EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY-NC-ND 4.0

MRI ‐Based Topology Deep Learning Model for Noninvasive Prediction of Microvascular Invasion and Assisting Prognostic Stratification in HCC

Tianying Zheng, Yajing Zhu, Hanyu Jiang iD, Chongtu Yang, Yuxiang Ye, Mustafa R Bashir, Chenhui Li, Liling Long, Shishi Luo, Bin Song iD, Yinan Chen, Yidi Chen iD

Liver International · 2025

DOI: 10.1111/liv.16205 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Liver International, 2025. Verfasst von Tianying Zheng und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China. Hauptthemen laut MEDLINE: Liver Neoplasms, Deep Learning, Carcinoma, Hepatocellular, Magnetic Resonance Imaging. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Science and Technology Department of Hainan Province, Post-doctoral Station Development Project of Sanya, Development Project of Hainan Provincial Clinical Medical Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background & Aims Microvascular invasion (MVI) is associated with poor prognosis in hepatocellular carcinoma (HCC). Topology may improve the predictive performance and interpretability of deep learning (DL). We aimed to develop and externally validate an MRI‐based topology DL model for preoperative prediction of MVI.

Methods

This dual‐centre retrospective study included consecutive surgically treated HCC patients from two tertiary care hospitals. Automatic liver and tumour segmentations were performed with DL methods. A pure convolutional neural network (CNN) model, a topology‐CNN (TopoCNN) model and a topology‐CNN‐clinical (TopoCNN+Clinic) model were developed and externally validated. Model performance was assessed using the area under the receiver operating characteristic curve (AUC). Cox regression analyses were conducted to identify risk factors for recurrence‐free survival within 2 years (early RFS) and overall survival (OS).

Results

In total, 589 patients were included (292 [49.6%] with pathologically confirmed MVI). The AUCs of the TopoCNN and TopoCNN+Clinic models were 0.890 and 0.895 for the internal test dataset and 0.871 and 0.879 for the external test dataset, respectively. For tumours ≤ 3.0 cm, the AUCs of the TopoCNN and TopoCNN+Clinic models were 0.879 and 0.929 for the internal test dataset, and 0.763 and 0.758 for the external test dataset. The TopoCNN‐derived MVI prediction probability was an independent risk factor for early RFS (hazard ratio 6.64) and OS (hazard ratio 13.33).

Conclusions

The MRI topological DL model based on automatic liver and tumour segmentation could accurately predict MVI and effectively stratify postoperative early RFS and OS, which may assist in personalised treatment decision‐making.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Liver NeoplasmsDeep LearningCarcinoma, HepatocellularMagnetic Resonance ImagingMicrovesselsHumansMaleFemaleRetrospective StudiesMiddle AgedPrognosisNeoplasm InvasivenessAgedROC CurveProportional Hazards ModelsRisk Factors

Stichwörter der Autor:innen

deep learninghepatocellular carcinomamagnetic resonance imagingmicrovascular invasion

Autor:innen und Institutionen

  • Department of Radiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China.
  • Department of Research, SenseTime, Shanghai, China.
  • Department of Radiology, Center for Advanced Magnetic Resonance in Medicine, and Division of Gastroenterology, Department of Medicine, Duke University Medical Center, Durham, North Carolina, USA.
  • Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, China.
  • Department of Radiology, Hainan General Hospital, Haikou, Hainan, China.
  • Department of Radiology, Sanya People's Hospital, Sanya, Hainan, China.

ORCID-Profile: Hanyu Jiang, Bin Song, Yidi Chen

Förderung

  • Science and Technology Department of Hainan Province
  • Post-doctoral Station Development Project of Sanya
  • Development Project of Hainan Provincial Clinical Medical Center
  • 1.3.5 project for disciplines of excellence, West China Hospital, Sichuan University
  • National Natural Science Foundation of China
  • China Post doctoral Science Foundation
  • Science and Technology Department of Sichuan Province

Zitieren

APA

Zheng, T., Zhu, Y., Jiang, H., Yang, C., Ye, Y., Bashir, M. R., Li, C., Long, L., Luo, S., Song, B., Chen, Y., & Chen, Y. (2025). MRI ‐Based Topology Deep Learning Model for Noninvasive Prediction of Microvascular Invasion and Assisting Prognostic Stratification in HCC. Liver International. https://doi.org/10.1111/liv.16205

Vancouver

Zheng T, Zhu Y, Jiang H, Yang C, Ye Y, Bashir MR, et al. MRI ‐Based Topology Deep Learning Model for Noninvasive Prediction of Microvascular Invasion and Assisting Prognostic Stratification in HCC. Liver International. 2025. doi:10.1111/liv.16205

BibTeX
@article{Zheng2025,
  author = {Zheng, Tianying and Zhu, Yajing and Jiang, Hanyu and Yang, Chongtu and Ye, Yuxiang and Bashir, Mustafa R and Li, Chenhui and Long, Liling and Luo, Shishi and Song, Bin and Chen, Yinan and Chen, Yidi},
  title = {MRI ‐Based Topology Deep Learning Model for Noninvasive Prediction of Microvascular Invasion and Assisting Prognostic Stratification in HCC},
  journal = {Liver International},
  year = {2025},
  doi = {10.1111/liv.16205}
}
Kostenlos starten →