AUTHOR=Thrussell Imogen , Winfield Jessica M. , Orton Matthew R. , Miah Aisha B. , Zaidi Shane H. , Arthur Amani , Thway Khin , Strauss Dirk C. , Collins David J. , Koh Dow-Mu , Oelfke Uwe , Huang Paul H. , O’Connor James P. B. , Messiou Christina , Blackledge Matthew D. 

TITLE=Radiomic Features From Diffusion-Weighted MRI of Retroperitoneal Soft-Tissue Sarcomas Are Repeatable and Exhibit Change After Radiotherapy

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.899180

DOI=10.3389/fonc.2022.899180

ISSN=2234-943X

ABSTRACT=Background
Size-based assessments are inaccurate indicators of tumour response in soft-tissue sarcoma (STS), motivating the requirement for new response imaging biomarkers for this rare and heterogeneous disease. In this study we assess the test-retest repeatability of radiomic features from MR diffusion-weighted imaging (DWI) and derived maps of apparent diffusion coefficient (ADC) in retroperitoneal STS and compare baseline repeatability with changes in radiomic features following radiotherapy (RT). 
Materials and Methods
Thirty patients with retroperitoneal STS received an MR examination prior to treatment, of whom 23/30 were investigated in our repeatability analysis having received repeat baseline examinations, and 14/30 patients were investigated in our post-treatment analysis having received an MR examination after completing pre-operative RT. 107 radiomic features were extracted from the full manually delineated tumour region using PyRadiomics. Test-retest repeatability was assessed using an intraclass correlation coefficient (baseline-ICC), and a post-radiotherapy variance analysis (postRT-IMS) was used to compare the change in radiomic feature value to baseline repeatability.  
Results
For the ADC maps and DWI images respectively, 101 and 102 features demonstrated good baseline repeatability (baseline-ICC > 0.85) alone. 43 and 2 features respectively demonstrated both good baseline repeatability and a high postRT-IMS (> 0.85). Pearson correlation between the baseline-ICC and postRT-IMS was weak (0.432 and 0.133 respectively).
Conclusions
ADC-based radiomic analysis shows better test-retest repeatability compared with features derived from DWI images in STS, and some of these features are sensitive to post-treatment change. However, good repeatability at baseline does not imply sensitivity to post-treatment change. 
(ClinicalTrials.gov, NCT01902667).