Pre-treatment CEMRI habitat radiomics and deep learning for noninvasive prediction of the VETC pattern in hepatocellular carcinoma: an exploratory radiogenomic analysis - Scorecard - MDSpire
Advertisement
Pre-treatment CEMRI habitat radiomics and deep learning for noninvasive prediction of the VETC pattern in hepatocellular carcinoma: an exploratory radiogenomic analysis
Clinical Scorecard: Noninvasive Prediction of Vessels Encapsulating Tumor Clusters in Hepatocellular Carcinoma Using Pre-treatment Contrast-Enhanced MRI Radiomics and Deep Learning: An Exploratory Radiogenomic Study
At a Glance
Category
Detail
Condition
Hepatocellular Carcinoma (HCC)
Key Mechanisms
Vessels encapsulating tumor clusters (VETC) linked to aggressive tumor behavior and immune evasion.
Target Population
Patients with histologically confirmed HCC.
Care Setting
Clinical decision-making for HCC treatment planning.
Key Highlights
CEMRI-based fusion model achieved AUCs of 0.901 and 0.870 for predicting VETC.
Differential gene expression analysis revealed significant differences between high- and low-risk groups.
Immune profiling indicated reduced resting dendritic cells in the high-risk group.
Guideline-Based Recommendations
Diagnosis
Pathological biopsy remains the gold standard for diagnosing VETC.
Management
Accurate recognition of VETC-positive tumors is essential for surgical margin assessment and planning of adjuvant therapies.
Monitoring & Follow-up
Risks
High recurrence rate and poor prognosis associated with VETC in HCC.
Patient & Prescribing Data
336 patients with HCC analyzed in the study.
Noninvasive prediction of VETC can optimize clinical decision-making.
Clinical Best Practices
Utilize CEMRI for assessing intratumoral heterogeneity in HCC.
Incorporate radiomics and deep learning features for enhanced predictive capability.
