Avian malaria, a mosquito-borne disease, is one of the most common veterinary threats in tropical regions, including South East Asia and South Asia 1. Plasmodium gallinaceum is an important causative agent of avian malaria, which causes more than 80% mortality if left untreated 2. The disease entails an economic and agricultural loss in poultry processes systems such as poor quality and quantity of meat and egg production1. Early and rapid routine screening for a safe and low-cost parasite infection may help prevent transmissions of the disease. Microscopic inspection is a gold standard approach and is widely used to examine and identify avian malaria-infected blood stages under thin-blood film examinations, the outcome of which is validated by highly trained and qualified technicians3. Nevertheless, the precise outcome of the above-mentioned procedure depends on the consistency of blood smearing and staining process. In addition, asymptomatic with low parasite infection can be time-consuming and may be undetectable or questionable as a result of inter/intra examiner variability 3. In addition, unspecific clinical symptoms of avian malaria, such as anorexia, anemia, and green stools, are often seen 1,4. While most of the nucleic acid-based amplification process, such as the polymerase chain reaction (PCR) assay, is an efficient method with a high sensitivity and malaria detection specificity, it requires an optimal consistency of genomic DNA and expensive tools such as thermocycler and electrophoresis apparatus 5–7. A professional molecular biologist is also required for further verification of the analysis. Consistently, the molecular biology approach could not always be affordable in low-income and resource-limited nations. As a result, an automated identification tool is desired
Artificial intelligence (AI) technology is currently a positive integration success in a diverse area of interest, including agriculture, medicine and veterinary medicine 8–15. Computer-aided diagnosis, AI subdivision, have been developed to identify human malaria infections and to classify their blood stage of the parasite growth. These can be used to assist clinical decision-making. Machine learning applications have also been studied in the documented veterinary field 16. Previous research have suggested a diagnostic tool in veterinary medicine focused on image analysis using machine learning techniques 17,18, such as fish disease diagnosis based microscopic method 19. The analysis referred to above is intended to enhance the inspection of the pathogen region in the image by means of object detection, which includes various image processing techniques, including noise reduction, edge detection, morphological operations and context extraction.
Deep learning is a revolutionary and groundbreaking approach that has been developed to incorporate a microscopic analysis for the veterinary medicine field 20,21. The methods are combined and tailored for individual datasets that differ in size of the region of interest. In specific, deep learning technology is applied to end-to-end methods of extraction of features and self-discovery. The deep learning algorithm is very popular and useful with the emergence of a high-power computing machine to be used to study the classification of images and the recognition of clinical issues. Several neural network models have been used to contend with the animal sector, Single-Shot MultiBox Detector (SSD) model used to evaluate the percentage of reticulocytes in cat’s samples 22, Alexnet for classification of fish dissease such as Epizootic ulcerative syndrome (EUS), Ichthyophthirius (Ich) and Columnaris.19. The works described above makes it possible to apply deep learning algorithms in the field of veterinary medicine.
Previously, several techniques for image-based identification and classification of malaria parasite infections have been discussed, such as dark stretching technique 23, modified fuzzy divergence technique, segmentation techniques 24, adaptive color segmentation and tree-based decision classification 25, segmentation, feature extraction, and SVM classifier 26, convolutional neural classification 27,28. Moreover, deep CNN research have been conducted under the channel color space segmentation method 29, deep belief network technique 30, the Faster Region-based Convolutional Neural Network (Faster R-CNN) 31, and the MATLAB-based Zach Threshold process for segmentation technique 32. Successfully, several studies have reported that the use of deep learning models to classify malaria parasites as automatic, rapid, and accurate approaches33–35. Interestingly, more than 95% of the accuracy is recorded in the detection of malaria-infected cells using three well-known CNNs, including LeNet, AlexNet, and GoogLeNet 36. The previous work demonstrated micro-platforms to study and identify the infected avian red blood cell by using morphological modifications on the RBC surface to reveal the phases of P. gallinaceum. Since malaria has been described as a disease of blood and blood-forming tissues, the blood film sample has been diagnosed to better understand different degrees of disease 37. Early rapid screening of parasite infection with reliable and also low cost development is required, which could help us deter the spread of the disease. Therefore, timely identification of malaria parasite in a blood smear test is crucial because it needs reliable and early diagnosis for successful containment 24.
A hybrid platform (VGG19 and SVM) recently demonstrated high performance in detecting infected and non-infected malaria parasite images, as observed follows: 93.44 per cent sensitivity; 92.92 per cent specificity; 89.95 per cent precision, 91.66 per cent F-score and 93.13 per cent accuracy 38. The outstanding performance of the hybrid algorithms mentioned previously motivates us to develop a hybrid object detection and classification method for further classifying avian malaria in Thailand.
In this work, we employ two-state learning techniques, which combine an object detection model based on YOLOv3 with one of four classification models, namely Darknet, Darknet19, Darknet19-448, and Densenet201, to characterize the avian malaria blood stages of P. gallinaceum. This contributes to the study's key contribution, which is to compare various image classification models using blood protozoa photographs, as qualitative and quantitative evidence for evaluating the proposed models. We compare the proposed model's performance to assist in the prediction of parasitized and healthy chicken RBCs in thin blood film photos. The stage of malaria progression would then be estimated, which determines the degree of infection as well as the probability of malaria transmission. In addition to author's knowledge, this research work is the first time that the CNNs deep learning model has been incorporated into the classification of clinical datasets relevant to clinical problems in P. gallenaceum-infected chicken. The study result would be useful for the disease diagnosis method in the poultry industry.