An algorithm to detect overlapping red blood cells for sickle cell disease diagnosis

In Africa, Uganda is among the countries with a high number of babies (20,000 babies) born sickle cell, contributing between 6.8% children cell every year worldwide and approximately 4.5% hemoglobinopathies worldwide. It estimated that by 2050, cases will increase 30% if no intervention put in place. To facilitate early detection anaemia, medical experts employ machine learning algorithms to detect abnormality. Previous research revealed for recognizing shape from blood smear fractional dimension, cannot cells applied on samples containing overlapping red cells. this research, authors developed an algorithm disease diagnosis. The uses canny edge double threshold techniques takes images as inputs these are anaemic. These have scale magnification (200×, 400×, 650×) pixel taken using microscope. was tested total 1000 digital overall accuracy, sensitivity specificity were 98.18%, 98.29% 97.98% respectively.