The image biomarker standardisation initiative¶
The image biomarker standardisation initiative (IBSI) is an independent international collaboration which works towards standardising the extraction of image biomarkers from acquired imaging for the purpose of high-throughput quantitative image analysis (radiomics). Lack of reproducibility and validation of radiomic studies is considered to be a major challenge for the field. Part of this challenge lies in the scantiness of consensus-based guidelines and definitions for the process of translating acquired imaging into high-throughput image biomarkers. The IBSI therefore seeks to provide standardised image biomarker nomenclature and definitions, a standardised general image processing workflow, tools for verifying radiomics software implementations and reporting guidelines for radiomic studies.
Permanent identifiers¶
The IBSI uses permanent identifiers for image biomarker definitions and important related concepts such as image processing. These consist of four-character codes and may be used for reference. Please do not use page numbers or section numbers as references, as these are subject to change.
Copyright¶
This work is a copy-edited version of the final (v10) pre-print version of the IBSI reference manual, which was licensed under the Creative Commons Attribution 4.0 International License (CC-BY). The original work may be cited as: [redacted]
Copyright information regarding the benchmark data sets may be found on GitHub: https://github.com/theibsi/data_sets
Contents¶
- Introduction
- Image processing
- Image features
- Grid distances
- Feature aggregation
- Distance weighting
- Morphological features
- Mesh-based representation
- ROI morphological and intensity masks
- Aggregating features
- Units of measurement
- Local intensity features
- Aggregating features
- Intensity-based statistical features
- Aggregating features
- Intensity histogram features
- Aggregating features
- Intensity-volume histogram features
- Discrete calibrated image intensities
- Continuous calibrated image intensities
- Arbitrary intensity units
- Calculating the IV histogram
- Aggregating features
- Grey level co-occurrence based features
- Aggregating features
- Distances and distance weighting
- Grey level run length based features
- Aggregating features
- Distance weighting
- Grey level size zone based features
- Aggregating features
- Distances
- Note on feature references
- Grey level distance zone based features
- Morphological and intensity masks.
- Aggregating features
- Distances
- Note on feature references
- Neighbourhood grey tone difference based features
- Aggregating features
- Distances and distance weighting
- Neighbouring grey level dependence based features
- Aggregating features
- Distances and distance weighting
- Note on feature references
- Radiomics reporting guidelines and nomenclature
- Reference data sets
- Digital phantom texture matrices
- Grey level co-occurrence matrix (2D)
- Grey level co-occurrence matrix (2D, merged)
- Grey level co-occurrence matrix (3D)
- Grey level co-occurrence matrix (3D, merged)
- Grey level run length matrix (2D)
- Grey level run length matrix (2D, merged)
- Grey level run length matrix (3D)
- Grey level run length matrix (3D, merged)
- Grey level size zone matrix (2D)
- Grey level size zone matrix (3D)
- Grey level distance zone matrix (2D)
- Grey level distance zone matrix (3D)
- Neighbourhood grey tone difference matrix (2D)
- Neighbourhood grey tone difference matrix (3D)
- Neighbouring grey level dependence matrix (2D)
- Neighbouring grey level dependence matrix (3D)
- References