Accurate Recognition of Leukemia Sub-types by Utilizing a Transfer Learned Deep Convolutional Neural Network

Leukemia has been causing more than 350,000 deaths per year despite holding a notable number of studies on the prognosis, diagnosis, and therapy for Leukemia. Computerized Leukemia disclosure may change the circumstances, as steps can be obtained instantly, hence, precise identification of Leukemia has been a domain of concern for researchers for nearly a decade now. Lately, many contributions have been bestowed to the scientific society concerning the identification of Leukemia. But with the expansion and development of the datasets, the demand for accurate identification of Leukemia is becoming more demanding every day. In this research, we examined a Leukemia sub-types dataset that consists of three kinds of Leukemia individuals. We introduced and implemented a modified DenseNet-201 design and produced an overall accuracy of 99.56% which exceeded all the previous investigations.