MalariaSD: Malaria-Infected Cell Images dataset

MalariaSD is a dataset encompassing various stages and classes of the malaria parasite, including Plasmodium falciparum, Plasmodium malariae, Plasmodium vivax, and Plasmodium ovale. These divisions consist of four distinct phases: ring, schizont, trophozoite, and gametocyte stages. The dataset serves as a valuable resource for researchers and healthcare professionals, offering crucial insights into the epidemiology, diagnosis, and treatment of malaria.The MP-IDB , a comprehensive collection of high-quality malaria parasite images, features the aforementioned four stages. This database presents an opportunity to develop and evaluate novel image processing and analysis techniques, aiming to enhance the accuracy and efficiency of malaria diagnosis. In our proposed paper, these images were used to create a new dataset using stable diffusion and advanced image processing methods.By utilizing stable diffusion, we generated a dataset comprising 16 distinct classes. Specifically, we focused on single-celled images and applied cropping and enhancement techniques to produce refined images. Subsequently, this new dataset underwent training through stable diffusion, resulting in the generation of 20 additional images for each class. As a result of our efforts, the image count of the original dataset increased significantly from an average of 12 images to 40 images per class.Through the expansion of the dataset using stable diffusion and image processing, our paper contributes to the advancement of malaria research. The augmented dataset provides a more comprehensive representation of the various stages and classes of malaria parasites, empowering researchers and healthcare professionals to enhance their understanding of malaria’s complexities and improve diagnostic methodologies. MalariaSD is a dataset encompassing various stages and classes of the malaria parasite, including Plasmodium falciparum, Plasmodium malariae, Plasmodium vivax, and Plasmodium ovale. These divisions consist of four distinct phases: ring, schizont, trophozoite, and gametocyte stages. The dataset serves as a valuable resource for researchers and healthcare professionals, offering crucial insights into the epidemiology, diagnosis, and treatment of malaria. The MP-IDB , a comprehensive collection of high-quality malaria parasite images, features the aforementioned four stages. This database presents an opportunity to develop and evaluate novel image processing and analysis techniques, aiming to enhance the accuracy and efficiency of malaria diagnosis. In our proposed paper, these images were used to create a new dataset using stable diffusion and advanced image processing methods. By utilizing stable diffusion, we generated a dataset comprising 16 distinct classes. Specifically, we focused on single-celled images and applied cropping and enhancement techniques to produce refined images. Subsequently, this new dataset underwent training through stable diffusion, resulting in the generation of 20 additional images for each class. As a result of our efforts, the image count of the original dataset increased significantly from an average of 12 images to 40 images per class. Through the expansion of the dataset using stable diffusion and image processing, our paper contributes to the advancement of malaria research. The augmented dataset provides a more comprehensive representation of the various stages and classes of malaria parasites, empowering researchers and healthcare professionals to enhance their understanding of malaria’s complexities and improve diagnostic methodologies.