Skip to main content Skip to navigation Penn Medicine Department of Radiology
Menu
Menu

Research Areas: Computational Biomarker Imaging Group (CBIG)

Screening

Identifying women at high-risk of breast cancer is critical for implementing personalized breast cancer screening protocols and forming preventive strategies. We are working on developing computational methods to characterize breast tissue composition, including breast density and parenchymal texture, from emerging digital breast images modalities and estimating the predictive value of these imaging features to assess a woman's risk of developing breast cancer. Our goal is to incorporate novel imaging biomarkers of cancer risk and clinical breast cancer risk information to improve breast cancer risk assessment for women.

Breast density estimation from digital mammography
Breast density estimation from digital mammography using the LIBRA algorithm developed by our group, based on an adaptive fuzzy C-means clustering dense tissue segmentation.

Selected Publications:

  1. McCarthy AM, Keller BM, Pantalone LM, Hsieh MK, Synnestvedt M, Conant EF, et al. "Racial Differences in Quantitative Measures of Area and Volumetric Breast Density." J Natl Cancer Inst. 2016 Apr 29;108(10). pii: djw104. doi: 10.1093/jnci/djw104. Print 2016 Oct. PubMed PMID: 27130893.
  2. Pertuz S, McDonald ES, Weinstein SP, Conant EF, Kontos D. "Fully Automated Quantitative Estimation of Volumetric Breast Density from Digital Breast Tomosynthesis Images: Preliminary Results and Comparison with Digital Mammography and MR Imaging." Radiology. 2016 Apr;279(1):65-74. doi: 10.1148/radiol.2015150277. Epub 2015 Oct 21. PubMed PMID: 26491909.
  3. Keller BM, Chen J, Daye D, Conant EF, Kontos D. "Preliminary evaluation of the publicly available Laboratory for Breast Radiodensity Assessment (LIBRA) software tool: comparison of fully automated area and volumetric density measures in a case-control study with digital mammography." Breast Cancer Res. 2015 Aug 25;17:117. doi: 10.1186/s13058-015-0626-8. PubMed PMID: 26303303.
  4. Zheng Y, Keller BM, Ray S, Wang Y, Conant EF, Gee JC, Kontos D. "Parenchymal texture analysis in digital mammography: A fully automated pipeline for breast cancer risk assessment." Med Phys. 2015 Jul;42(7):4149-60. doi: 10.1118/1.4921996. PubMed PMID: 26133615.

Prognosis

We are working on developing methods to characterize the imaging characteristics of cancer tumors from multimodality breast imaging data. Our goal is to investigate the value of these imaging features as prognostic biomarkers and incorporate this information in clinical decision making. We are working on elucidating associations between histopathology, cancer receptors, gene expression profiles, and the corresponding imaging phenotype for breast. These imaging biomarkers could complement the current methods for assessing breast cancer prognosis and guide clinical decisions for identifying women who would benefit from specific tailored treatment options.

CBIG - Radio-Genomic Phenotypes Graphic
Breast tumor segmentation from Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) and extraction of multi-parametric imaging biomarkers representing molecular tumor characteristics.

Selected Publications:

  1. Mahrooghy M, Ashraf AB, Daye D, McDonald ES, Rosen M, Mies C, Feldman M, Kontos D. "Pharmacokinetic Tumor Heterogeneity as a Prognostic Biomarker for Classifying Breast Cancer Recurrence Risk." IEEE Trans Biomed Eng. 2015 Jun;62(6):1585-94. doi: 10.1109/TBME.2015.2395812. Epub 2015 Jan 23. PubMed PMID: 25622311.
  2. Ashraf AB, Daye D, Gavenonis S, Mies C, Feldman M, Rosen M, Kontos D. "Identification of intrinsic imaging phenotypes for breast cancer tumors: preliminary associations with gene expression profiles." Radiology. 2014 Aug;272(2):374-84. doi: 10.1148/radiol.14131375. Epub 2014 Apr 4. PubMed PMID: 24702725.
  3. Ashraf AB, Gavenonis SC, Daye D, Mies C, Rosen MA, Kontos D. "A multichannel Markov random field framework for tumor segmentation with an application to classification of gene expression-based breast cancer recurrence risk." IEEE Trans Med Imaging. 2013 Apr;32(4):637-48. doi: 10.1109/TMI.2012.2219589. Epub 2012 Sep 19. PubMed PMID: 23008246.

Treatment

We are developing approaches to integrate structural and functional information from multimodality breast images that could be used to assess and guide personalized breast cancer treatment, including chemotherapy, endocrine therapy, and radiation treatment. In addition, we are looking into the effect of preventative interventions for high-risk women, such as chemoprevention and lifestyle interventions that can effectively reduce the risk of developing breast cancer. Imaging biomarkers in this setting can be used to quantify the effect of treatment, assess the effectiveness of drugs in development, and identify targets for new therapeutic agents.

CBIG - Parametric Response Map Graphic
Longitudinal registration of serial DCE-MRI scans for extracting parametric response maps (PRM) of response to neoadjuvant chemotherapy for breast cancer.

Selected Publications:

  1. Ou Y, Weinstein SP, Conant EF, Englander S, Da X, Gaonkar B, Hsieh MK, et al. "Deformable registration for quantifying longitudinal tumor changes during neoadjuvant chemotherapy." Magn Reson Med. 2015 Jun;73(6):2343-56. doi: 10.1002/mrm.25368. Epub 2014 Jul 15. PubMed PMID: 25046843.
  2. Ashraf A, Gaonkar B, Mies C, DeMichele A, Rosen M, Davatzikos C, Kontos D. "Breast DCE-MRI Kinetic Heterogeneity Tumor Markers: Preliminary Associations With Neoadjuvant Chemotherapy Response." Transl Oncol. 2015 Jun;8(3):154-62. doi: 10.1016/j.tranon.2015.03.005. PubMed PMID: 26055172.
  3. Wu S, Weinstein SP, DeLeo MJ 3rd, Conant EF, Chen J, Domchek SM, Kontos D. "Quantitative assessment of background parenchymal enhancement in breast MRI predicts response to risk-reducing salpingo-oophorectomy: preliminary evaluation in a cohort of BRCA1/2 mutation carriers." Breast Cancer Res. 2015 May 19;17:67. doi: 10.1186/s13058-015-0577-0. PubMed PMID: 25986460.

See all our research publications in PubMed

Share This Page:
Post Tweet