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
Photo by Peter Boccia on Unsplash
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
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:
Resources
InBreast
The INbreast database is a mammographic database, with images acquired at a Breast Centre, located in a University Hospital (Hospital de São João, Breast Centre, Porto, Portugal). INbreast has a total of 115 cases (410 images) of which 90 cases are from women with both breasts (4 images per case) and 25 cases are from mastectomy patients (2 images per case). Several types of lesions (masses, calcifications, asymmetries, and distortions) are included. Accurate contours made by specialists are also provided in XML format.
IEEE Xplore
IEEE Xplore link
Contributors
The following have contributed to this page