EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MRI-based 2.5D deep learning and radiomics effectively predicted microvascular invasion and Ki-67 expression in hepatocellular carcinoma

Hongmei Yu iD, Depeng Kong, Xiaojun Mo, Ju Huang, Jie Wu, Yang Wang, Feizhou Du iD

PLOS One · 14.11.2025 · 20 (11) · e0336579

DOI: 10.1371/journal.pone.0336579 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 14.11.2025. Verfasst von Hongmei Yu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Chinese People's Liberation the General Hospital of Western Theater Command, Chengdu, China. Hauptthemen laut MEDLINE: Carcinoma, Hepatocellular, Liver Neoplasms, Deep Learning, Magnetic Resonance Imaging. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Foundation of General Hospital of Western Theater Command.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To develop and validate an integrated 2.5D deep learning (DL) and Radiomics model using gadoxetic acid-enhanced MRI hepatobiliary phase (HBP) images combined with clinical features for preoperative prediction of microvascular invasion (MVI) and high Ki-67 expression (>20%) dual positivity in hepatocellular carcinoma (HCC).

Methods

This retrospective study included 235 pathologically confirmed HCC patients categorized as MVI/Ki-67 double-positive (n = 129) or non-double-positive (n = 106). Clinical data (tumor diameter, AFP, GGT, differentiation grade, etc.) and HBP MRI images were collected. Tumor ROIs were segmented on HBP images. A 2.5D DL approach utilized axial, sagittal, and coronal planes of the largest tumor cross-section. LASSO regression selected key features from clinical, radiomic, and DL feature sets. Multivariate logistic regression identified independent predictors, and a nomogram was built. Model performance was evaluated via ROC curves, calibration plots, DCA, confusion matrices, and waterfall plots. Assessment of early recurrence within 2 years after HCC surgery was performed using alpha-fetoprotein (AFP) levels and imaging examinations.

Results

Significant intergroup differences existed in tumor diameter, AFP, GGT, and differentiation grade ( P < 0.05). LASSO selected 38 key features (7 clinical, 23 DL, 8 radiomic). Multivariate analysis confirmed the derived clinical feature score, DL_Radscore, and radiomics Radscore as independent predictors of dual positivity. The integrated nomogram model (combining 2.5D DL, radiomics, and clinical features) achieved optimal prediction performance: AUROC, sensitivity, specificity, precision, accuracy, and F1-score values of 0.939, 0.793, 0.940, 0.942, 0.859, and 0.861, respectively.Calibration curves demonstrated good agreement, and DCA indicated clinical utility. Furthermore, postoperative follow-up confirmed that the MVI/Ki-67 dual-positive group exhibited a significantly higher early recurrence rate compared to the non-dual-positive group ( P < 0.05).

Conclusion

The integrated MRI 2.5D DL model synergizing radiomics and clinical features surpasses single-modality models for preoperative prediction of MVI/Ki-67 dual positivity in HCC. This tool shows strong potential for enhancing HCC risk stratification and guiding personalized treatment planning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carcinoma, HepatocellularLiver NeoplasmsDeep LearningMagnetic Resonance ImagingKi-67 AntigenMicrovesselsHumansMaleFemaleMiddle AgedRetrospective StudiesAgedNeoplasm InvasivenessAdultNomogramsRadiomics

Substanzen

Ki-67 Antigen

Autor:innen und Institutionen

  • Department of Radiology, Chinese People's Liberation the General Hospital of Western Theater Command, Chengdu, China.
  • Department of Medical Equipment, The Second Affiliated Hospital of Chengdu Medical College, Nuclear Industry 416 Hospital, Chengdu, China.

ORCID-Profile: Hongmei Yu, Feizhou Du

Förderung

  • Foundation of General Hospital of Western Theater Command

Zitieren

APA

Yu, H., Kong, D., Mo, X., Huang, J., Wu, J., Wang, Y., & Du, F. (2025). MRI-based 2.5D deep learning and radiomics effectively predicted microvascular invasion and Ki-67 expression in hepatocellular carcinoma. PLOS One, 20(11), e0336579. https://doi.org/10.1371/journal.pone.0336579

Vancouver

Yu H, Kong D, Mo X, Huang J, Wu J, Wang Y, et al. MRI-based 2.5D deep learning and radiomics effectively predicted microvascular invasion and Ki-67 expression in hepatocellular carcinoma. PLOS One. 2025;20(11):e0336579. doi:10.1371/journal.pone.0336579

BibTeX
@article{Yu2025,
  author = {Yu, Hongmei and Kong, Depeng and Mo, Xiaojun and Huang, Ju and Wu, Jie and Wang, Yang and Du, Feizhou},
  title = {MRI-based 2.5D deep learning and radiomics effectively predicted microvascular invasion and Ki-67 expression in hepatocellular carcinoma},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {11},
  pages = {e0336579},
  doi = {10.1371/journal.pone.0336579}
}
Kostenlos starten →