Fully automated breast segmentation on spiral breast CT images

A real breakthrough in breast cancer diagnostics

Breast cancer is the most diagnosed cancer and the leading cause of cancer death among women worldwide. Breast density affects the risk of developing breast cancer. At the same time, the sensitivity of mammograms decreases with high breast density due to masking effects.

To reduce breast cancer mortality rate by early cancer diagnosis, breast imaging technologies such as nuview breast CT have been developed, and studies for assessing the breast cancer risk based on those images have been conducted.

Universitätsspital Zürich proposed a fully automated segmentation method for spiral breast CT, which is necessary to properly assess the quantitative breast density.

The results:

> The automatic segmentation coincided well with the human expert´s reading.

> The segmentation and breast density estimation demonstrated that an accurate segmentation is important to avoid a significant bias in breast density analysis.

> This method enabled accurate quantification of the breast density and amount of the glandular tissue that is directly related to breast cancer risk.

This segmentation method can in principle be applied as a standalone tool, for example, to provide the description of individual breast tissue structures and complement existing software in the clinical workflow.

A real breakthrough in breast cancer diagnostics!

Click on "more information" and read the whole study