Automatic Recognition of Human Parasite Cysts on Microscopic Stools Images using Principal Component Analysis and Probabilistic Neural Network

Abstract

Abstract-Parasites live in a host and get its food from or at the expensive of that host. Cysts represent a form of resistance and spread of parasites. The manual diagnosis of microscopic stools images is time-consuming and depends on the human expert. In this paper, we propose an automatic recognition system that can be used to identify various intestinal parasite cysts from their microscopic digital images. We employ image pixel feature to train the probabilistic neural networks (PNN). Probabilistic neural networks are suitable for classification problems. The main novelty is the use of features vectors extracted directly from the image pixel. For this goal, microscopic images are previously segmented to separate the parasite image from the background. The extracted parasite is then resized to 12x12 image features vector. For dimensionality reduction, the principal component analysis basis projection has been used. 12x12 extracted features were orthogonalized into two principal components variables that consist the input vector of the PNN. The PNN is trained using 540 microscopic images of the parasite. The proposed approach was tested successfully on 540 samples of protozoan cysts obtained from 9 kinds of intestinal parasites.

Advances Towards Automatic Detection and Classification of Parasites Microscopic Images Using Deep Convolutional Neural Network: Methods, Models and Research Directions

“… References Date Method Type of features Objective Parasites (species) Dataset details Evaluation metrics Limitations Future scope [ 31 ] 2001 ANN Pixel intensity Automatic detection of human helminth eggs Helminth eggs C = 2 T.I = 82 Acc. = 86.1% Small dataset An enhanced model proposed to classify helminth eggs [ 32 ] 2001 ANN Pixel intensity Automatic Identification of human helminth eggs Helminth Eggs C = 7 T.I = 82 Det. = 86.1% Small dataset To improve results large dataset may be used [ 34 ] 2005 ANN Shape feature Classification of Giardia cyst (GC) and Cryptosporidium oocyst(CO) Giardia cyst and Cryptosporidium oocyst C = 2 Tr.…”

“…In the same year, Tchinda et al [ 32 ] presented a machine learning technique to recognize intestinal parasite cysts from microscopic images. Probabilistic neural network approach trained by using image pixels feature was employed.…”

Primary Mobile Image Analysis of Human Intestinal Worm Detection

“…Features such as shape, shell, smoothness, and size are extracted as input for the classifier to resulting in 94% and 93% success rate for Trichuris trichiura and Ascaris lumbricoides respectively. The method of probabilistic neural networks was used by Saha, Tchiotsop, Tchinda, Wolf, & Noubom (2015) to recognize the cyst of nine human intestinal helminth parasites. Their study recorded a 100% correct classification rate after training their network with an image pixel feature.…”