Breast cancer detection in histopathological images using convolutional neural networks
Andrio Rodrigo Corrêa da Silva, Iális Cavalcante de Paula Júnior, Márcio André Baima Amora · 2019
Breast cancer is one of the biggest causes of death among women around the world. Diagnosing this disease early can offer better treatment to the patient. Intelligent systems have been used for the detection of diseases using images. In this work a convolutional neural network was used for the detection of breast cancer in histopathological images through Keras library and TensorFlow framework. Models were created for 4 datasets with different magnifying factors (40x, 100x, 200x and 400x). Using k-fold cross-validation, it was found that there was a better result for the set of 400x images with 98.44% accuracy in the training data. The set of 200x images obtained a better result for recall and f1-score.