What is it about?

Breast cancer screening is made, in some parts of the world to every women from age 45, yearly or every two years. The acquired images need to me manually analysed by specialists. This may lead to human errors and delay in the results. The algorithm here proposed has the goal of identifying normal cases, lightening the burden to the specialists. They can thus analyse the normal results faster, and spend more time in the cases the algorithm did not rule as normal.

Featured Image

Why is it important?

Breast cancer screening images should be analysed in a fast way since it is known that cancer treatment has better results the sooner the cancer is detected. It is also very important not to miss a cancer case. The developed tool identifies normal exams. In this way, the specialists can analyse the images ruled as normal faster, while analysing more carefully the ones the algorithm did not rule as normal. This tool to help specialists can diminish human errors and provide faster results.

Perspectives

It is a great pleasure for me to contribute to a field that I feel is so important and that has an impact in womans health.

Inês Domingues
Centro de Investigação do IPO-Porto (CI-IPOP)

Read the Original

This page is a summary of: Normal breast identification in screening mammography: A study on 18 000 images, November 2014, Institute of Electrical & Electronics Engineers (IEEE),
DOI: 10.1109/bibm.2014.6999178.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page