Computer algorithm for volumetric breast density estimation

This technology is a fully automated computer algorithm used to estimate volumetric breast density from 3D digital breast tomosynthesis (DBT) images.

Unmet Need: Automated method to quantify volumetric breast density from 3D images

Increased breast density is a risk factor for developing breast cancer; therefore, accurately measuring breast density is important for informing disease risk assessments and guiding patient screening recommendations. Current methods for classifying breast density rely on subjective, qualitative visual assessments with minimal reproducibility across multiple observers. While magnetic resonance imaging (MRI) and full-field digital mammography (FFDM) can be used to estimate volumetric breast density, these approaches are limited by their availability and the 2D nature of FFDM, respectively. Therefore, objective, quantitative, and accurate methods for estimating breast density that utilize accessible, 3D digital breast tomosynthesis (DBT) images are needed.

The Technology: Computer algorithm for breast density estimation from accessible digital breast tomosynthesis images

This technology is a fully automated method for quantifying volumetric breast density from digital breast tomosynthesis (DBT) images. This technology utilizes a computer algorithm to identify dense areas of the breast across multiple different DBT images. These images can then be modeled into a predictive 3D model structure in order to quantify volumetric breast density. This method has shown significant correlation with estimates measured using established methods to quantify volumetric breast density, including FFDM, MRI, and manual evaluation.

This technology has been validated with human breast DBT images.

Applications:

• Method to assess breast density
• Risk assessment tool for breast cancer
• Method to investigate clinical implications of increased volumetric breast density

Advantages:

• Quantitative measurement
• Objective analysis of breast density
• Fully automated

Lead Inventor:

Despina Kontos, Ph.D.

Related Publications:

• Ahluwalia VS, Doiphode N, Mankowski WC, Cohen EA, Pati S, Pantalone L, Bakas S, Brooks A, Vachon CM, Conant EF, Gastounioti A, Kontos D. “Volumetric breast density estimation from three-dimensional reconstructed digital breast tomosynthesis images using deep learning.” JCO Clin Cancer Inform. 2024 Dec; 8: e2400103.

• 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.

Tech Ventures Reference:

• IR CU26093

• Licensing Contact: Joan Martinez