Search

Leukemia falls in the category of life-threatening disease. Moreover, it is difficult to detect it in its initial stage, so its prognosis and treatment becomes even more difficult. Machine Learning has found its application in almost all domains of our life. One of the most crucial domains is medical diagnosis. It was found from various studies that computational leukemia detection has been performed on various types of datasets like clinical data, genomic data, micro-array dataset, peripheral blood smear images, and flow-cytometry data. In the present study, we limit the domain of study to the detection of leukemia from blood cell images only. This paper presents a thorough review of machine learning and deep learning algorithms in the diagnosis of leukemia from microscopic blood cell images. The paper also discusses the publicly available datasets used by various researchers in this domain and various algorithms used for disease detection and classification. This paper concludes that deep learning gives the best result when it comes to diagnosis of disease from peripheral blood smear images. [ABSTRACT FROM AUTHOR]

In this paper we have taken different types of system of fractional delay differential equations with coefficient matrices considering constant as well as variable entries and discussed their oscillatory and non oscillatory behaviour. By giving suitable examples, theoretical results have been justified. [ABSTRACT FROM AUTHOR]