Classification of cancer microscopic images via convolutional neural networks

Abstract

This paper describes our approach for the classification of normal versus malignant cells in B-ALL white blood cancer microscopic images: ISBI 2019—classification of leukemic B-lymphoblast cells from normal B-lymphoid precursors from blood smear microscopic images. We leverage a state of the art convolutional neural network pretrained with the ImageNet dataset and applied several data augmentation and hyperparameters optimization strategies. Our method obtains an F1 score of 0.83 for the final test set in the competition.