Classification for avian malaria parasite Plasmodium gallinaceum blood stages by using deep convolutional neural networks

The infection of an avian malaria parasite (Plasmodium gallinaceum) in domestic chickens presents a major threat to the poultry industry because it causes economic loss in both the quality and quantity of meat and egg production. Computer-aided diagnosis has been developed to automatically identify avian malaria infections and classify the blood infection stage development. In this study, four types of deep convolutional neural networks, namely Darknet, Darknet19, Darknet19-448 and Densenet201 are used to classify P. gallinaceum blood stages. We randomly collected a dataset of 12,761 single-cell images consisting of three parasite stages from ten-infected blood films stained by Giemsa. All images were confirmed by three well-trained examiners. The study mainly compared several image classification models and used both qualitative and quantitative data for the evaluation of the proposed models. In the model-wise comparison, the four neural network models gave us high values with a mean average accuracy of at least 97%. The Darknet can reproduce a superior performance in the classification of the P. gallinaceum development stages across any other model architectures. Furthermore, the Darknet has the best performance in multiple class-wise classification, with average values of greater than 99% in accuracy, specificity, and sensitivity. It also has a low misclassification rate (< 1%) than the other three models. Therefore, the model is more suitable in the classification of P. gallinaceum blood stages. The findings could help us create a fast-screening method to help non-experts in field studies where there is a lack of specialized instruments for avian malaria diagnostics.

Classification for Avian Malaria Parasite Plasmodium Gallinaceum Blood Stages by Using Deep Convolutional Neural Networks

The infection of an avian malaria parasite (Plasmodium gallinaceum) in domestic chickens presents a major threat to the poultry industry because it causes economic loss in both the quality and quantity of meat and egg production. Computer-aided diagnosis has been developed to automatically identify avian malaria infections and classify the blood infection stage development. In this study, four types of deep convolutional neural networks, namely Darknet, Darknet19, Darknet19-448 and Densenet201 are used to classify P. gallinaceum blood stages. We randomly collected a dataset of 12,761 single-cell images consisting of four parasite stages from ten-infected blood films stained by Giemsa. All images were confirmed by three well-trained examiners. The study mainly compared several image classification models and used both qualitative and quantitative data for the evaluation of the proposed models. In the model-wise comparison, the four neural network models gave us high values with the mean average accuracy of at least 97%. The Darknet can reproduce a superior performance in the classification of the P. gallinaceum development stages across any other model architectures. Furthermore, the Darknet has the best performance in multiple class-wise classification, with average values of greater than 99% in accuracy, specificity, and sensitivity. It also has a low misclassification rate (< 1%) than the other three models. Therefore, the model is more suitable in the classification of P. gallinaceum blood stages. The findings could help us create a fast screening method to help non-experts in field studies where there is a lack of specialized instruments for avian malaria diagnostics.

Classification for Avian Malaria Parasite Plasmodium Gallinaceum Blood Stages by Using Deep Convolutional Neural Networks

Background: The infections of an avian malaria parasite (Plasmodium gallinaceum) in domestic chickens presents a major threat to poultry industry because it cause economical loss in both quality and quantity of meat and egg productions. Deep learning algorithms have been developed to identify avian malaria infections and classify its blood stage development. Methods: In this study, four types of deep convolutional neural networks namely Darknet, Darknet19, darknet19_448x448 and Densenet 201 are used to classify P. gallinaceum blood stages. We randomly collected dataset of 10,548 single-cell images consisting of four parasite stages from ten-infected blood films stained by Giemsa. All images were confirmed by three well-trained examiners. Results: In the model-wise comparison, the four neural network models gave us high values in the mean average precision at least 95%. Darknet can reproduce a superior performance in classification of the P. gallinaceum development stages across any other model architectures. In addition, Darknet also has best performance in multiple class-wise classification, scoring the average values of greater than 99% in accuracy, specificity, sensitivity, precision, and F1-score.Conclusions: Therefore, Darknet model is more suitable in the classification of P. gallinaceum blood stages than the other three models. The result may contribute us to develop the rapid screening tool for further assist non-expert in filed study where is lack of specific instrument for avian malaria diagnostic.

Aedes aegypti SGS1 is critical for Plasmodium gallinaceum infection of both the mosquito midgut and salivary glands

Background The invasion of the mosquito salivary glands by Plasmodium sporozoites is a critical step that defines the success of malaria transmission and a detailed understanding of the molecules responsible for salivary gland invasion could be leveraged towards control of vector-borne pathogens. Antibodies directed against the mosquito salivary gland protein SGS1 have been shown to reduce Plasmodium gallinaceum sporozoite invasion of Aedes aegypti salivary glands, but the specific role of this protein in sporozoite invasion and in other stages of the Plasmodium life cycle remains unknown. Methods RNA interference and CRISPR/Cas9 were used to evaluate the role of A. aegypti SGS1 in the P. gallinaceum life cycle. Results Knockdown and knockout of SGS1 disrupted sporozoite invasion of the salivary gland. Interestingly, mosquitoes lacking SGS1 also displayed fewer oocysts. Proteomic analyses confirmed the abolishment of SGS1 in the salivary gland of SGS1 knockout mosquitoes and revealed that the C-terminus of the protein is absent in the salivary gland of control mosquitoes. In silico analyses indicated that SGS1 contains two potential internal cleavage sites and thus might generate three proteins. Conclusion SGS1 facilitates, but is not essential for, invasion of A. aegypti salivary glands by P. gallinaceum and has a dual role as a facilitator of parasite development in the mosquito midgut. SGS1 could, therefore, be part of a strategy to decrease malaria transmission by the mosquito vector, for example in a transgenic mosquito that blocks its interaction with the parasite.

Molecular Detection of Avian Malaria (Plasmodium gallinaceum) in Local Domesticated Breed Chickens (Gallus gallus domesticus) in Baghdad

This study was conducted to investigate the prevalence of avian malaria (Plasmodium gallinaceum) in the local domesticated breed chickens (Gallus gallus domesticus) that were purchased from the local markets in Baghdad city, using 100 blood samples which were collected from the wing vein, and kept in EDTA-K2 tubes for conventional PCR analysis during the period extended from 1 /10 / 2018 till 31/ 3 / 2019. Total infection rate was 18% (18/100), which were divided into males 20.00% and in females 16.00%. The eight isolates were recorded in the GenBank under accession numbers ID: MN082405.1, MN082406.1, MN082407.1, MN082408.1, MN082409.1, MN082410.1, MN082411.1, and MN082412.1 with identity 99.20 - 99.87% and with other isolates (United Kingdom and USA) 99.34 - 99.88 %. In conclusion, Plasmodium gallinaceum may have a moderate spread in local domesticated breed chicken at Baghdad.