Fully automatic classification of breast MRI background parenchymal enhancement using a transfer learning approach
Authors:
- Karol BorkowskiKBKarol Borkowski
- Cristina RossiCRCristina Rossi
- Alexander CiritsisACAlexander Ciritsis
- Magda MarconMMMagda Marcon
- Patryk HejdukPHPatryk Hejduk
- Sonja StiebSSSonja Stieb
- Andreas BossABAndreas Boss
- Nicole BergerNBNicole Berger
Open Access
- 17 July 2020
- journal article
- research article
- Published by Wolters Kluwer Health in Medicine
- Vol. 99 (29) , e21243
Abstract
Marked enhancement of the fibroglandular tissue on contrast-enhanced breast magnetic resonance imaging (MRI) may affect lesion detection and classification and is suggested to be associated with higher risk of developing breast cancer. The background parenchymal enhancement (BPE) is qualitatively classified according to the BI-RADS atlas into the categories “minimal,” “mild,” “moderate,” and “marked.” The purpose of this study was to train a deep convolutional neural network (dCNN) for standardized and automatic classification of BPE categories. This IRB-approved retrospective study included 11,769 single MR images from 149 patients. The MR images were derived from the subtraction between the first post-contrast volume and the native T1-weighted images. A hierarchic approach was implemented relying on 2 dCNN models for detection of MR-slices imaging breast tissue and for BPE classification, respectively. Data annotation was performed by 2 board-certified radiologists. The consensus of the 2 radiologists was chosen as reference for BPE classification. The clinical performances of the single readers and of the dCNN were statistically compared using the quadratic Cohen's kappa. Slices depicting the breast were classified with training, validation, and real-world (test) accuracies of 98%, 96%, and 97%, respectively. Over the 4 classes, the BPE classification was reached with mean accuracies of 74% for training, 75% for the validation, and 75% for the real word dataset. As compared to the reference, the inter-reader reliabilities for the radiologists were 0.780 (reader 1) and 0.679 (reader 2). On the other hand, the reliability for the dCNN model was 0.815. Automatic classification of BPE can be performed with high accuracy and support the standardization of tissue classification in MRI.Keywords
This publication has 28 references indexed in Scilit:
- Background Parenchymal Enhancement at Breast MR Imaging and Breast Cancer RiskRadiology, 2011
- Does the degree of background enhancement in breast MRI affect the detection and staging of breast cancer?European Radiology, 2011
- Screening Breast MR Imaging: Comparison of Interpretation of Baseline and Annual Follow-up StudiesRadiology, 2011
- Breast Cancers Not Detected at MRI: Review of False-Negative LesionsAmerican Journal of Roentgenology, 2010
- Breast Stromal Enhancement on MRI Is Associated with Response to Neoadjuvant ChemotherapyAmerican Journal of Roentgenology, 2008
- Diagnostic Breast MR Imaging: Current Status and Future DirectionsRadiologic Clinics of North America, 2007
- The Current Status of Breast MR Imaging Part I. Choice of Technique, Image Interpretation, Diagnostic Accuracy, and Transfer to Clinical PracticeRadiology, 2007
- Physiologic Changes in Breast Magnetic Resonance Imaging during the Menstrual Cycle: Perfusion Imaging, Signal Enhancement, and Influence of the T1 Relaxation Time of Breast TissueThe Breast Journal, 2005
- Undetected Malignancies of the Breast: Dynamic Contrast-enhanced MR Imaging at 1.0 TRadiology, 2002
- Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit.Psychological Bulletin, 1968