SKDrepaData-v2: Microscopic images of red blood cells for sickle cell disease research.

SKDrepaData-v2 is a publicly available dataset of 33,333 Giemsa-stained microscopic blood smear images collected from confirmed sickle cell disease (SCD) patients at UMRED (Université de Thiès, Senegal) and Diamniadio Children’s Hospital.   The dataset was annotated by expert hematopathologists into three exclusive classes:  - 11,106 Normal red blood cells,  - 11,473 Sickled cells,  - 11,253 Other abnormal cells (e.g., codocytes, ovalocytes, poikilocytes).   All images were preprocessed, resized to 224×224 px, and stored as individual image files. The dataset provides a balanced collection of morphologically diverse red blood cell samples.   SKDrepaData-v2 supports research on automated red blood cell classification, benchmarking of deep learning models, and the development of AI-based screening tools for sickle cell disease, with a focus on deployment in resource-limited settings.