± HEALTH In our modern society, digital devices, social media platforms, and artificial intelligence (AI) tools have b…+ CLIMATE The growing complexity of electric vehicle charging station (EVCS) operations—driven by grid constraints, ren…± HEALTH Objectives This study aim to develop, compare and internally validate machine-learning models for predicting…+ HEALTH Diabetes management faces a number of obstacles, such as fragmented healthcare data, privacy concerns, poor e…− SCIENCE Background Craniofacial soft tissue thickness (CFSTT) is a critical parameter in forensic facial reconstructi…+ HEALTH Background Technological innovation in total joint arthroplasty (TJA) has largely focused on intraoperative p…± HEALTH Infective endocarditis (IE) continues to be an often fatal condition despite improvements in cardiac surgical…± HEALTH Purpose of review Systemic sclerosis-associated interstitial lung disease (SSc-ILD) is the leading cause of d…
TruaceTracing the truth around AIFriday, September 11, 2026
Subscribe
Health·G Space·Evidence-backed gain·Published 2026-09-06

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

TRV-2026-0992Peer-reviewedPermanent record — 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

The quick read

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.

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
  • Multicenter study enrolled 496 patients with solitary HCC  5 cm, mean age 58 7 10 years, 376 men.
  • 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.
  • 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.
  • RSF model with clinical parameters and 2PI achieved C-index 0.76 training, 0.69 internal test, and 0.68 external test.
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

Reader signal

How should this claim be treated?

The debate