A machine learning-based system for detecting leishmaniasis in microscopic images

Background Leishmaniasis, a disease caused by a protozoan, causes numerous deaths in humans each year. After malaria, leishmaniasis is known to be the deadliest parasitic disease globally. Direct visual detection of leishmania parasite through microscopy is the frequent method for diagnosis of this disease. However, this method is time-consuming and subject to errors. This study was aimed to develop an artificial intelligence-based algorithm for automatic diagnosis of leishmaniasis. Methods We used the Viola-Jones algorithm to develop a leishmania parasite detection system. The algorithm includes three procedures: feature extraction, integral image creation, and classification. Haar-like features are used as features. An integral image was used to represent an abstract of the image that significantly speeds up the algorithm. The adaBoost technique was used to select the discriminate features and to train the classifier. Results A 65% recall and 50% precision was concluded in the detection of macrophages infected with the leishmania parasite. Also, these numbers were 52% and 71%, respectively, related to amastigotes outside of macrophages. Conclusion The developed system is accurate, fast, easy to use, and cost-effective. Therefore, artificial intelligence might be used as an alternative for the current leishmanial diagnosis methods.

Malaria Parasite Detection in Thick Blood Smears using Deep Learning

Malaria parasitized detection is very important to detect as there are so many deaths due to false detection of malaria in medical reports. So analysis has gained a lot of attention in recent years. Detection of malaria is important as fast as possible because detecting malaria is difficult in blood smears. Our idea is to build a transfer learning model and detect the thick blood smears whether the presence of malaria parasites in a drop of blood. The data consists of 5000 each infected and uninfected data obtained from the NIH website. In this paper, I propose to use three different types of neural networks for the performance evaluation of the malaria data by transfer learning using CNN, VGG19, and fine-tuned VGG19. Transfer learning model performed well among various other models by achieving a precision of 98 percent and an f-1 score of 96 percent.

Malaria Parasite Detection using Efficient Neural Ensembles

Caused by the bite of the Anopheles mosquito infected with the parasite of genus Plasmodium, malaria has remained a major burden towards healthcare for years with an approximate 400,000 deaths reported globally every year. The traditional diagnosis process for malaria involves an examination of the blood smear slide under the microscope. This process is not only time consuming but also requires pathologists to be highly skilled in their work. Timely diagnosis and availability of robust diagnostic facilities and skilled laboratory technicians are very much vital to reduce the mortality rate. This study aims to build a robust system by applying deep learning techniques such as transfer learning and snapshot ensembling to automate the detection of the parasite in the thin blood smear images. All the models were evaluated against the following metrics - F1 score, Accuracy, Precision, Recall, Mathews Correlation Coefficient (MCC), Area Under the Receiver Operating Characteristics (AUC-ROC) and the Area under the Precision Recall curve (AUC-PR). The snapshot ensembling model created by combining the snapshots of the EfficientNet-B0 pre-trained model outperformed every other model achieving a f1 score - 99.37%, precision - 99.52% and recall - 99.23%. The results show the potential of model ensembles which combine the predictive power of multiple weal models to create a single efficient model that is better equipped to handle the real world data. The GradCAM experiment displayed the gradient activation maps of the last convolution layer to visually explicate where and what a model sees in an image to classify them into a particular class. The models in this study correctly activate the stained parasitic region of interest in the thin blood smear images. Such visuals make the model more transparent, explainable, and trustworthy which are very much essential for deploying AI based models in the healthcare network.

Malaria Parasite Detection using Efficient Neural Ensembles

Caused by the bite of the Anopheles mosquito infected with the parasite of genus Plasmodium, malaria has remained a major burden towards healthcare for years with an approximate 400,000 deaths reported globally every year. The traditional diagnosis process for malaria involves an examination of the blood smear slide under the microscope. This process is not only time consuming but also requires pathologists to be highly skilled in their work. Timely diagnosis and availability of robust diagnostic facilities and skilled laboratory technicians are very much vital to reduce the mortality rate. This study aims to build a robust system by applying deep learning techniques such as transfer learning and snapshot ensembling to automate the detection of the parasite in the thin blood smear images. All the models were evaluated against the following metrics - F1 score, Accuracy, Precision, Recall, Mathews Correlation Coefficient (MCC), Area Under the Receiver Operating Characteristics (AUC-ROC) and the Area under the Precision Recall curve (AUC-PR). The snapshot ensembling model created by combining the snapshots of the EfficientNet-B0 pre-trained model outperformed every other model achieving a f1 score - 99.37%, precision - 99.52% and recall - 99.23%. The results show the potential of model ensembles which combine the predictive power of multiple weal models to create a single efficient model that is better equipped to handle the real world data. The GradCAM experiment displayed the gradient activation maps of the last convolution layer to visually explicate where and what a model sees in an image to classify them into a particular class. The models in this study correctly activate the stained parasitic region of interest in the thin blood smear images. Such visuals make the model more transparent, explainable, and trustworthy which are very much essential for deploying AI based models in the healthcare network.

Identification of molecular biomarkers associated with disease progression in the testis of bulls infected with Besnoitia besnoiti

Breeding bulls infected with Besnoitia besnoiti may develop sterility during either acute or chronic infection. The aim of this study was to investigate the molecular pathogenesis of B. besnoiti infection with prognosis value in bull sterility. Accordingly, five well-characterized groups of naturally and experimentally infected males were selected for the study based on clinical signs and lesions compatible with B. besnoiti infection, serological results and parasite detection. A broad panel of molecular markers representative of endothelial activation and fibrosis was investigated and complemented with a histopathological approach that included conventional histology and immunohistochemistry. The results indicated the predominance of an intense inflammatory infiltrate composed mainly of resident and recruited circulating macrophages and to a lesser extent of CD3+ cells in infected bulls. In addition, a few biomarkers were associated with acute, chronic or subclinical bovine besnoitiosis. The testicular parenchyma showed a higher number of differentially expressed genes in natural infections (acute and chronic infections) versus scrotal skin in experimental infections (subclinical infection). In subclinical infections, most genes were downregulated except for the CCL24 and CXCL2 genes, which were upregulated. In contrast, the acute phase was mainly characterized by the upregulation of IL-1α, IL-6 and TIMP1, whereas in the chronic phase, the upregulation of ICAM and the downregulation of MMP13, PLAT and IL-1α were the most relevant findings. Macrophages could be responsible for the highest level of gene regulation in the testicular parenchyma of severely affected and sterile bulls, and all these genes could be prognostic markers of sterility.