18 February 2019 Effect of biopsy on the MRI radiomics classification of benign lesions and luminal A cancers
Heather M. Whitney, Karen Drukker, Alexandra Edwards, John Papaioannou, Maryellen L. Giger
Author Affiliations +
Abstract
Radiomic features extracted from magnetic resonance (MR) images have potential for diagnosis and prognosis of breast cancer. However, presentation of lesions on images may be affected by biopsy. Thirty-four nonsize features were extracted from 338 dynamic contrast-enhanced MR images of benign lesions and luminal A cancers (80 benign/34 luminal A prebiopsy; 46 benign/178 luminal A postbiopsy). Feature value distributions were compared by biopsy condition using the Kolmogorov–Smirnov test. Classification performance was assessed by biopsy condition in the task of distinguishing between lesion types using the area under the receiver operating characteristic curve (AUCROC) as performance metric. Superiority and equivalence testing of differences in AUCROC between biopsy conditions were conducted using Bonferroni–Holm-adjusted significance levels. Distributions for most nonsize features for each lesion type failed to show a statistically significant difference between biopsy conditions. Fourteen features outperformed random guessing in classification. Their differences in AUCROC by biopsy condition failed to reach statistical significance, but we were unable to prove equivalence using a margin of ΔAUCROC  =    ±  0.10. However, classification performance for lesions imaged either prebiopsy or postbiopsy appears to be similar when taking into account biopsy condition.
© 2019 Society of Photo-Optical Instrumentation Engineers (SPIE) 2329-4302/2019/$25.00 © 2019 SPIE
Heather M. Whitney, Karen Drukker, Alexandra Edwards, John Papaioannou, and Maryellen L. Giger "Effect of biopsy on the MRI radiomics classification of benign lesions and luminal A cancers," Journal of Medical Imaging 6(3), 031408 (18 February 2019). https://doi.org/10.1117/1.JMI.6.3.031408
Received: 13 September 2018; Accepted: 14 January 2019; Published: 18 February 2019
Lens.org Logo
CITATIONS
Cited by 7 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Biopsy

Magnetic resonance imaging

Cancer

Feature extraction

Image enhancement

Breast cancer

Image classification

Back to Top