Keywords:
Breast, Artificial Intelligence, Computer applications, Mammography, Computer Applications-Detection, diagnosis, Diagnostic procedure, Decision analysis, Cancer, Image verification
Authors:
J. P. Pereira Fontes, M. A. Guevara Lopez; Guimarães/PT
DOI:
10.26044/ecr2019/C-2062
Aims and objectives
According to the American Cancer Society [1],
breast cancer represents 25 per cent of the new cancer diagnostics in women worldwide,
being the greatest cause of death in the world’s developing regions.
This study aims to present ways of using Deep Learning (DL) algorithms in the automatic analysis of medical images representing pathological lesions of breast cancer masses.
The purpose of this work is to highlight DL functionalities to improve the current machine learning (ML) based breast cancer diagnosis methods (CADx).
CADx methods have been helping medical professionals in tasks,
such as screening,
early detection,
diagnosis,
treatment and monitoring,
which bring a bigger change of recovery to patients.
However,
current CADx methods need to be improved to achieve a better performance in classifying breast cancer.
DL approaches can be seen as a natural evolution of traditional ML methods,
giving a boost in CADx performance.