfficientNet (DSL-Net), based on the BA-specific staging system. METHODS: A total of 530 HE whole slide images scanned from liver biopsies at Kasai portoenterostomy were used for the train (80%), validation (10%), and test (10%) of DSL-Net model. In the test cohort, the quantitative performance of DSL-Net was compared with that of existing lightweight models. Additionally, the model’s performance in liver fibrosis assessment was compared with that of six pathologists, and its prognostic predictive ability was further validated against traditional liver fibrosis scoring systems. RESULTS: The quantitative performance of DSL-Net model was 6.9 M (Params), 0.5G (FLOPs), and 86.4 ± 0.7% (average Dice coefficient). It achieved an AUC of 0.906 for liver fibrosis assessment (≥ stage 3), comparable to two senior pediatric pathologists. With DSL-Net’s assistance, the AUCs for two junior pathologists and one attending pediatric pathologist improved from 0.685, 0.867, and 0.837 to 0.916 (P = 0.008), 0.907 (P = 0.005), and 0.948 (P = 0.021), respectively. Compared to the Metavir and Ishark scoring systems, DSL-Net model also demonstrated promising potential in predicting native liver survival (NLS), with 2-year and 5-year NLS AUCs of 0.8232 (P = 0.013; P = 0.046) and 0.7845 (P = 0.144; P = 0.656). CONCLUSION: Based on the results of this study, the DSL-Net model demonstrates relatively higher accuracy in liver fibrosis assessment (≥ stage 3) and short-term prognostic prediction of BA, with both parameter count and computational cost comparable to the mainstream lightweight architecture. This positions DSL-Net as a promising, lightweight, and efficient tool for liver fibrosis assessment in BA, thereby better guiding clinical decision-making for BA patients.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Biliary AtresiaDeep LearningLiver CirrhosisHumansMaleInfantFemalePortoenterostomy, HepaticBiopsyPrognosis

Stichwörter der Autor:innen

Biliary atresiaDeep learningHistopathologyLiver fibrosisStaging system

Autor:innen und Institutionen

  • Clinical School of Pediatrics, Tianjin Medical University, Tianjin, China.
  • Department of General Surgery, Tianjin Children's Hospital (Children's Hospital of Tianjin University, Tianjin University, Tianjin, China.
  • Department of General Surgery, Urumqi Children's Hospital, Urumqi, Xinjiang, China.
  • School of Electrical and Information Engineering, Tianjin University, Tianjin, China.
  • Department of Pathology, Tianjin Children's Hospital (Children's Hospital of Tianjin University, Tianjin University, Tianjin, China.
  • Department of Pediatric Surgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei Province, China.

Förderung

  • Tianjin Applied Basic Research Project
  • Tianjin Key Medical Discipline(Specialty) Construction Project

Zitieren

APA

Yang, Q., Chen, Y., Meng, Y., Luo, X., Zhao, L., Xu, X., Guo, J., Zhang, S., & Zhan, J. (2026). Development of a lightweight deep learning model for accurate assessment of liver fibrosis in biliary atresia. Pediatric Surgery International, 42(1). https://doi.org/10.1007/s00383-026-06296-8

Vancouver

Yang Q, Chen Y, Meng Y, Luo X, Zhao L, Xu X, et al. Development of a lightweight deep learning model for accurate assessment of liver fibrosis in biliary atresia. Pediatric Surgery International. 2026;42(1). doi:10.1007/s00383-026-06296-8

BibTeX
@article{Yang2026,
  author = {Yang, Qianhui and Chen, Yuqiang and Meng, Yu and Luo, Xizhe and Zhao, Li and Xu, Xiaodan and Guo, Jichang and Zhang, Shufang and Zhan, Jianghua},
  title = {Development of a lightweight deep learning model for accurate assessment of liver fibrosis in biliary atresia},
  journal = {Pediatric Surgery International},
  year = {2026},
  volume = {42},
  number = {1},
  doi = {10.1007/s00383-026-06296-8}
}
Kostenlos starten →