Malaria is a significant disease that affects both animals and humans. The four main Plasmodium species that cause human malaria are Plasmodium falciparum, Plasmodium vivax, Plasmodium malariae, and Plasmodium ovale. Plasmodium knowlesi, a parasite typically infecting forest macaque monkeys, was recently revealed to be able to be transmitted by anophelines and provoke malaria in humans. This provides an increasing risk of spreading the disease to areas previously unaffected with it and infecting people during the increasingly popular travels abroad. Microscopic examination remains one of the most often used methods for its laboratory confirmation. These tests, however, should be performed immediately after receiving samples from a firstcontact doctor to allow immediate therapy. This research presents a novel, semantic segmentation neural network architecture designed to quickly create a classification mask, giving the doctor information about the position, shape, and possible affiliation of detected elements. The evaluation method is based on a light microscope imagery and was created to overcome problems resulting from the human diagnosis specifics. There are 3 abstract classes containing healthy cells, cells with malaria and background. The outputted mask can be later mapped to a more readable form with the inclusion of contrasting colors, next to an original image for quick validation. Such an approach allows for semi-automatic recognition of possible disease, nevertheless still giving the final verdict to the specialist. The developed solution has achieved a high recognition accuracy of 96.65%, while the computer power requirements are kept at a minimum. The proposed solution can help reduce misclassification rates by providing additional data for the doctor and speed up the entire process with the early diagnosis made by a deep learning model.