Sickle Cells AI Detection Computer Vision Model

Creator: Clint Fullido, Medical Student of SWU PHINMA Sickle Cell Identification by Using AI Detection Model.

Sickle cell anemia is an inherited disorder of the globin chains that causes hemolysis and chronic organ damage and is the most common form of sickle cell disease ( Mangla 2022). For many years, several techniques and assays are used for the detection and monitoring of the sickle disease. This include Peripheral blood smear, Solubility and Sickling, Capillary electrophoresis, High-performance liquid chromatography (HPLC), Amplification-refractory mutation system (ARMS) polymerase chain reaction (PCR) for prenatal analysis and Allele-Specific Recombinase Polymerase Amplification (Arishi 2021). Now with the advent of AI, various researchers are conducting deep learning or image processing/identification for faster and more accurate diagnosis of Sickle Cell Disease. The use of AI aids in a faster and more accurate diagnosis of SCD. Like in a image processing technique that analyses red blood cells by detecting sickle cells ( Chy 2019). Deep learning models like in the research of Alzubaidi et al. 2020, detect Sickle cell and classify the red blood cells based on the microscopic images with a 99.54%-99.98% accuracy. Although, AI maybe fast and accurate, sometimes there is still a need of a human expertise in diagnosing SCD. Challenges of detection using AI model is the lack of data to be used in training the AI, the software or the AI model used and many AI techniques only is able to detect sickle cells and not differentiate sickle cell diseases.

Sources:

Arishi, W. A., Alhadrami, H. A., & Zourob, M. (2021). Techniques for the Detection of Sickle Cell Disease: A Review. Micromachines, 12(5), 519. https://doi.org/10.3390/mi12050519 T. S. Chy and M. A. Rahaman, "Automatic Sickle Cell Anemia Detection Using Image Processing Technique," 2018 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE), Gazipur, Bangladesh, 2018, pp. 1-4, doi: 10.1109/ICAEEE.2018.8642984. Mangla A, Ehsan M, Agarwal N, et al. Sickle Cell Anemia. [Updated 2023 Sep 4]. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2023 Jan-. Available from: https://www.ncbi.nlm.nih.gov/books/NBK482164/ Inusa, B. P. D., Hsu, L. L., Kohli, N., Patel, A., Ominu-Evbota, K., Anie, K. A., & Atoyebi, W. (2019). Sickle Cell Disease-Genetics, Pathophysiology, Clinical Presentation and Treatment. International journal of neonatal screening, 5(2), 20. https://doi.org/10.3390/ijns5020020 Alzubaidi L., Fadhel M.A., Al-shamma O., Zhang J., Duan Y. Deep learning models for classification of red blood cells in microscopy images to aid in sickle cell anemia diagnosis. Electron. 2020;9:427. doi: 10.3390/electronics9030427