Automatic classification and grading of canine tracheal collapse on thoracic radiographs by using deep learning.

Tracheal collapse is a chronic and progressively worsening disease; the severity of clinical symptoms experienced by affected individuals depends on the degree of airway collapse. Cutting-edge automated tools are necessary to modernize disease screening using radiographs across various veterinary settings, such as animal clinics and hospitals. This is primarily due to the inherent challenges associated with interpreting uncertainties among veterinarians. In this study, an artificial intelligence model was developed to screen canine tracheal collapse using archived lateral cervicothoracic radiographs. This model can differentiate between a normal and collapsed trachea, ranging from early to severe degrees. The you-only-look-once (YOLO) models, including YOLO v3, YOLO v4, and YOLO v4 tiny, were used to train and test data sets under the in-house XXX platform. The results showed that the YOLO v4 tiny-416 model had satisfactory performance in screening among the normal trachea, grade 1-2 tracheal collapse, and grade 3-4 tracheal collapse with 98.30% sensitivity, 99.20% specificity, and 98.90% accuracy. The area under the curve of the precision-recall curve was >0.8, which demonstrated high diagnostic accuracy. The intraobserver agreement between deep learning and radiologists was κ = 0.975 (P < .001), with all observers having excellent agreement (κ = 1.00, P < .001). The intraclass correlation coefficient between observers was >0.90, which represented excellent consistency. Therefore, the deep learning model can be a useful and reliable method for effective screening and classification of the degree of tracheal collapse based on routine lateral cervicothoracic radiographs.

Dynamics of Plasmodium vivax populations in border areas of the Greater Mekong sub-region during malaria elimination.

BACKGROUND: Countries within the Greater Mekong Sub-region (GMS) of Southeast Asia have committed to eliminating malaria by 2030. Although the malaria situation has greatly improved, malaria transmission remains at international border regions. In some areas, Plasmodium vivax has become the predominant parasite. To gain a better understanding of transmission dynamics, knowledge on the changes of P. vivax populations after the scale-up of control interventions will guide more effective targeted control efforts. METHODS: This study investigated genetic diversity and population structures in 206 P. vivax clinical samples collected at two time points in two international border areas: the China-Myanmar border (CMB) (n = 50 in 2004 and n = 52 in 2016) and Thailand-Myanmar border (TMB) (n = 50 in 2012 and n = 54 in 2015). Parasites were genotyped using 10 microsatellite markers. RESULTS: Despite intensified control efforts, genetic diversity remained high (HE = 0.66-0.86) and was not significantly different among the four populations (P > 0.05). Specifically, HE slightly decreased from 0.76 in 2004 to 0.66 in 2016 at the CMB and increased from 0.80 in 2012 to 0.86 in 2015 at the TMB. The proportions of polyclonal infections varied significantly among the four populations (P < 0.05), and showed substantial decreases from 48.0% in 2004 to 23.7 at the CMB and from 40.0% in 2012 to 30.7% in 2015 at the TMB, with corresponding decreases in the multiplicity of infection. Consistent with the continuous decline of malaria incidence in the GMS over time, there were also increases in multilocus linkage disequilibrium, suggesting more fragmented and increasingly inbred parasite populations. There were considerable genetic differentiation and sub-division among the four tested populations. Temporal genetic differentiation was observed at each site (FST = 0.081 at the CMB and FST = 0.133 at the TMB). Various degrees of clustering were evident between the older parasite samples collected in 2004 at the CMB and the 2016 CMB and 2012 TMB populations, suggesting some of these parasites had shared ancestry. In contrast, the 2015 TMB population was genetically distinctive, which may reflect a process of population replacement. Whereas the effective population size (Ne) at the CMB showed a decrease from 4979 in 2004 to 3052 in 2016 with the infinite allele model, the Ne at the TMB experienced an increase from 6289 to 10,259. CONCLUSIONS: With enhanced control efforts on malaria, P. vivax at the TMB and CMB showed considerable spatial and temporal differentiation, but the presence of large P. vivax reservoirs still sustained genetic diversity and transmission. These findings provide new insights into P. vivax transmission dynamics and population structure in these border areas of the GMS. Coordinated and integrated control efforts on both sides of international borders are essential to reach the goal of regional malaria elimination.

A novel approach for identification of zoonotic trypanosome utilizing deep metric learning and vector database-based image retrieval system.

