A Survey on Transforming Blood Smear Analysis using Deep Learning

The importance of medical science are to examine, diagnose, and to cure various human diseases and also health issues. To upgrade medical care and therapies is its main goal. A blood smear is mainly used in pathology to identifies blood cell features. The purpose is to deposit a tiny layer of blood to a microscope slide and train it then to test it under a microscope. The accurate measurement of platelets, white blood cells (WBCs), and red blood cells (RBCs) aims in the detection of counts. Different problems, such as blood disorders like infections and diseases that affects the bone marrow, are identified by blood smears. Different techniques, such as Fast Pathology, Res Rand SVM technique, Deep Ensemble Learning and Deep Neural Networks, are available. Every article offers a deep learning, machine learning models. Certain preprocessing method are used to improve the performance of medical image data. The another different approach that illustrates deep ensemble learning techniques to enhance blood smear images. The framework that combines with multiple deep learning models to enhance categorization of robustness and accuracy in detecting ALL and its subtypes. It elaborates the importance of feature extraction and further more complex algorithms tare used to enhance model performance.