TY - JOUR
T1 - Incorporating robustness to imaging physics into radiomic feature selection for breast cancer risk estimation
AU - Acciavatti, Raymond J.
AU - Cohen, Eric A.
AU - Maghsoudi, Omid Haji
AU - Gastounioti, Aimilia
AU - Pantalone, Lauren
AU - Hsieh, Meng Kang
AU - Conant, Emily F.
AU - Scott, Christopher G.
AU - Winham, Stacey J.
AU - Kerlikowske, Karla
AU - Vachon, Celine
AU - Maidment, Andrew D.A.
AU - Kontos, Despina
N1 - Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2021/11/1
Y1 - 2021/11/1
N2 - Digital mammography has seen an explosion in the number of radiomic features used for risk‐assessment modeling. However, having more features is not necessarily beneficial, as some features may be overly sensitive to imaging physics (contrast, noise, and image sharpness). To measure the effects of imaging physics, we analyzed the feature variation across imaging acquisition settings (kV, mAs) using an anthropomorphic phantom. We also analyzed the intra-woman variation (IWV), a measure of how much a feature varies between breasts with similar parenchymal patterns—a woman’s left and right breasts. From 341 features, we identified “robust” features that minimized the effects of imaging physics and IWV. We also investigated whether robust features offered better case‐control classification in an independent data set of 575 images, all with an overall BI‐RADS® assessment of 1 (negative) or 2 (benign); 115 images (cases) were of women who developed cancer at least one year after that screening image, matched to 460 controls. We modeled cancer occurrence via logistic regression, using cross‐validated area under the receiver‐operating‐characteristic curve (AUC) to measure model performance. Models using features from the most‐robust quartile of features yielded an AUC = 0.59, versus 0.54 for the least-robust, with p < 0.005 for the difference among the quartiles.
AB - Digital mammography has seen an explosion in the number of radiomic features used for risk‐assessment modeling. However, having more features is not necessarily beneficial, as some features may be overly sensitive to imaging physics (contrast, noise, and image sharpness). To measure the effects of imaging physics, we analyzed the feature variation across imaging acquisition settings (kV, mAs) using an anthropomorphic phantom. We also analyzed the intra-woman variation (IWV), a measure of how much a feature varies between breasts with similar parenchymal patterns—a woman’s left and right breasts. From 341 features, we identified “robust” features that minimized the effects of imaging physics and IWV. We also investigated whether robust features offered better case‐control classification in an independent data set of 575 images, all with an overall BI‐RADS® assessment of 1 (negative) or 2 (benign); 115 images (cases) were of women who developed cancer at least one year after that screening image, matched to 460 controls. We modeled cancer occurrence via logistic regression, using cross‐validated area under the receiver‐operating‐characteristic curve (AUC) to measure model performance. Models using features from the most‐robust quartile of features yielded an AUC = 0.59, versus 0.54 for the least-robust, with p < 0.005 for the difference among the quartiles.
KW - Anthropomorphic phantom
KW - Breast cancer
KW - Case‐control analysis
KW - Digital mammography
KW - Feature selection
KW - Imaging acquisition physics
KW - Radiomics
KW - Risk assessment
KW - Robustness
UR - http://www.scopus.com/inward/record.url?scp=85118207671&partnerID=8YFLogxK
U2 - 10.3390/cancers13215497
DO - 10.3390/cancers13215497
M3 - Article
C2 - 34771660
AN - SCOPUS:85118207671
SN - 2072-6694
VL - 13
JO - Cancers
JF - Cancers
IS - 21
M1 - 5497
ER -