Data Sheet 1_A combined radiomics and habitat analysis model for predicting early recurren

A retrospective cohort of 140 hepatocellular carcinoma (HCC) patients was used to develop a predictive model. The model combines radiomics and habitat analysis from arterial-phase CECT images and clinical data. The dataset was authored by Ya Yang and last updated on 2026-05-26.

Use Cases

• Predicting early recurrence of hepatocellular carcinoma after liver transplantation based on radiomic features.
• Comparing the performance of combined radiomics-habitat models against clinical-only models.
• Identifying high-risk HCC patients for personalized follow-up strategies based on imaging-derived habitat analysis.

Strengths

• Model performance is quantified with specific metrics: AUC of 0.929 in training and 0.882 in testing cohorts.
• Dataset size is explicitly stated as 140 HCC patient records.
• Model validation includes ROC curves, calibration curves, and decision curve analysis.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data may reflect temporal or institutional bias inherent to the single retrospective cohort from figshare.

Provenance

Source

figshare, author Ya Yang.

Collection Method

Retrospective cohort study using arterial-phase CECT images and clinical data for ROI segmentation and feature extraction.

Freshness

Last updated 2026-05-26 04:39:16; freshness should be verified.