Phase classification of chronic myeloid leukemia using convolution neural networks
Ekaansh Khosla, Dharavath Ramesh · 2018
In the disseminate state of human health, there are over 100 types of different cancers in which Chronic myeloid leukemia (CML) is a commonly identified disease. Identification of CML phases such as chronic phase, accelerated phase, and blast crisis phase plays an important role in determining what kind of treatment the patient should receive. In recent times, the machine learning field has taken a spectacular twist with the acclivity of the Artificial Neural Networks (ANNs). These computational models which are biologically inspired are able to give a satisfactory performance in comparison with previous forms of artificial intelligence among various machine learning tasks. From the variants of ANN architecture, Convolutional Neural Network (CNN) is considered as one of the massive computational paradigm. Currently, CNN is used in various applications like image and video recognition, natural language processing and recommendation systems. In this paper, we propose a method to build an image classifier which uses the concept of convolution neural network in classifying the different phases of CML, which can help the doctor correctly identify the present condition of the patient so that appropriate treatment can be given.