A Survey on Sickle Cell Disease Detection and Analysis

Abstract

With increasing population numbers worldwide, sickle cell disease (SCD) continues to pose a serious global health problem, especially in sub-Saharan Africa, where close to 240,000 babies are born every year with the disease. SCD refers to a genetic disorder that leads to the distortion of hemoglobin molecules and subsequent deformity of red blood cells into rigid, sickle-like forms. The irregular blood cells block blood vessels and degenerate prematurely, causing health problems such as anemia, pain crises, infections, and organ dysfunction. It is critical to diagnose the condition early and correctly to manage and control it effectively.
Advancements in artificial intelligence and image processing have facilitated the development of automatic detection systems for SCD. Deep learning methods have shown great promise in recognizing deformities in microscopic images of blood smears with high accuracy and speed. Automatic detection models can aid healthcare practitioners through shortened diagnostic duration, reduced error rates, and easy-to-use tests in resource-limited areas. This survey paper provides an extensive analysis of deep learning solutions for the detection of sickle cell disease.