Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 10, 2025DiagnosticsOpen Access

Multi-Task Deep Learning on MRI for Tumor Segmentation and Treatment Response Prediction in an Experimental Model of Hepatocellular Carcinoma

View Full Paper
Ask AI
Bookmark
Share

Authors

GYGuangbo YuZZZigeng ZhangZZZigeng Zhang

Discussion

Loading...

Member takes

Overview

Multi-task deep learning demonstrates accurate tumor segmentation and predicts outcomes in HCC, suggesting better therapeutic evaluation methods.

Key Points

  • The research aims to enhance tumor segmentation and predict treatment responses using deep learning and MRI in hepatocellular carcinoma.
  • Developed a multi-task deep learning model for tumor segmentation and treatment response prediction.
  • Utilized an experimental model of HCC in rats with various treatment groups.
  • Implemented weekly multi-parametric MRI scans and U-Net++ architecture for analysis.
  • Achieved high precision in tumor segmentation with a Dice coefficient of 0.92 and IoU of 0.86.
  • Model predicted therapeutic outcomes with an AUROC of 0.97 and 85% accuracy.
  • Strong correlation between MRI-derived biomarkers and histological markers of viability and apoptosis.

Cite This Study

Yu et al. (2025) studied this question.

synapsesocial.com/papers/69253a1ec0ce034ddc35702chttps://doi.org/10.3390/diagnostics15222844
View Full Paper
Ask AI
Bookmark
Share