Comparison of Deep Learning Alexnet and Support Vector Machine to Classify Severity of Sickle Cell Anemia

Sickle cell anemia (SCA) is a serious hematological blood disorder, where affected patients arefrequently hospitalized throughout a lifetime. Most of the patient's life span reduced, and somebecome addict based on the nature of strong analgesic that is taken by the concern patients,which they all have strong side effects. The existing method of severity classification for SCApatient is done manually through a microscope which is time-consuming, tedious, prone to error,and require a trained hematologist. The affected patient has many cell shapes that showimportant biomechanical characteristics of patient severity level. The main purpose of the studyis to develop an automated severity level classification method of SCA patients by comparingdeep learning AlexNet and Support Vector Machine (SVM) to enable present the percentage ofeach cell present in blood smear image. Hence, having an effective way of classifying theabnormalities present in the SCA disease based on the level of patient severity to give a betterinsight into managing the concerned patient's life. The study was performed with 182 SCApatients (over 11,000 single RBC images) with 14 classes of abnormalities and a class of normalcells to develop a shape factor quantification and general multiscale shape analysis to classify thepatient based on severity level. As a result, it was found that the proposed framework can detect85.4% abnormalities in SCA patient blood smear in automated manner when compared withSupport Vector Machine (SVM) method with 71.9%. Hence, the system classifies the severity ofSCA patient automatically and reduce the time and eye stress with performance AlexNet modelperformance of 95.1% accuracy, 99.1% specificity, and 98.5% precision value.