You are here: Home / Protocols / Automated Quantitative Measures of Breast Density

Automated Quantitative Measures of Breast Density

448

No coordinating investigator defined.

Breast density
Other, Specify
Breast and Gynecologic Cancers Research
1

Mammographic breast density (BD) is a significant breast cancer risk factor, second in magnitude only to inherited BRCA mutations. Most research studies generating this conclusion used an operator-assisted method (applied to digitized film) to estimate the percentage of BD (i.e. PD, the standard), which requires an expert technician to outline the breast region and define thresholds. Although clearly an invaluable research tool, this standard does not lend itself to automation, and is therefore not amenable for application in the clinical setting (i.e. large-scale implementation) for patient risk assessment and management. Our goal is to lay the foundation for translating the demonstrated research value of BD into the clinic by advancing our recent achievements in full field digital mammography (FFDM), the emerging standard modality for breast screening in the US. We developed a calibration system for FFDM using a specific unit that produced four significant findings: (1) a standardization technique that makes pixel values comparable across all images, (2) a new calibrated spatial variation BD measurement (or Vc) that offered a stronger measurement of risk than the standard, (3) Vc is a function of PD, another calibrated measure of BD that is also a significant risk factor, and other important risk covariates, i.e. high correlation but non-linear, and (4) demonstrated the variation measure (or V) applied to raw mammograms (or Vr) is also a significant breast cancer risk factor. In this proposed work we build on our calibration approach and apply it to different FFDM units. We will validate the Vc and Vr measures from different FFDM technology and make comparisons with our previous findings using a matched case-control study using both pre-existing and new FFDM datasets. Because differences in detector designs have the potential to alter spatial variation, it is imperative to assess these influences on the new V-metrics to demonstrate that breast cancer risk is not dependent upon the system design. We will quantify the gains derived from calibration by comparing Vc and Vr, because gains are derived at the expense of advanced image processing and analyses. We will determine the optimal breast density measure and representation (i.e. is calibration required), where optimal is defined by these attributes: automated, quantitative, reproducible, consistent across different imaging platforms, and offers risk prediction at least equivalent with that offered by PD. To meet our objectives, we use accepted techniques and introduce novel analysis strategies that include statistical learning to better capture the relationships between the import risk covariates. This work will provide a prescription for making the optimal BD measurement. The successful completion of this work will allow the full scale integration of BD into the clinical environment. Potential applications include personalized care of patients in terms of screening frequency, risk reduction interventions, and the identification of situations where mammography may be ineffective (i.e. where dense tissue significantly reduces either sensitivity or specificity of mammography).

Background: Mammographic breast density (BD) is a significant breast cancer risk factor, second in magnitude only to inherited mutations in BRCA1/2. Most research in this area to date used an operator assisted approach to estimate the percentage of breast density (PD). Although an important research tool, PD is somewhat subjective, does not lend itself to automation, and is therefore not amenable for application in the clinical setting for patient risk assessment and management. Preliminary Data and Justification: We recently developed a calibration system to adjust for image acquisition technique differences for FFDM. After applying the calibration, inter-image pixel values are comparable. From this research, a new variation measure of breast density (or V) emerged that provided stronger breast cancer risk prediction than PD. We also showed that there is a non-linear functional relationship between V, PD, and several other relevant and highly correlated covariates. Analogous measures of V were also derived from both non-calibrated FFDM and digitized film images. These various non-calibrated V measurements showed both stronger (the majority of comparisons) and equivalent risk association than offered by PD, indicating the form of detection may impact this new measure more so than PD. Because V measures variation rather than relative brightness (as does PD), we have insufficient evidence to determine whether (a) V is independent of the detection system, or (b) depends on the calibration step, which if so will provide a benchmark (i.e. define the technical effort requirement) to automate the V measurement. There are three Specific Aims required to meet our objectives. These will be examined using FFDM data from a large matched case-control study of breast cancer. Specific Aim 1: A calibration methodology will be established for newer model FFDM units. Inter-FFDM system (i.e. inter-manufacturer) V-BD consistency will be assessed to demonstrate that V is invariant with respect to technological design differences. V-BD will be compared with PD to demonstrate it shows stronger association with breast cancer. Expected Outcome: We will validate the calibrated V measure (or Vc) with a larger dataset and demonstrate that Vc is not dependent upon the FFDM technological design. This is a crucial step in developing the optimal measure since risk should be independent of system design. Alternatively, this aim may demonstrate there is a preferable (technological-design) FFDM unit for risk prediction. Specific Aim 2: We will determine whether calibration is required for the development of the optimal breast density measurement by comparing intra and inter-machine (i.e. inter-manufacturer) calibrated and non-calibrated V measures. We will also compare the non-calibrated measures with PD. Expected Outcome: Because the calibration-system requires extensive experimentation and advanced image processing before it is possible to calibrate prospective mamm
Advanced image processing

There are currently no biomarkers annotated for this protocol.

No datasets are currently associated with this protocol.


Announcement 09/27/2019
Thank you to everyone who made the 11th EDRN Scientific Workshop a success. The next EDRN Steering Committee Meeting is from Tuesday-Thursday, March 31-April 2, 2020 in Tempe, AZ.
Announcement



 
This icon signifies that something is happening and we kindly ask you to please wait