CNN-based classification of 150 x 150 cell images
Malaria parasites are identified by microscopic examination of a drop of the patient’s blood, spread out as a “blood smear” on a microscope slide.
Prior to examination, the specimen is stained to give the parasites a distinctive appearance. This technique remains the gold standard for laboratory confirmation of malaria. Accuracy depends on the quality of the reagents, of the microscope, and on the experience of the laboratorian.
The objective of this classifier is to automate the classification of uninfected and parasitized cells from a 150 x 150 sample image. Our model consists of a CNN built using Keras and scikit-learn and trained on Kaggle's "Malaria Cell Images" dataset.
Infected (A-left) vs uninfected cell (B-right), along with corresponding predictions