Recognition of parasite eggs in microscopic medical images based on YOLOv5

Abstract

Parasitosis is a disease caused by parasites invading the human body. Because of the different species and parasitic sites, it causes different pathological changes and clinical manifestations, and also causes other complications, which is harmful to human health. In clinical medicine, the diagnosis of parasitic diseases is mostly through etiological diagnosis, that is, through the detection of whether there are parasitic eggs in human feces. The diagnosis and treatment of parasitic diseases is a very important part of clinical medicine. At present, the recognition and classification of parasite eggs in human fecal microscopic images are mainly based on manual processing and machine learning, which are inefficient and easily affected by subjective factors, while machine learning can not deal with complex and changeable fecal environment. Here, an automatic recognition algorithm based on YOLOv5 for parasite eggs in fecal microscopic medical images is proposed. Experimental results show that the average accuracy of the model is 0.994 in our test set. In addition, the calculation time of each human fecal microscopic image under GPU is less than 25 ms, and the algorithm has higher accuracy and faster speed than the traditional machine learning algorithm. As such, it will help advance the etiological diagnosis of parasitic diseases and the development of therapeutic drugs.