Integrated multi-task learning framework for hepatocellular carcinoma segmentation and histological grading using fused multi-phase MRI.
Objective: This study aims to develop and validate an integrated multi-task framework for hepatocellular carcinoma analysis by combining deep learning-based segmentation with radiomics-based histological grading using fused multi-phase MRI. Materials and methods: In this retrospective study, MRI dat...
| Publicado en: | Abdominal Radiology Vol. 51; no. 5; pp. 2439 - 2461 |
|---|---|
| Autores principales: | , , |
| Formato: | Journal Article |
| Publicado: |
Springer Nature
May2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=194809206&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 194809206 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 2366004X JT14 jtl: Abdominal Radiology issn: 2366004X maglogo: N pubinfo: dt: May2026 vid: 51 iid: 5 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 194809206 188941564 10.1007/s00261-025-05266-3 194809206 ppf: 2439 ppct: 22 formats: tig: atl: Integrated multi-task learning framework for hepatocellular carcinoma segmentation and histological grading using fused multi-phase MRI. aug: au: You, Zhihui Wang, Yuanru Zhou, Shili affil: https://ror.org/03mqfn238 The Second Affiliated Hospital, Department of Ultrasonography, Hengyang Medical School, University of South China, Hengyang, China sug: ab: Objective: This study aims to develop and validate an integrated multi-task framework for hepatocellular carcinoma analysis by combining deep learning-based segmentation with radiomics-based histological grading using fused multi-phase MRI. Materials and methods: In this retrospective study, MRI data from 1673 patients with histopathologically confirmed hepatocellular carcinoma (875 high-grade, 798 low-grade) were analyzed. Arterial-phase and portal-venous-phase T1-weighted images were acquired using a standardized, bolus-tracking protocol to ensure consistent contrast timing. Six segmentation models, Vision Transformer, nnU-Net, U-Net, DeepLabV3+, Swin Transformer, and SegNet, were trained on arterial, portal-venous, and fused (wavelet-based) MRI data. Radiomic features (n = 215) were extracted from segmented tumor volumes and pre-filtered to remove multicollinearity. Feature refinement was performed using Lasso, Recursive Feature Elimination (RFE), and ANOVA. Tumor grade classification was conducted using TabTransformer, TabNet, XGBoost, and CatBoost. Five-fold cross-validation and an independent test set were used for robust evaluation. Standardized preprocessing, including intensity normalization, bias field correction, and inter-phase registration, ensured consistent image quality and analytical reproducibility. Results: The proposed framework achieved high segmentation accuracy with DSC scores above 0.92 across fused MRI images. Classification performance was exceptional, with training accuracy reaching 93.2% and testing accuracy 92.5%, while AUC values exceeded 96% in the fused modality. Comparative analyses revealed that the Transformer-RFE-Fused model outperformed alternative architectures, demonstrating superior generalization and robust feature learning. In addition, SHAP analysis confirmed the high contribution of key radiomic features, and t-SNE visualizations illustrated clear separation between low-grade and high-grade tumors. These results validate the efficacy of our multi-task learning approach in enhancing HCC tumor segmentation and grading. Our evaluation underscores the clinical potential of our integrated framework for accurate, reproducible, and interpretable HCC diagnosis. Conclusions: Our integrated multi-task learning framework markedly improves HCC tumor segmentation and grading. Transformer-RFE-Fused (Wavelet) MRI offers superior accuracy and robustness, efficiently paving the way for enhanced clinical decision-making. pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|