ComBat Harmonization for MRI Radiomics

Leithner, Doris; Nevin, Rachel B; Gibbs, Peter; Weber, Michael; Otazo, Ricardo; Vargas, Hebert Alberto; Mayerhoefer, Marius E.

doi:10.1097/rli.0000000000000970

Cited by 9 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering all feature categories, ComBat harmonization could increase the model accuracy significantly. In that study two different variants of ComBat were implemented and both improved the results in comparison to unharmonized data 46 .…”

Section: Discussionmentioning

confidence: 99%

MRI-based radiomics for predicting histology in malignant salivary gland tumors: methodology and “proof of principle”

Khodabakhshi,

Motisi,

Bink

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Defining the exact histological features of salivary gland malignancies before treatment remains an unsolved problem that compromises the ability to tailor further therapeutic steps individually. Radiomics, a new methodology to extract quantitative information from medical images, could contribute to characterizing the individual cancer phenotype already before treatment in a fast and non-invasive way. Consequently, the standardization and implementation of radiomic analysis in the clinical routine work to predict histology of salivary gland cancer (SGC) could also provide improvements in clinical decision-making. In this study, we aimed to investigate the potential of radiomic features as imaging biomarker to distinguish between high grade and low-grade salivary gland malignancies. We have also investigated the effect of image and feature level harmonization on the performance of radiomic models. For this study, our dual center cohort consisted of 126 patients, with histologically proven SGC, who underwent curative-intent treatment in two tertiary oncology centers. We extracted and analyzed the radiomics features of 120 pre-therapeutic MRI images with gadolinium (T1 sequences), and correlated those with the definitive post-operative histology. In our study the best radiomic model achieved average AUC of 0.66 and balanced accuracy of 0.63. According to the results, there is significant difference between the performance of models based on MRI intensity normalized images + harmonized features and other models (p value < 0.05) which indicates that in case of dealing with heterogeneous dataset, applying the harmonization methods is beneficial. Among radiomic features minimum intensity from first order, and gray level-variance from texture category were frequently selected during multivariate analysis which indicate the potential of these features as being used as imaging biomarker. The present bicentric study presents for the first time the feasibility of implementing MR-based, handcrafted radiomics, based on T1 contrast-enhanced sequences and the ComBat harmonization method in an effort to predict the formal grading of salivary gland carcinoma with satisfactory performance.

show abstract

Section: Discussionmentioning

confidence: 99%

MRI-based radiomics for predicting histology in malignant salivary gland tumors: methodology and “proof of principle”

Khodabakhshi,

Motisi,

Bink

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…GLCM mathematically assesses the structural properties of images, including complexity and homogeneity. Its entropy parameters, applied in our Rad_score, have been proven to be informative of tissue structural degradation 23 . Given the high level of structural changes caused by BC invasion, the association of Treg infiltration with GLCM entropy parameters is rationalized.…”

Section: Discussionmentioning

confidence: 99%

Profiling regulatory T lymphocytes within the tumor microenvironment of breast cancer via radiomics

Jiang,

Wu,

Yang

et al. 2023

Cancer Medicine

View full text Add to dashboard Cite

ObjectiveTo generate an image‐driven biomarker (Rad_score) to predict tumor‐infiltrating regulatory T lymphocytes (Treg) in breast cancer (BC).MethodsOverall, 928 BC patients were enrolled from the Cancer Genome Atlas (TCGA) for survival analysis; MRI (n = 71 and n = 30 in the training and validation sets, respectively) from the Cancer Imaging Archive (TCIA) were retrieved and subjected to repeat least absolute shrinkage and selection operator for feature reduction. The radiomic scores (rad_score) for Treg infiltration estimation were calculated via support vector machine (SVM) and logistic regression (LR) algorithms, and validated on the remaining patients.ResultsLandmark analysis indicated Treg infiltration was a risk factor for BC patients in the first 5 years and after 10 years of diagnosis (p = 0.007 and 0.018, respectively). Altogether, 108 radiomic features were extracted from MRI images, 4 of which remained for model construction. Areas under curves (AUCs) of the SVM model were 0.744 (95% CI 0.622–0.867) and 0.733 (95% CI 0.535–0.931) for training and validation sets, respectively, while for the LR model, AUCs were 0.771 (95% CI 0.657–0.885) and 0.724 (95% CI 0.522–0.926). The calibration curves indicated good agreement between prediction and true value (p > 0.05), and DCA shows the high clinical utility of the radiomic model. Rad_score was significantly correlated with immune inhibitory genes like CTLA4 and PDCD1.ConclusionsHigh Treg infiltration is a risk factor for patients with BC. The Rad_score formulated on radiomic features is a novel tool to predict Treg abundance in the tumor microenvironment.

