Untitled

doi:10.1002/mp.2019.46.issue-5

Cited by 24 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Preliminary efforts toward harmonization of image-based features of cancer have been previously described for radiomic features extracted from postreconstruction positron-emission tomography images of breast cancer 17 and from full-field digital mammography images of breast lesions. 18 Our findings extend the application of this harmonization method to radiomic features extracted from DCE-MR images of breast lesions in two populations and demonstrate the importance of applying the method to features in terms of categories as well as carefully identifying which features can actually be submitted for harmonization. It is important to note that the scope of this work is limited to harmonization of radiomic features and does not consider harmonization in the context of feature selection or classifier training, which also could affect performance.…”

Section: Discussionsupporting

confidence: 56%

Harmonization of radiomic features of breast lesions across international DCE-MRI datasets

Whitney

et al. 2020

J. Med. Imag.

View full text Add to dashboard Cite

Purpose: Radiomic features extracted from medical images acquired in different countries may demonstrate a batch effect. Thus, we investigated the effect of harmonization on a database of radiomic features extracted from dynamic contrast-enhanced magnetic resonance (DCE-MR) breast imaging studies of 3150 benign lesions and cancers collected from international datasets, as well as the potential of harmonization to improve classification of malignancy.Approach: Eligible features were harmonized by category using the ComBat method. Harmonization effect on features was evaluated using the Davies-Bouldin index for degree of clustering between populations for both benign lesions and cancers. Performance in distinguishing between cancers and benign lesions was evaluated for each dataset using 10-fold cross validation with the area under the receiver operating characteristic curve (AUC) determined on the pre-and postharmonization sets of radiomic features in each dataset and a combined one. Differences in AUCs were evaluated for statistical significance.Results: The Davies-Bouldin index increased by 27% for benign lesions and by 43% for cancers, indicating that the postharmonization features were more similar. Classification performance using postharmonization features performed better than that using preharmonization features (p < 0.001 for all three). Conclusion:Harmonization of radiomic features may enable combining databases from different populations for more comprehensive computer-aided diagnosis models of breast cancer.

show abstract

Section: Discussionsupporting

confidence: 56%