Computer aided diagnosis of breast cancer in mammography using deep neural networks

T. Kooi

• Promotor: N. Karssemeijer and G. den Heeten
• Graduation year: 2018
• Radboud University, Nijmegen

Abstract

Breast cancer is one of the most common types of cancer in the general population and most common cancer in women. In spite of advances in treatment it is still a leading cause of cancer death. Early detection has been shown to significantly improve chances of survival and therefore screening, where asymptomatic women in high risk subpopulations are invited for annual or biennial breast exams, is being performed in many countries. These programs generate an enormous amount of data which have to be read by trained experts, often a time consuming and error prone process. To mitigate this, computer aided detection and diagnosis (CAD) systems are being developed to aid and ultimately replace human readers of various medical images.