Breast cancer is one of the diseases that most affects women. Di- agnosis of the disease in the early stages increases the chances of success in treatments. For this purpose several classification algorithms are studied and applied in this context. This work proposes an experimental study of the applica- tion of the algorithm of Neuroevolution of Augmenting Topologies (NEAT) to de- tect cancer in medical images. The proposal was evaluated for accuracy being applied to different medical imaging databases. The NEAT achieved promising results when compared to different classifiers widely used in the literature.