TY - JOUR
T1 - Radiomic and deep learning characterization of breast parenchyma on full field digital mammograms and specimen radiographs
T2 - a pilot study of a potential cancer field effect
AU - Baughan, Natalie
AU - Li, Hui
AU - Lan, Li
AU - Embury, Matthew
AU - Yim, Isaiah
AU - Whitman, Gary J.
AU - El-Zein, Randa
AU - Bedrosian, Isabelle
AU - Giger, Maryellen L.
N1 - Publisher Copyright:
© 2023 Society of Photo-Optical Instrumentation Engineers (SPIE).
PY - 2023/7/1
Y1 - 2023/7/1
N2 - Purpose: In women with biopsy-proven breast cancer, histologically normal areas of the parenchyma have shown molecular similarity to the tumor, supporting a potential cancer field effect. The purpose of this work was to investigate relationships of human-engineered radiomic and deep learning features between regions across the breast in mammographic parenchymal patterns and specimen radiographs. Approach: This study included mammograms from 74 patients with at least 1 identified malignant tumor, of whom 32 also possessed intraoperative radiographs of mastectomy specimens. Mammograms were acquired with a Hologic system and specimen radiographs were acquired with a Fujifilm imaging system. All images were retrospectively collected under an Institutional Review Board-approved protocol. Regions of interest (ROI) of 128 × 128 pixels were selected from three regions: within the identified tumor, near to the tumor, and far from the tumor. Radiographic texture analysis was used to extract 45 radiomic features and transfer learning was used to extract 20 deep learning features in each region. Kendall's Tau-b and Pearson correlation tests were performed to assess relationships between features in each region. Results: Statistically significant correlations in select subgroups of features with tumor, near to the tumor, and far from the tumor ROI regions were identified in both mammograms and specimen radiographs. Intensity-based features were found to show significant correlations with ROI regions across both modalities. Conclusions: Results support our hypothesis of a potential cancer field effect, accessible radiographically, across tumor and non-tumor regions, thus indicating the potential for computerized analysis of mammographic parenchymal patterns to predict breast cancer risk.
AB - Purpose: In women with biopsy-proven breast cancer, histologically normal areas of the parenchyma have shown molecular similarity to the tumor, supporting a potential cancer field effect. The purpose of this work was to investigate relationships of human-engineered radiomic and deep learning features between regions across the breast in mammographic parenchymal patterns and specimen radiographs. Approach: This study included mammograms from 74 patients with at least 1 identified malignant tumor, of whom 32 also possessed intraoperative radiographs of mastectomy specimens. Mammograms were acquired with a Hologic system and specimen radiographs were acquired with a Fujifilm imaging system. All images were retrospectively collected under an Institutional Review Board-approved protocol. Regions of interest (ROI) of 128 × 128 pixels were selected from three regions: within the identified tumor, near to the tumor, and far from the tumor. Radiographic texture analysis was used to extract 45 radiomic features and transfer learning was used to extract 20 deep learning features in each region. Kendall's Tau-b and Pearson correlation tests were performed to assess relationships between features in each region. Results: Statistically significant correlations in select subgroups of features with tumor, near to the tumor, and far from the tumor ROI regions were identified in both mammograms and specimen radiographs. Intensity-based features were found to show significant correlations with ROI regions across both modalities. Conclusions: Results support our hypothesis of a potential cancer field effect, accessible radiographically, across tumor and non-tumor regions, thus indicating the potential for computerized analysis of mammographic parenchymal patterns to predict breast cancer risk.
KW - breast cancer risk assessment
KW - breast parenchymal patterns
KW - deep learning
KW - image analysis
KW - radiomics
UR - http://www.scopus.com/inward/record.url?scp=85171571787&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85171571787&partnerID=8YFLogxK
U2 - 10.1117/1.JMI.10.4.044501
DO - 10.1117/1.JMI.10.4.044501
M3 - Article
C2 - 37426053
AN - SCOPUS:85171571787
SN - 2329-4302
VL - 10
JO - Journal of Medical Imaging
JF - Journal of Medical Imaging
IS - 4
M1 - 044501
ER -