Introduction to the IBSI

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 high-throughput quantitative image analysis 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 image biomarker nomenclature and definitions, benchmark data sets, and benchmark values to verify image processing and image biomarker calculations, as well as reporting guidelines, for high-throughput image analysis.

IBSI Chapter 1 − COMPLETED!

Chapter 1 of the IBSI (a.k.a. IBSI 1) is dedicated to the standardisation of commonly used radiomic features. IBSI 1 was initiated in September 2016, and it reached completion in March 2020 with the publication of the first IBSI article in the Radiology journal. IBSI 1 consisted of three phases:

IBSI 1 − Phase 1: standardisation of radiomic feature computations using a digital phantom (no image processing).
IBSI 1 − Phase 2: standardisation of radiomic feature computations under a general image processing scheme using CT data of a lung cancer patient.
IBSI 1 − Phase 3: validation of benchmarked processes from previous phases using a multi-modality imaging dataset of multiple patients.

From that work, the IBSI established reference values for 169 commonly used features, created a standard radiomics image processing scheme, and developed reporting guidelines for radiomic studies. Other researchers can now use the reference values and standardised radiomic computation workflow established by the IBSI 1 to calibrate their own software. Please follow the instructions in the IBSI 1 tab of this website for that purpose.

IBSI Chapter 2 − COMPLETED!

Chapter 2 of the IBSI (a.k.a. IBSI 2) is dedicated to the standardisation of commonly used imaging filters in radiomic studies. Specifically, we address the computation of several convolutional filters in the radiomics workflow (e.g. wavelets, Laplacian of Gaussian, etc.), which can play an important part in highlighting specific image characteristics. IBSI 2 was launched in June 2020 and similarly to IBSI 1, it is divided in three phases:

IBSI 2 − Phase 1: technical validation of image filters without additional image processing using digital phantoms.
IBSI 2 − Phase 2: establishing radiomic reference values for features obtained from filter response maps using CT data of a lung cancer patient.
IBSI 2 − Phase 3: validating the reproducibility of radiomic features obtained from filter response maps using a multi-modality imaging dataset of multiple patients.

IBSI 2 finished February 2024 with the publication of its results in Radiology. For more information see the IBSI 2 tab of this website.

IBSI Google Group Forum

All participants are welcome to visit the IBSI's Google Group Forum to start any discussion topic about the IBSI.