show abstract

“…Given that, in vivo, the reproducibility of radiomics features at other scanners is worse than their repeatability, 26 this heterogeneity probably limited the accuracy of the predictions, which is also in line with our finding that the performance of the predictive models declined in the external data sets. Therefore, further standardization of MRI scanners and protocols, as currently ongoing, 58 in general standardization of radiomics pipelines, 29 and application of advanced data harmonization methods, [59][60][61] should be pursued to improve the performance of our approach in the future. A further limitation is that when biopsy was performed before MRI, this had caused postbioptic BM changes and thereby influenced the images.…”

Section: Limitationsmentioning

confidence: 99%

Prediction of Bone Marrow Biopsy Results From MRI in Multiple Myeloma Patients Using Deep Learning and Radiomics

et al. 2023

View full text Add to dashboard Cite

Objectives: In multiple myeloma and its precursor stages, plasma cell infiltration (PCI) and cytogenetic aberrations are important for staging, risk stratification, and response assessment. However, invasive bone marrow (BM) biopsies cannot be performed frequently and multifocally to assess the spatially heterogenous tumor tissue. Therefore, the goal of this study was to establish an automated framework to predict local BM biopsy results from magnetic resonance imaging (MRI). Materials and Methods: This retrospective multicentric study used data from center 1 for algorithm training and internal testing, and data from center 2 to 8 for external testing. An nnU-Net was trained for automated segmentation of pelvic BM from T1-weighted whole-body MRI. Radiomics features were extracted from these segmentations, and random forest models were trained to predict PCI and the presence or absence of cytogenetic aberrations. Pearson correlation coefficient and the area under the receiver operating characteristic were used to evaluate the prediction performance for PCI and cytogenetic aberrations, respectively. Results: A total of 672 MRIs from 512 patients (median age, 61 years; interquartile range, 53-67 years; 307 men) from 8 centers and 370 corresponding BM biopsies were included. The predicted PCI from the best model was significantly correlated ( P ≤ 0.01) to the actual PCI from biopsy in all internal and external test sets (internal test set: r = 0.71 [0.51, 0.83]; center 2, high-quality test set: r = 0.45 [0.12, 0.69]; center 2, other test set: r = 0.30 [0.07, 0.49]; multicenter test set: r = 0.57 [0.30, 0.76]). The areas under the receiver operating characteristic of the prediction models for the different cytogenetic aberrations ranged from 0.57 to 0.76 for the internal test set, but no model generalized well to all 3 external test sets. Conclusions: The automated image analysis framework established in this study allows for noninvasive prediction of a surrogate parameter for PCI, which is significantly correlated to the actual PCI from BM biopsy.

show abstract

ComBat Harmonization for MRI Radiomics

Cited by 9 publications

References 39 publications

MRI-based radiomics for predicting histology in malignant salivary gland tumors: methodology and “proof of principle”

MRI-based radiomics for predicting histology in malignant salivary gland tumors: methodology and “proof of principle”

Profiling regulatory T lymphocytes within the tumor microenvironment of breast cancer via radiomics

Prediction of Bone Marrow Biopsy Results From MRI in Multiple Myeloma Patients Using Deep Learning and Radiomics

Contact Info

Product

Resources

About