Malaria is a contagious disease that affects millions of lives every year. Traditional diagnosis of malaria in laboratory requires an\nexperienced person and careful inspection to discriminate healthy and infected red blood cells (RBCs). It is also very timeconsuming\nand may produce inaccurate reports due to human errors. Cognitive computing and deep learning algorithms simulate\nhuman intelligence to make better human decisions in applications like sentiment analysis, speech recognition, face detection,\ndisease detection, and prediction. Due to the advancement of cognitive computing and machine learning techniques, they are now\nwidely used to detect and predict early disease symptoms in healthcare field. With the early prediction results, healthcare\nprofessionals can provide better decisions for patient diagnosis and treatment. Machine learning algorithms also aid the humans to\nprocess huge and complex medical datasets and then analyze them into clinical insights. This paper looks for leveraging deep\nlearning algorithms for detecting a deadly disease, malaria, for mobile healthcare solution of patients building an effective mobile\nsystem. The objective of this paper is to show how deep learning architecture such as convolutional neural network (CNN) which\ncan be useful in real-time malaria detection effectively and accurately from input images and to reduce manual labor with a mobile\napplication. To this end, we evaluate the performance of a custom CNN model using a cyclical stochastic gradient descent (SGD)\noptimizer with an automatic learning rate finder and obtain an accuracy of 97.30% in classifying healthy and infected cell images\nwith a high degree of precision and sensitivity. This outcome of the paper will facilitate microscopy diagnosis of malaria to a\nmobile application so that reliability of the treatment and lack of medical expertise can be solved.
Loading....