ComBat harmonization for MRI radiomics: Impact on nonbinary tissue classification by machine learning Journal Article
| Authors: | Leithner, D.; Nevin, R. B.; Gibbs, P.; Weber, M.; Otazo, R.; Vargas, H. A.; Mayerhoefer, M. E. |
| Article Title: | ComBat harmonization for MRI radiomics: Impact on nonbinary tissue classification by machine learning |
| Abstract: | Objectives The aims of this study were to determine whether ComBat harmonization improves multiclass radiomics-based tissue classification in technically heterogeneous MRI data sets and to compare the performances of 2 ComBat variants. Materials and Methods One hundred patients who had undergone T1-weighted 3D gradient echo Dixon MRI (2 scanners/vendors; 50 patients each) were retrospectively included. Volumes of interest (2.5 cm3) were placed in 3 disease-free tissues with visually similar appearance on T1 Dixon water images: liver, spleen, and paraspinal muscle. Gray-level histogram (GLH), gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), and gray-level size-zone matrix (GLSZM) radiomic features were extracted. Tissue classification was performed on pooled data from the 2 centers (1) without harmonization, (2) after ComBat harmonization with empirical Bayes estimation (ComBat-B), and (3) after ComBat harmonization without empirical Bayes estimation (ComBat-NB). Linear discriminant analysis with leave-one-out cross-validation was used to distinguish among the 3 tissue types, using all available radiomic features as input. In addition, a multilayer perceptron neural network with a random 70%:30% split into training and test data sets was used for the same task, but separately for each radiomic feature category. Results Linear discriminant analysis-based mean tissue classification accuracies were 52.3% for unharmonized, 66.3% for ComBat-B harmonized, and 92.7% for ComBat-NB harmonized data. For multilayer perceptron neural network, mean classification accuracies for unharmonized, ComBat-B-harmonized, and ComBat-NB-harmonized test data were as follows: 46.8%, 55.1%, and 57.5% for GLH; 42.0%, 65.3%, and 71.0% for GLCM; 45.3%, 78.3%, and 78.0% for GLRLM; and 48.1%, 81.1%, and 89.4% for GLSZM. Accuracies were significantly higher for both ComBat-B-and ComBat-NB-harmonized data than for unharmonized data for all feature categories (at P = 0.005, respectively). For GLCM (P = 0.001) and GLSZM (P = 0.005), ComBat-NB harmonization provided slightly higher accuracies than ComBat-B harmonization. Conclusions ComBat harmonization may be useful for multicenter MRI radiomics studies with nonbinary classification tasks. The degree of improvement by ComBat may vary among radiomic feature categories, among classifiers, and among ComBat variants. © Wolters Kluwer Health, Inc. All rights reserved. |
| Keywords: | adult; human tissue; retrospective studies; major clinical study; clinical trial; nuclear magnetic resonance imaging; positron emission tomography; magnetic resonance imaging; diagnostic accuracy; bayes theorem; image analysis; retrospective study; training; discriminant analysis; multicenter study; mri; nerve cell network; histogram; receiver operating characteristic; artificial neural network; image segmentation; feature extraction; harmonization; machine learning; combat medic; humans; human; male; female; article; radiomics; bayesian network; multilayer perceptron; leave one out cross validation; cross validation; neural networks, computer; t1 weighted imaging; combat harmonization; paraspinal muscle |
| Journal Title: | Investigative Radiology |
| Volume: | 58 |
| Issue: | 9 |
| ISSN: | 0020-9996 |
| Publisher: | Lippincott Williams & Wilkins |
| Date Published: | 2023-09-01 |
| Start Page: | 697 |
| End Page: | 701 |
| Language: | English |
| DOI: | 10.1097/rli.0000000000000970 |
| PUBMED: | 36897814 |
| PROVIDER: | scopus |
| PMCID: | PMC10403369 |
| DOI/URL: | |
| Notes: | Article -- MSK Cancer Center Support Grant (P30 CA008748) acknowledged in PubMed and PDF -- MSK corresponding author is Marius Mayerhoefer -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
-
267Vargas Alvarez -
47Otazo Torres -
43Leithner -
70Mayerhoefer -
33Gibbs -
2
Nevin
Related MSK Work