Radiomics and the Image Biomarker Standardisation Initiative (IBSI): A Narrative Review Using a Six-Question Map and Implementation Framework for Reproducible Imaging Biomarkers
Open Access
- 24 October 2025
- journal article
- review article
- Published by Springer Nature in Cureus
- Vol. 17 (10) , e95335
Abstract
Radiomics can quantify image-derived tumor heterogeneity and support diagnosis, prognosis, and treatment assessment, yet adoption has been limited by poor reproducibility across scanners, protocols, and software. The Image Biomarker Standardisation Initiative (IBSI) was founded to harmonize feature definitions and preprocessing. This narrative review explains what IBSI standardizes, how it is implemented, and what clinicians need to know, using a six-question map (who, why, what, how, when, where) and an implementation framework linking standardized pipeline blocks to compliance tools. Targeted searches (PubMed/Google Scholar, 2010-2025) emphasized IBSI manuals, consensus statements, multicenter evaluations, and clinically oriented studies. Because this is a narrative review, no quantitative synthesis (meta-analysis or meta-regression) was performed; numerical examples (e.g., an entropy coefficient-of-variation illustration) are descriptive. IBSI specifies the mathematics of radiomic features and upstream steps (interpolation/re-segmentation, intensity discretization, convolutional filtering, and feature aggregation) and provides compliance resources (digital phantoms, benchmark values, validation checklists/portals). These measures improve cross-software agreement - especially for first-order and shape features - while clarifying residual variability in higher-order textures. IBSI complements QIBA (acquisition/reconstruction profiles) and DICOM (data/metadata standards) and is now embedded in widely used platforms (e.g., PyRadiomics, LIFEx), enabling more stable multicenter workflows and integration with machine-learning models. IBSI functions as a clinical quality infrastructure for radiomics. Adopting its standardized pipeline and compliance framework reduces inter-software variability, strengthens the generalizability of predictive and prognostic models, and supports regulatory readiness. Continued refinement of filters and texture metrics, together with transparent reporting and shared datasets, will further enhance reproducibility and clinical trust.Keywords
This publication has 47 references indexed in Scilit:
- Evaluating feature extraction reproducibility across image biomarker standardization initiative‐compliant radiomics platforms using a digital phantomJournal of Applied Clinical Medical Physics, 2025
- Can computed tomography findings and radiomics analysis of mediastinal lymph nodes differentiate between sarcoidosis and lymphoma?Clinical Radiology, 2024
- Benchmarking Various Radiomic Toolkit Features While Applying the Image Biomarker Standardization Initiative toward Clinical Translation of Radiomic AnalysisJournal of Digital Imaging, 2021
- Reliability and prognostic value of radiomic features are highly dependent on choice of feature extraction platformEuropean Radiology, 2020
- Stable and discriminating radiomic predictor of recurrence in early stage non-small cell lung cancer: Multi-site studyLung Cancer, 2020
- Effects of MRI image normalization techniques in prostate cancer radiomicsPhysica Medica, 2020
- Radiogenomics: bridging imaging and genomicsAbdominal Radiology, 2019
- A Deep Look Into the Future of Quantitative Imaging in Oncology: A Statement of Working Principles and Proposal for ChangeInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2018
- Technical Note: Extension of CERR for computational radiomics: A comprehensive MATLAB platform for reproducible radiomics researchMedical Physics, 2018
- Radiomics: Extracting more information from medical images using advanced feature analysisEuropean Journal of Cancer, 2012