Implementation of Potential Leukemia Detection using Recurrent Neural Networks with Blood Cell Counting
Madasu Naga Venkata Akanksha, Srinivas Bachu, M. Aravind Kumar, Naluguru Udaya Kumar · 2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT) · 2022
A total of 412,000 persons are expected to be diagnosed with leukemia worldwide, with acute lymphoblastic leukemia accounting for around 12% of all cases. Thus, the early detection of leukemia can save millions of populations. This article mainly focusing on blood cell counting and detection of Leukemia using deep learning mechanisms. Initially, the images are preprocessed using median filters and segmented using RGB-Otsu's approach. Then, the features are extracted using scale-invariant feature transform (SIFT) and these features are applied to recurrent neural network (RNN) for classification. Finally, the proposed method resulted in superior performance as compared to the state of art machine learning approaches.