Harmonization of radiomic feature distributions: impact on classification of hepatic tissue in CT imaging
Authors:
- 18 January 2021
- journal article
- research article
- Published by Springer Nature in European Radiology
- Vol. 31 (8) , 6059-6068
Abstract
Objectives Following the craze for radiomic features (RF), their lack of reliability raised the question of the generalizability of classification models. Inter-site harmonization of images therefore becomes a central issue. We compared RF harmonization processing designed to detect liver diseases in CT images. Methods We retrospectively analyzed 76 multi-center portal CT series of non-diseased (NDL) and diseased liver (DL) patients. In each series, we positioned volumes of interest in spleen and liver, then extracted 9 RF (histogram and texture). We evaluated two RF harmonization approaches. First, in each series, we computed the Z-score of liver measurements based on those computed in the spleen. Second, we evaluated the ComBat method according to each imaging center; parameters were computed in the spleen and applied to the liver. We compared RF distributions and classification performances before/after harmonization. We classified NDL versus spleen and versus DL tissues. Results The RF distributions were all different between liver and spleen (p < 0.05). The Z-score harmonization outperformed for the detection of liver versus spleen: AUC = 93.1% (p < 0.001). For the detection of DL versus NDL, in a case/control setting, we found no differences between the harmonizations: mean AUC = 73.6% (p = 0.49). Using the whole datasets, the performances were improved using ComBat (p = 0.05) AUC = 82.4% and degraded with Z-score AUC = 67.4% (p = 0.008). Conclusions Data harmonization requires to first focus on data structuring to not degrade the performances of subsequent classifications. Liver tissue classification after harmonization of spleen-based RF is a promising strategy for improving the detection of DL tissue. Key Points • Variability of acquisition parameter makes radiomics of CT features non-reproducible. • Data harmonization can help circumvent the inter-site variability of acquisition protocols. • Inter-site harmonization must be carefully implemented and requires designing consistent data sets.Keywords
This publication has 30 references indexed in Scilit:
- Multicenter CT phantoms public dataset for radiomics reproducibility testsMedical Physics, 2019
- Repeatability and Reproducibility of Radiomic Features: A Systematic ReviewInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2018
- CT Texture Analysis: Definitions, Applications, Biologic Correlates, and ChallengesRadioGraphics, 2017
- Review of Texture Descriptors for Texture Classification2017
- Imaging biomarker roadmap for cancer studiesNature Reviews Clinical Oncology, 2016
- Characterization of PET/CT images using texture analysis: the past, the present… any future?European Journal of Nuclear Medicine and Molecular Imaging, 2016
- Measuring Computed Tomography Scanner Variability of Radiomics FeaturesInvestigative Radiology, 2015
- Quantification of Heterogeneity as a Biomarker in Tumor Imaging: A Systematic ReviewPLOS ONE, 2014
- Radiomics: the process and the challengesMagnetic Resonance Imaging, 2012
- New response evaluation criteria in solid tumours: Revised RECIST guideline (version 1.1)European Journal of Cancer, 2009