Truace
Subscribe

CT-based scoring system helps predict liver cancer return after surgery in 496 patients

Study title: A CECT-Based 2PI System as a Novel Noninvasive Prognostic Tool for Hepatocellular Carcinoma: A Dual-Validation Study

Researchers developed a CECT-based 2PI system that scores imaging features associated with pathological markers and combined it with clinical parameters in machine learning models to predict postoperative recurrence in solitary HCC  5 cm. In 496 patients across primary and external centers, a threshold of  stratified high- versus low-risk groups.

Read the study abstract

This study aimed to develop and validate machine learning (ML) models integrating clinical parameters and the 2PI system (Pathology and Prognosis-Informed Imaging System) for predicting postoperative recurrence risk in hepatocellular carcinoma (HCC). The multicenter retrospective study included 496 patients with solitary HCC (≤ 5 cm). Surgical resection (SR) patients from the primary center constituted the training set; radiofrequency ablation (RFA) patients from the same center formed the internal test set; and…

By the Truvace desk1 min read1 sourceEvidence: Moderate · 60/100 — Observational study · n = 496 · 1 independent sourcePeer-reviewedTRV-2026-0992· cite & verify
A CECT-Based 2PI System as a Novel Noninvasive Prognostic Tool for Hepatocellular Carcinoma: A Dual-Validation Study
Tumors of the liver and intrahepatic bile ducts by Craig, John Redfernd, 1943- Peters, Robert L., 1927- Edmondson, Hugh A., 1906- Armed Forces Institute of Pathology (U.S.). Public domain

In brief

By publication date 2026-09-05, the RSF model showed favorable but decreasing discrimination from training to external validation, suggesting potential as a noninvasive prognostic tool. Whether the score changes treatment decisions, improves survival, or generalizes beyond small solitary tumors and retrospective cohorts remains unproven.

Main points

  1. Multicenter study enrolled 496 patients with solitary HCC  5 cm, mean age 58 7 10 years, 376 men.
  2. Training set was surgical resection patients from primary center; internal test was radiofrequency ablation patients from same center; external test was surgical resection patients from other centers.
  3. Seven imaging features associated with pathological markers were identified by multivariable logistic regression and weighted by odds ratios and Kendall's tau-b to build the 2PI system.
  4. RSF model with clinical parameters and 2PI achieved C-index 0.76 training, 0.69 internal test, and 0.68 external test.

The gain

A CECT-based 2PI imaging scoring system combined with clinical parameters enabled a Random Survival Forest model to stratify solitary HCC patients into high- and low-risk recurrence groups and predict postoperative recurrence.

The rundown

The authors built a dual-information pathway 2PI system using seven CECT imaging features linked to pathology, weighting them by exp(b) odds ratios and Kendall's tau-b association with recurrence. A threshold of  separated high- and low-risk groups.

Validation used three cohorts from 496 patients: SR training at primary center, RFA internal test at same center, and SR external test at other centers. The RSF model integrating clinical parameters and 2PI reported C-index 0.76 [95% CI: 0.72-0.80] training, 0.69 [95% CI: 0.63-0.75] internal, and 0.68 [95% CI: 0.57-0.79] external.

Sources

  1. Peer-reviewedCancer Science2026-09-05

The debate