Detection criteria for evaluation of computer aided diagnosis systems

A Scalable System for Microcalcification Cluster Automated Detection in a Distributed Mammographic Database

“…A cluster detection criterion has to be a priori defined. The effect the choice of the detection criteria in addition to the size of the annotated region has on the CAD performance evaluation have been systematically examined in the literature [18,19]. As there is no universal scoring method currently in use for evaluating the performances of a CAD system for microcalcification cluster detection, we briefly describe the detection criteria we adopted:…”

“…A cluster detection criterion has to be a priori defined. The effect the choice of the detection criteria in addition to the size of the annotated region has on the CAD performance evaluation have been systematically examined in the literature [18,19]. As there is no Table 1: Evaluation of the performances of the standard back-propagation learning algorithm for the neural classifier according to the 5×2 cross validation method.…”

Aplicación de técnicas de inteligencia artificial para contribuir en la detección de microcalcificaciones en mamografía digitalizada

“…En el caso de [Strickland, 1994], la detección de microcalcificaciones se enfoca al uso de la transformada wavelet en combinación con el criterio propuesto por [Brake & Karssemeijer, 1997], donde se analiza el tamaño, la forma y el número de microcalcificaciones por unidad de área. [Veldkamp & Karssemeijer, 2000] utilizan técnicas clásicas en 1.…”