Diagnostic value of radiomics and machine learning with dynamic contrast-enhanced magnetic resonance imaging for patients with atypical ductal hyperplasia in predicting malignant upgrade Journal Article

   

Authors:	Lo Gullo, R.; Vincenti, K.; Rossi Saccarelli, C.; Gibbs, P.; Fox, M. J.; Daimiel, I.; Martinez, D. F.; Jochelson, M. S.; Morris, E. A.; Reiner, J. S.; Pinker, K.
Article Title:	Diagnostic value of radiomics and machine learning with dynamic contrast-enhanced magnetic resonance imaging for patients with atypical ductal hyperplasia in predicting malignant upgrade
Abstract:	Purpose: To investigate whether radiomics features extracted from magnetic resonance imaging (MRI) of patients with biopsy-proven atypical ductal hyperplasia (ADH) coupled with machine learning can differentiate high-risk lesions that will upgrade to malignancy at surgery from those that will not, and to determine if qualitatively and semi-quantitatively assessed imaging features, clinical factors, and image-guided biopsy technical factors are associated with upgrade rate. Methods: This retrospective study included 127 patients with 139 breast lesions yielding ADH at biopsy who were assessed with multiparametric MRI prior to biopsy. Two radiologists assessed all lesions independently and with a third reader in consensus according to the BI-RADS lexicon. Univariate analysis and multivariate modeling were performed to identify significant radiomic features to be included in a machine learning model to discriminate between lesions that upgraded to malignancy on surgery from those that did not. Results: Of 139 lesions, 28 were upgraded to malignancy at surgery, while 111 were not upgraded. Diagnostic accuracy was 53.6%, specificity 79.2%, and sensitivity 15.3% for the model developed from pre-contrast features, and 60.7%, 86%, and 22.8% for the model developed from delta radiomics datasets. No significant associations were found between any radiologist-assessed lesion parameters and upgrade status. There was a significant correlation between the number of specimens sampled during biopsy and upgrade status (p = 0.003). Conclusion: Radiomics analysis coupled with machine learning did not predict upgrade status of ADH. The only significant result from this analysis is between the number of specimens sampled during biopsy procedure and upgrade status at surgery. © 2021, The Author(s).
Keywords:	adult; middle aged; major clinical study; clinical feature; diagnostic accuracy; sensitivity and specificity; consensus; breast cancer; prediction; radiologist; diagnostic value; quantitative analysis; high risk population; dynamic contrast-enhanced magnetic resonance imaging; breast biopsy; correlational study; qualitative analysis; atypical ductal hyperplasia; machine learning; high-risk lesions; image guided biopsy; breast imaging reporting and data system; multiparametric magnetic resonance imaging; human; female; article; radiomics; adh
Journal Title:	Breast Cancer Research and Treatment
Volume:	187
Issue:	2
ISSN:	0167-6806
Publisher:	Springer
Date Published:	2021-06-01
Start Page:	535
End Page:	545
Language:	English
DOI:	10.1007/s10549-020-06074-7
PUBMED:	33471237
PROVIDER:	scopus
PMCID:	PMC8190021
DOI/URL:	https://www.scopus.com/inward/record.uri?eid=2-s2.0-85099582726&doi=10.1007%2fs10549-020-06074-7&partnerID=40&md5=f2e005628563ce042097346141e553e3
Notes:	Article -- Export Date: 1 July 2021 -- Source: Scopus

https://synapse.mskcc.org/synapse/works/has_related_data_chk/182479