Assessment of Stability and Discrimination Capacity of Radiomic Features on Apparent Diffusion Coefficient Images

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

The objectives of the study are to develop a new way to assess stability and discrimination capacity of radiomic features without the need of test-retest or multiple delineations and to use information obtained to perform a preliminary feature selection. Apparent diffusion coefficient (ADC) maps were computed from diffusion-weighted magnetic resonance images (DW-MRI) of two groups of patients: 18 with soft tissue sarcomas (STS) and 18 with oropharyngeal cancers (OPC). Sixty-nine radiomic features were computed, using three different histogram discretizations (16, 32, and 64 bins). Geometrical transformations (translations) of increasing entity were applied to the regions of interest (ROIs), and the intra-class correlation coefficient (ICC) was used to compare the features computed on the original and modified ROIs. The distribution of ICC values for minimal and maximal entity translations (ICC ₁₀ and ICC ₁₀₀, respectively) was used to adjust thresholds of ICC (ICC _min and ICC _max) used to discriminate between good, unstable (ICC ₁₀ < ICC _min), and non-discriminative features (ICC ₁₀₀ > ICC _max). Fifty-four and 59 radiomic features passed the stability-based selection for all the three histogram discretizations for the OPC and STS datasets, respectively. The excluded features were similar across the different histogram discretizations (Jaccard’s index 0.77 ± 0.13 and 0.9 ± 0.1 for OPC and STS, respectively) but different between datasets (Jaccard’s index 0.19 ± 0.02). The results suggest that the observed radiomic features are mainly stable and discriminative, but the stability depends on the region of the body under observation. The method provides a way to assess stability without the need of test-retest or multiple delineations.

Electronic supplementary material

The online version of this article (10.1007/s10278-018-0092-9) contains supplementary material, which is available to authorized users.

Related collections

Most cited references 29

Record: found
Abstract: found
Article: not found

Diffusion-weighted magnetic resonance imaging as a cancer biomarker: consensus and recommendations.

Anwar Padhani, Guoying Liu, Dow Koh … (2009)

On May 3, 2008, a National Cancer Institute (NCI)-sponsored open consensus conference was held in Toronto, Ontario, Canada, during the 2008 International Society for Magnetic Resonance in Medicine Meeting. Approximately 100 experts and stakeholders summarized the current understanding of diffusion-weighted magnetic resonance imaging (DW-MRI) and reached consensus on the use of DW-MRI as a cancer imaging biomarker. DW-MRI should be tested as an imaging biomarker in the context of well-defined clinical trials, by adding DW-MRI to existing NCI-sponsored trials, particularly those with tissue sampling or survival indicators. Where possible, DW-MRI measurements should be compared with histologic indices including cellularity and tissue response. There is a need for tissue equivalent diffusivity phantoms; meanwhile, simple fluid-filled phantoms should be used. Monoexponential assessments of apparent diffusion coefficient values should use two b values (>100 and between 500 and 1000 mm2/sec depending on the application). Free breathing with multiple acquisitions is superior to complex gating techniques. Baseline patient reproducibility studies should be part of study designs. Both region of interest and histogram analysis of apparent diffusion coefficient measurements should be obtained. Standards for measurement, analysis, and display are needed. Annotated data from validation studies (along with outcome measures) should be made publicly available. Magnetic resonance imaging vendors should be engaged in this process. The NCI should establish a task force of experts (physicists, radiologists, and oncologists) to plan, organize technical aspects, and conduct pilot trials. The American College of Radiology Imaging Network infrastructure may be suitable for these purposes. There is an extraordinary opportunity for DW-MRI to evolve into a clinically valuable imaging tool, potentially important for drug development.

0 comments Cited 360 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Measuring Computed Tomography Scanner Variability of Radiomics Features.

Dennis Mackin, Xenia Fave, Lifei Zhang … (2015)

The purpose of this study was to determine the significance of interscanner variability in CT image radiomics studies.

0 comments Cited 248 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: found

Is Open Access

The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis

Ralph Leijenaar, Georgi Nalbantov, Sara Carvalho … (2015)

FDG-PET-derived textural features describing intra-tumor heterogeneity are increasingly investigated as imaging biomarkers. As part of the process of quantifying heterogeneity, image intensities (SUVs) are typically resampled into a reduced number of discrete bins. We focused on the implications of the manner in which this discretization is implemented. Two methods were evaluated: (1) RD, dividing the SUV range into D equally spaced bins, where the intensity resolution (i.e. bin size) varies per image; and (2) RB, maintaining a constant intensity resolution B. Clinical feasibility was assessed on 35 lung cancer patients, imaged before and in the second week of radiotherapy. Forty-four textural features were determined for different D and B for both imaging time points. Feature values depended on the intensity resolution and out of both assessed methods, RB was shown to allow for a meaningful inter- and intra-patient comparison of feature values. Overall, patients ranked differently according to feature values–which was used as a surrogate for textural feature interpretation–between both discretization methods. Our study shows that the manner of SUV discretization has a crucial effect on the resulting textural features and the interpretation thereof, emphasizing the importance of standardized methodology in tumor texture analysis.

0 comments Cited 158 times – based on 0 reviews      Review now

Bookmark

All references

Author and article information

Contributors

Marco Bologna: +39 0223993322 , marco.bologna@polimi.it

Journal

Journal ID (nlm-ta): J Digit Imaging

Journal ID (iso-abbrev): J Digit Imaging

Title: Journal of Digital Imaging

Publisher: Springer International Publishing (Cham )

ISSN (Print): 0897-1889

ISSN (Electronic): 1618-727X

Publication date (Electronic): 3 May 2018

Publication date PMC-release: 3 May 2018

Publication date (Print): December 2018

Volume: 31

Issue: 6

Pages: 879-894

Affiliations

[1 ]Departement of Electronics, Information and Bioengineering, Milan, Italy

[2 ]ISNI 0000 0001 0807 2568, GRID grid.417893.0, Fondazione IRCCS Istituto Nazionale dei Tumori, ; Milan, Italy

Article

Publisher ID: 92

DOI: 10.1007/s10278-018-0092-9

PMC ID: 6261192

PubMed ID: 29725965

SO-VID: fd9d0f75-fc3c-43d9-9bfa-5a6657c08840

License:

Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

History

Funding

Funded by: FundRef http://dx.doi.org/10.13039/501100007601, Horizon 2020;

Award ID: 689715

Award Recipient : Valentina D. A. Corino

Custom metadata

ScienceOpen disciplines: Radiology & Imaging

Keywords: apparent diffusion coefficient maps,radiomics,radiomic features stability,magnetic resonance imaging,intra-class correlation coefficient

Data availability:

ScienceOpen disciplines: Radiology & Imaging

Keywords: apparent diffusion coefficient maps, radiomics, radiomic features stability, magnetic resonance imaging, intra-class correlation coefficient

Assessment of Stability and Discrimination Capacity of Radiomic Features on Apparent Diffusion Coefficient Images

Read this article at

Abstract

Electronic supplementary material

Related collections

Stroke MRI

Most cited references 29

Diffusion-weighted magnetic resonance imaging as a cancer biomarker: consensus and recommendations.

Measuring Computed Tomography Scanner Variability of Radiomics Features.

The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis

Author and article information

Contributors

Journal

Affiliations

Article

History

Funding

Categories

Custom metadata

Comments

Comment on this article

Similar content 109

Cited by 24

Most referenced authors 646