Adeleke Olumide T, Aworinde Halleluyah O, Oboh Mary, Oladosu Oladipo, Ayenigba Alaba B, Atobatele Bukola, Adeleke Oludamola V, Oladipo Tunde S, Adebayo Segun
Directorate of Health Services, Bowen University, Iwo, Nigeria.
Family Medicine Department, Bowen University Teaching Hospital, Ogbomoso, Nigeria.
Data Brief. 2024 Sep 17;57:110950. doi: 10.1016/j.dib.2024.110950. eCollection 2024 Dec.
Malaria remains a serious public health problem in many developing countries, particularly in Sub-Saharan Africa. Early detection and treatment of malaria are crucial in the fight against malaria in order to reduce morbidity and mortality, especially in the endemic regions. We set out to develop a simple, accurate, and efficient innovative diagnostic tool for malaria parasite identification that uses automated image processing to provide shorter diagnosis times while improving accuracy, efficiency, and standardization. Our primary goal in this study is to collect, curate, annotate and achieve blood smear images containing Plasmodium species for effective malaria diagnosis using Artificial Intelligent based system. The study curated 881 blood smear images which are categorized as positive and negative images.
疟疾在许多发展中国家,尤其是撒哈拉以南非洲地区,仍然是一个严重的公共卫生问题。疟疾的早期检测和治疗对于抗击疟疾至关重要,以便降低发病率和死亡率,特别是在疟疾流行地区。我们着手开发一种简单、准确且高效的创新诊断工具,用于疟原虫鉴定,该工具利用自动图像处理技术,在提高准确性、效率和标准化的同时缩短诊断时间。本研究的主要目标是收集、整理、标注并获取包含疟原虫种类的血涂片图像,以使用基于人工智能的系统进行有效的疟疾诊断。该研究整理了881张血涂片图像,这些图像被分类为阳性和阴性图像。