Radiomics-Based Prediction of Ki-67 Index in Non-Small Cell Lung Cancer: A Meta-Analysis and Diagnostic Performance Evaluation
Code: G-1615
Authors: Fatemeh Safari Jahandideh ℗, Akram Farhadi, Ramin Shahidi *
Schedule: Not Scheduled!
Tag: Cancer Diagnosis & Treatment
Download: Download Poster
Abstract:
Abstract
Background and aims : Lung cancer is one of the leading causes of cancer-related mortality worldwide, with the Ki-67 index being a crucial biomarker for assessing tumor proliferation and aggressiveness. Radiomics, an emerging computational imaging technique, allows for the extraction of quantitative imaging features that may improve non-invasive tumor characterization. This study aims to systematically evaluate the diagnostic performance of radiomics in predicting Ki-67 index status in Non-Small Cell Lung Cancer (NSCLC) using computed tomography (CT) imaging. Method: A systematic review was conducted following PRISMA guidelines. Literature searches were performed in PubMed/MEDLINE, Embase, Scopus, and Web of Science databases up to April 19, 2024. Studies evaluating the predictive accuracy of CT-based radiomics models for Ki-67 index classification in NSCLC were included. The methodological quality of selected studies was assessed using QUADAS-2, Radiomics Quality Score (RQS), and METhodological RadiomICs Score (METRICS). Meta-analysis was performed using statistical tools in R software to determine pooled sensitivity, specificity, and diagnostic odds ratios. Results: A total of 10 studies, comprising 2,279 NSCLC patients, were included, with 9 studies analyzed quantitatively. The pooled sensitivity and specificity of radiomics-based models were 0.783 (95% CI: 0.732–0.827) and 0.796 (95% CI: 0.707–0.864) in training cohorts, and 0.803 (95% CI: 0.744–0.851) and 0.696 (95% CI: 0.613–0.768) in validation cohorts. Subgroup analysis revealed that segmentation software significantly impacted diagnostic accuracy, with ITK-SNAP achieving higher sensitivity. Conclusion: This systematic review and meta-analysis highlight the potential of radiomics as a promising non-invasive tool for predicting the Ki-67 index in NSCLC. The findings support the clinical utility of radiomics in personalized oncology, though further prospective studies with standardized methodologies are necessary to enhance its applicability in clinical settings.
Keywords
Lung Cancer, Ki-67 Index, Radiomics, CT
