The application of a workflow integrating the variable reproducibility and harmonizability of radiomic features on a phantom dataset

PLoS ONE, vol. 16, pp. e0251147

Abstract

Radiomics-the high throughput extraction of quantitative features from medical images and their correlation with clinical and biological endpoints- is the subject of active and extensive research. Although the field shows promise, the generalizability of radiomic signatures is affected significantly by differences in scan acquisition and reconstruction settings. Previous studies reported on the sensitivity of radiomic features (RFs) to test-retest variability, inter-observer segmentation variability, and intra-scanner variability. A framework involving robust radiomics analysis and the application of a post-reconstruction feature harmonization method using ComBat was recently proposed to address these challenges. In this study, we investigated the reproducibility of RFs across different scanners and scanning parameters using this framework. We analysed thirteen scans of a ten-layer phantom that were acquired differently. Each layer was subdivided into sixteen regions of interest (ROIs), and the scans were compared in a pairwise manner, resulting in seventy-eight different scenarios. Ninety-one RFs were extracted from each ROI. As hypothesized, we demonstrate that the reproducibility of a given RF is not a constant but is dependent on the heterogeneity found in the data under analysis. The number (%) of reproducible RFs varied across the pairwise scenarios investigated, having a wide range between 8 (8.8%) and 78 (85.7%) RFs. Furthermore, in contrast to what has been previously reported, and as hypothesized in the robust radiomics analysis framework, our results demonstrate that ComBat cannot be applied to all RFs but rather on a percentage of those-the "ComBatable" RFs-which differed depending on the data being harmonized. The number (%) of reproducible RFs following ComBat harmonization varied across the pairwise scenarios investigated, ranging from 14 (15.4%) to 80 (87.9%) RFs, and was found to depend on the heterogeneity in the data. We conclude that the standardization of image acquisition protocols remains the cornerstone for improving the reproducibility of RFs, and the generalizability of the signatures developed. Our proposed approach helps identify the reproducible RFs across different datasets.

Authors 9

1. Abdalla Ibrahim corresponding Aachen Department of Nuclear Medicine and Comprehensive diagnostic center Aachen (CDCA)

   University of Liège · Maastricht University Medical Centre · Maastricht University · Universitätsklinikum Aachen · Centre Hospitalier Universitaire de Liège · RWTH Aachen University

   Affiliation as printed

   Department of Nuclear Medicine and Comprehensive Diagnostic Centre Aachen (CDCA), University Hospital RWTH Aachen University, Aachen, Germany

   Department of Radiology and Nuclear Medicine, Maastricht University Medical Centre+, Maastricht, The Netherlands

   Division of Nuclear Medicine and Oncological Imaging, Department of Medical Physics, University Hospital of Liège and GIGA CRC-in vivo imaging, University of Liège, Liege, Belgium

   The D-Lab, Department of Precision Medicine, GROW- School for Oncology, Maastricht University, Maastricht, The Netherlands

2. Turkey Refaee

   Maastricht University · Jazan University

   Affiliation as printed

   Faculty of Applied Medical Sciences, Department of Diagnostic Radiology, Jazan University, Jazan, Saudi Arabia

   The D-Lab, Department of Precision Medicine, GROW- School for Oncology, Maastricht University, Maastricht, The Netherlands

3. Ralph T. H. Leijenaar
   Affiliation as printed

   Oncoradiomics SA, Liege, Belgium

4. Sergey P. Primakov Aachen Department of Nuclear Medicine and Comprehensive diagnostic center Aachen (CDCA)

   Maastricht University · Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   Department of Nuclear Medicine and Comprehensive Diagnostic Centre Aachen (CDCA), University Hospital RWTH Aachen University, Aachen, Germany

   The D-Lab, Department of Precision Medicine, GROW- School for Oncology, Maastricht University, Maastricht, The Netherlands

5. Roland Hustinx

   University of Liège · Centre Hospitalier Universitaire de Liège

   Affiliation as printed

   Division of Nuclear Medicine and Oncological Imaging, Department of Medical Physics, University Hospital of Liège and GIGA CRC-in vivo imaging, University of Liège, Liege, Belgium

6. Felix Manuel Mottaghy Aachen Department of Nuclear Medicine and Comprehensive diagnostic center Aachen (CDCA)

   Maastricht University Medical Centre · Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   Department of Nuclear Medicine and Comprehensive Diagnostic Centre Aachen (CDCA), University Hospital RWTH Aachen University, Aachen, Germany

   Department of Radiology and Nuclear Medicine, Maastricht University Medical Centre+, Maastricht, The Netherlands

7. Henry C. Woodruff

   Maastricht University Medical Centre · Maastricht University

   Affiliation as printed

   Department of Radiology and Nuclear Medicine, Maastricht University Medical Centre+, Maastricht, The Netherlands

   The D-Lab, Department of Precision Medicine, GROW- School for Oncology, Maastricht University, Maastricht, The Netherlands

8. Andrew D. A. Maidment

   University of Pennsylvania

   Affiliation as printed

   Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States of America

9. Philippe Lambin

   Maastricht University Medical Centre · Maastricht University

   Affiliation as printed

   Department of Radiology and Nuclear Medicine, Maastricht University Medical Centre+, Maastricht, The Netherlands

   The D-Lab, Department of Precision Medicine, GROW- School for Oncology, Maastricht University, Maastricht, The Netherlands