Performance study of augmentation techniques for HEp2 CNN classification

Computers have been playing an important role in the medical field. More specifically in the field of computer aided diagnoses. Moreover, making computers and human work together, in the medical field, not only makes it easy for medical experts to do their tasks, but also makes their work more accurate. That is the main motivation of the growing utilization of advanced computer techniques such as machine learning and artificial intelligence in the medical field. In this proposed work, we use the recent machine learning framework that is implemented in the latest MATLAB[1] version to classify HEp2 cell images. Which is one of the difficult classification tasks for a computer due to the low resolution, amount of details, and also to how similar the different classes are from each other. We make an intense study for pre-augmentation and real-time augmentation that is built-in the latest MATLAB version. In this work we use Convolutional Neural Network (CNN) with some of the state of the art techniques that proved significant improvements over older classical architectures. The proposed work has achieved 98.29% validation accuracy in only 10 epochs of training.