Skip to Content
COVID-19 Resources
Cancer Imaging Program (CIP)
Contact CIP
Show menu
Search this site
Last Updated: 11/19/19
Quantitative Imaging Network (QIN)

University of Chicago

Quantatitive Image Analysis for Assessing Response to Breast Cancer Therapy

Maryellen L. Giger, Ph.D.
m-giger@uchicago.edu

Grant Number: U01 CA195564

The goal of this research is to develop quantitative image-based phenotypes for use in predicting response to therapy and ultimately aiding in patient management. There is a large variation in the clinical presentation of breast cancer in women, and it has been shown that in many instances, biological characteristics of the primary tumor correlates with outcome. Methods to assess such biological features for the prediction of outcome, however, may be invasive, expensive or not widely available. In addition, breast cancer tumors are heterogeneous, and current MRI biomarkers include only size and SER (signal enhancement ratio). Our hypothesis is that MRI phenotypes obtained through quantitative image analysis will prove useful as non-invasive biomarkers for the assessment of, and prediction of, the response of breast cancer to neoadjuvant therapy. The team proposes to validate such image-based biomarkers (phenotypic tumor signatures) using magnetic resonance (MR) images of breast tumors from the ACRIN 6657 clinical trial, which includes pathological response data. Specifically the team will (1) investigate the relationship of breast cancer therapy outcome and MR image-based tumor characteristics (phenotypes), and changes in these phenotypes over time, using two University of Chicago databases and the ACRIN 6657 I-SPY clinical trial dataset of breast cancer tumors from patients who have undergone neoadjuvant treatment, (2) and will develop and evaluate the MRI-derived ‘signatures’ of breast cancer tumors for the prediction of, and assessment of, response to therapy, and (3) will conduct preliminary, initial stratification and association of the MRI phenotypes with cancer subtype and other clinical/histopathological data. The team will build on their 25-year history of taking innovation to the clinical setting by extending our prior development, validation, and translation of quantitative image analyses for computer-aided diagnosis to the post-diagnosis, predictive component in order to assess response to therapy. The team’s research addresses the development & validation of algorithms using the existing ACRIN 6657 dataset with the goal of “improving the ability to measure the response of targeted tumors to therapy quantitatively”, and is aligned with the QIN U01 goals of including robustness investigations and multi-site trial data. This research is expected to yield a set of validated tumor phenotypes/signatures that will serve as quantitative tools for use in clinical studies/trials to predict and/or assess tumor response.

Reference listing:

  1. Li H, Zhu Y, Burnside ES, . Perou CM, Ji Y, Giger ML: MRI radiomics signatures for predicting the risk of breast cancer recurrence as given by research versions of gene assays of MammaPrint, Oncotype DX, and PAM50. Radiology DOI: http://dx.doi.org/10.1148/radiol.2016152110, 2016.

  2. Li H, Zhu Y, Burnside ES, . Perou CM, Ji Y, Giger ML: Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA Dataset. npj Breast Cancer (2016) 2, 16012; doi:10.1038/npjbcancer.2016.12; published online 11 May 2016.

  3. Huynh B, Li H, Giger ML: Digital mammographic tumor classification using transfer learning from deep convolutional neural networks. J Medical Imaging 3(3), 034501, 2016.

  4. Li H, Weiss WA, Medved M, Abe H, Newstead GM, Karczmar GS, Giger ML: Breast density estimation from high spectral and spatial resolution MRI. J Med Imaging 2016 Oct;3(4):044507. doi: 10.1117/1.JMI.3.4.044507. Epub 2016 Dec 28, 2016.

  5. Antropova N, Huynh BQ, Giger ML: A deep fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets. Medical Physics online doi.org/10.1002/mp.12453, 2017.

  6. Mendel K, Li H, Lan L, Cahill C, Rael V, Abe H, Giger ML: Quantitative texture analysis: robustness of radiomics across two digital mammography manufacturers' systems. J Med Imaging 5(1), 011002 (2017), doi: 10.1117/1.JMI.5.1.011002, 2017.

