Standardization in Quantitative Imaging: A Multicenter Comparison of Radiomic Features from Different Software Packages on Digital Reference Objects and Patient Data Sets

Radiomic features are being increasingly studied for clinical applications. We aimed to assess the agreement among radiomic features when computed by several groups by using different software packages under very tightly controlled conditions, which included standardized feature definitions and common image data sets. Ten sites (9 from the NCI's Quantitative Imaging Network] positron emission tomography–computed tomography working group plus one site from outside that group) participated in this project. Nine common quantitative imaging features were selected for comparison including features that describe morphology, intensity, shape, and texture. The common image data sets were: three 3D digital reference objects (DROs) and 10 patient image scans from the Lung Image Database Consortium data set using a specific lesion in each scan. Each object (DRO or lesion) was accompanied by an already-defined volume of interest, from which the features were calculated. Feature values for each object (DRO or lesion) were reported. The coefficient of variation (CV), expressed as a percentage, was calculated across software packages for each feature on each object. Thirteen sets of results were obtained for the DROs and patient data sets. Five of the 9 features showed excellent agreement with CV < 1%; 1 feature had moderate agreement (CV < 10%), and 3 features had larger variations (CV ≥ 10%) even after attempts at harmonization of feature calculations. This work highlights the value of feature definition standardization as well as the need to further clarify definitions for some features.

MO-A-BRA-01: State of the Art in Quantitative Imaging in CT, PET and MRI

Diagnostic Imaging is evolving from a modality where the emphasis is on the acquisition and interpretation of image data by radiologists to one where imaging devices may be used as measurement devices that are able to produce quantitative results. Some examples of quantitative measured values are already in clinical practice, including coronary artery calcium scores from CT, Standard Uptake Values (SUV) in PET imaging and Diffusion Weighted Imaging (DWI) in MRI. Clinical and clinical research applications of quantitative anatomical and functional imaging biomarkers, including those focused on treatment assessment, have continued to dramatically expand. Studies at single centers have clearly demonstrated the potential of such applications. However, sources of bias and variance of quantitative imaging biomarkers have not previously been adequately investigated, thus limiting the implementation of robust methods to mitigate their effects. Therefore, when it comes to applications of such techniques across vendor platforms, centers, and time, challenges arise due to lack of standards, appropriate phantoms, and protocols. During the past few years, several quantitative imaging initiatives have been instigated. This symposium presentation will review selected applications of quantitative imaging biomarkers, illustrate some of the current challenges in broadening the use of such biomarkers, and discuss some of the current initiatives of various scientific and federal organizations that are focused on the standardization, qualification, and validation of quantitative imaging biomarkers.

LEARNING OBJECTIVES

1. Understand selected applications of quantitative imaging biomarkers. 2. Understand the factors that currently limit widespread acceptance and use of such quantitative imaging biomarkers, including sources of bias and variance. 3. Understand some of the current initiatives focused on the standardization, qualification, and validation of selected quantitative imaging biomarkers.

LEARNING OBJECTIVES

1. Understand selected applications of quantitative imaging biomarkers. 2. Understand the factors that currently limit widespread acceptance and use of such quantitative imaging biomarkers, including sources of bias and variance. 3. Understand some of the current initiatives focused on the standardization, qualification, and validation of selected quantitative imaging biomarkers.