Artificial Intelligence and Radiomics for Differentiating Pseudoprogression from True Progression in High-Grade Gliomas: A Systematic Review and Meta-Analysis

Read full text Summarise with VIRAT
Authors: G Facchinetti, Nicola Pagani, Francesco Ponzio, Lucio De Maria
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Differentiating true progression (TP) from pseudoprogression (PsP) in high-grade gliomas (HGGs) on MRI is a critical clinical challenge. This meta-analysis evaluates the overall diagnostic accuracy of radiomics and artificial intelligence (AI) models to identify algorithmic determinants of optimal performance. A PRISMA-compliant search of PubMed, Ovid MEDLINE, and EMBASE (up to 2025) was conducted. Quality was assessed via QUADAS-2. Diagnostic metrics were pooled utilizing bivariate random-effects models and Summary Receiver Operating Characteristic (SROC) curves. Across 34 included studies, the overall pooled sensitivity and specificity were 82% and 79%, respectively. Shape-based and Deep Learning (DL) features achieved the highest Area Under the Curve (up to 0.96 and 0.95). First-order statistics and Gray-Level Co-occurrence Matrix (GLCM) yielded the highest consistency and accuracy peaks (up to 98%). Multiparametric MRI was the most robust and widely used imaging modality. Radiomics demonstrates high, reliable diagnostic potential for discriminating HGG PsP from TP. While advanced DL models and shape features maximize discriminative performance, classical handcrafted features remain the most extensively validated. Future studies must prioritize independent external validation, federated learning (FL), and Explainable AI (XAI) for clinical translation.

Fields of Study & Subjects

Radiomics and Machine Learning in Medical Imaging Glioma Diagnosis and Treatment Brain Tumor Detection and Classification

Publication details

Publication date
25 March 2026
Language
EN
Document type
Preprint