  7. Sutton EJ, Huang EP, Drukker K, Burnside ES, Li H, Net JM, Rao A, Whitman GJ, Zuley M, Ganott M, Bonaccio E, Giger ML, Morris EA and TCGA Group. Breast MRI radiomics: comparison of computer- and human-extracted imaging phenotypes. European Radiology Experimental 22:1-10, 2017.

  8. Antropova N, Abe H, Giger ML: Use of clinical MRI maximum intensity projections for improved breast lesion classification with deep CNNs J Med Imaging (Bellingham). 2018 Jan;5(1):014503. doi: 10.1117/1.JMI.5.1.014503, 2018.

  9. Drukker K, Li H, Antropova N, Edwards A, Papaioannou J, Giger ML: Most-enhancing tumor volume by MRI radiomics predicts recurrence-free survival "early on" in neoadjuvant treatment of breast cancer. Cancer Imaging 18:12. https://doi.org/10.1186/s40644-018-0145-9, 2018.

  10. Whitney H, Taylor NS, Drukker K, Edwards A, Papaioannou J, Schacht D, Giger ML: Additive benefit of radiomics over size alone in the distinction between benign lesions and luminal A cancers on a large clinical breast MRI dataset. Academic Radiology, 2018 May 10. pii: S1076-6332(18)30202-2. doi: 10.1016/j.acra.2018.04.019. [Epub ahead of print], 2018.

  11. Antropova N, Huynh B, Li H, Giger ML: Breast lesion classification based on DCE-MRI sequences with long short-term memory networks. J of Medical Imaging, 6(1) 011002 doi: 10.1117/1.JMI.6.1.011002, 2018.

  12. Mendel K, Li H, Sheth D, Giger ML: Transfer learning from convolutional neural networks for computer-aided diagnosis: A comparison of digital breast tomosynthesis and full-field digital mammography. Acad Radiol. 2018 Jul 31. pii: S1076-6332(18)30333-7. doi: 10.1016/j.acra.2018.06.019. [Epub ahead of print], 2018.

  13. Net JM, Whitman GJ, Morris E, Brandt KR, Burnside ES, Giger ML, Ganott M, Sutton EJ, Zuley MZ, Rao A: Relationships between human-extracted MRI tumor phenotypes of breast cancer and clinical prognostic indicators including receptor status and molecular subtype. Current Problems in Diagnostic Radiology 2018 Aug 23. pii: S0363-0188(18)30157-9. doi: 10.1067/j.cpradiol.2018.08.003, 2018.

  14. Drukker K, Giger ML, Joe BN, Kerlikowske K, Greenwood H, Drukteinis JS, Niell B, Fan B, Malkov S, Avila J, Kazemi L, Shepherd J: Combined benefit of quatitative three-compartment breast image analysis and mammography radiomics in the classification of breast masses in a clinical data set. Radiology Published Online: Dec 11 2018 https://doi.org/10.1148/radiol.2018180608, 2018.

  15. Li H, Mendel K, Sheth D, Lan L, Giger ML: Digital mammography in breast cancer: additive value of radiomics of breast parenchyma. Radiology 2019 Apr;291(1):15-20. doi: 10.1148/radiol.2019181113. Epub Feb 12, 2019.

  16. Whitney K, Drukker K, Edwards A, Papaioannou J, Giger ML: Effect of biopsy on the MRI radiomics classification of benign lesions and luminal A cancers. J Medical Imaging Journal of Medical Imaging 6(3), 031408, 2019.

  17. Robinson K, Li H, Lan L, Schacht D, Giger ML: Radiomics assessment and classification evaluation: A two-stage method demonstrated on multi-vendor FFDM. Medical Physics 2019 Feb 25. doi: 10.1002/mp.13455.