Low cost breast cancer prognostic. Pre-processes the images to improve the ability of other algorithms to segment and analyze dense breast tissue.

About

Stanford Reference: 15-193 Abstract Researchers in Dr. Daniel Rubin’s lab have created an automated method to quantify breast density and predict the risk that a woman will develop breast cancer. Breast tissue is composed of fibroglandular and fatty tissue. Fibroglandular tissue appears dense on X-ray mammography and fatty tissue appears lucent. Breast density (or mammographic density) is an estimate of the area of fibroglandular tissue in a breast as shown by mammogram. Higher breast density is a strong risk factor for developing breast cancer. A variety of approaches have been developed to assess breast density but they are not optimal and have poor predictive performance. To overcome these limitations, the inventors have developed a fully automated method to provide a direct estimate of the amount of dense breast tissue based on polychromatic X-ray absorptiometry (PXA). This PXA method estimates dense volume and a ratio of dense to adipose tissue on a pixel-by-pixel basis throughout full digital mammograms. This method may be used to stratify women according to breast cancer risk and enable tailored screening and personalized patient management. Stage of research The technology was validated using a phantom. Further analysis comparing the PXA method to existing predictive techniques was performed using mammograms. The inventors found the PXA method provided stronger associations with breast cancer. Applications Breast cancer prognostic Produces a personalized breast cancer risk score to guide screening and patient management Image analysis Provides a more optimal display of the mammographic images Pre-process the images to improve the ability of other algorithms to segment and analyze dense breast tissue   Advantage Low cost Fully automated Non-subjective- no user involvement required No phantom required Improves accuracy of estimating breast density including regional differences in density Allows personalized risk score- reduces amount of unnecessary tests More optimal display of mammographic images- helps improve detection of cancer  

Register for free for full unlimited access to all innovation profiles on LEO

  • Discover articles from some of the world’s brightest minds, or share your thoughts and add one yourself
  • Connect with like-minded individuals and forge valuable relationships and collaboration partners
  • Innovate together, promote your expertise, or showcase your innovations