Trypanosomiasis, a significant health concern in South America, South Asia, and Southeast Asia, requires active surveys to effectively control the disease. To address this, we have developed a hybrid model that combines deep metric learning (DML) and image retrieval. This model is proficient at identifying Trypanosoma species in microscopic images of thin-blood film examinations. Utilizing the ResNet50 backbone neural network, a trained-model has demonstrated outstanding performance, achieving an accuracy exceeding 99.71 % and up to 96 % in recall. Acknowledging the necessity for automated tools in field scenarios, we demonstrated the potential of our model as an autonomous screening approach. This was achieved by using prevailing convolutional neural network (CNN) applications, and vector database based-images returned by the KNN algorithm. This achievement is primarily attributed to the implementation of the Triplet Margin Loss function as 98 % of precision. The robustness of the model demonstrated in five-fold cross-validation highlights the ResNet50 neural network, based on DML, as a state-of-the-art CNN model as AUC >98 %. The adoption of DML significantly improves the performance of the model, remaining unaffected by variations in the dataset and rendering it a useful tool for fieldwork studies. DML offers several advantages over conventional classification model to manage large-scale datasets with a high volume of classes, enhancing scalability. The model has the capacity to generalize to novel classes that were not encountered during training, proving particularly advantageous in scenarios where new classes may consistently emerge. It is also well suited for applications requiring precise recognition, especially in discriminating between closely related classes. Furthermore, the DML exhibits greater resilience to issues related to class imbalance, as it concentrates on learning distances or similarities, which are more tolerant to such imbalances. These contributions significantly make the effectiveness and practicality of DML model, particularly in in fieldwork research.

Automatic identification of medically important mosquitoes using embedded learning approach-based image-retrieval system.

Mosquito-borne diseases such as dengue fever and malaria are the top 10 leading causes of death in low-income countries. Control measure for the mosquito population plays an essential role in the fight against the disease. Currently, several intervention strategies; chemical-, biological-, mechanical- and environmental methods remain under development and need further improvement in their effectiveness. Although, a conventional entomological surveillance, required a microscope and taxonomic key for identification by professionals, is a key strategy to evaluate the population growth of these mosquitoes, these techniques are tedious, time-consuming, labor-intensive, and reliant on skillful and well-trained personnel. Here, we proposed an automatic screening, namely the deep metric learning approach and its inference under the image-retrieval process with Euclidean distance-based similarity. We aimed to develop the optimized model to find suitable miners and suggested the robustness of the proposed model by evaluating it with unseen data under a 20-returned image system. During the model development, well-trained ResNet34 are outstanding and no performance difference when comparing five data miners that showed up to 98% in its precision even after testing the model with both image sources: stereomicroscope and mobile phone cameras. The robustness of the proposed-trained model was tested with secondary unseen data which showed different environmental factors such as lighting, image scales, background colors and zoom levels. Nevertheless, our proposed neural network still has great performance with greater than 95% for sensitivity and precision, respectively. Also, the area under the ROC curve given the learning system seems to be practical and empirical with its value greater than 0.960. The results of the study may be used by public health authorities to locate mosquito vectors nearby. If used in the field, our research tool in particular is believed to accurately represent a real-world scenario.

Superior Auto-Identification of Trypanosome Parasites by Using a Hybrid Deep-Learning Model.

Trypanosomiasis is a significant public health problem in several regions across the world, including South Asia and Southeast Asia. The identification of hotspot areas under active surveillance is a fundamental procedure for controlling disease transmission. Microscopic examination is a commonly used diagnostic method. It is, nevertheless, primarily reliant on skilled and experienced personnel. To address this issue, an artificial intelligence (AI) program was introduced that makes use of a hybrid deep learning technique of object identification and object classification neural network backbones on the in-house low-code AI platform (CiRA CORE). The program can identify and classify the protozoan trypanosome species, namely Trypanosoma cruzi, T. brucei, and T. evansi, from oil-immersion microscopic images. The AI program utilizes pattern recognition to observe and analyze multiple protozoa within a single blood sample and highlights the nucleus and kinetoplast of each parasite as specific characteristic features using an attention map. To assess the AI program's performance, two unique modules are created that provide a variety of statistical measures such as accuracy, recall, specificity, precision, F1 score, misclassification rate, receiver operating characteristics (ROC) curves, and precision versus recall (PR) curves. The assessment findings show that the AI algorithm is effective at identifying and categorizing parasites. By delivering a speedy, automated, and accurate screening tool, this technology has the potential to transform disease surveillance and control. It could also assist local officials in making more informed decisions on disease transmission-blocking strategies.

Simultaneous phenotyping of five Rh red blood cell antigens on a paper-based analytical device combined with deep learning for rapid and accurate interpretation.

Both the ABO and Rhesus (Rh) blood groups play crucial roles in blood transfusion medicine. Herein, we report a simple and low-cost paper-based analytical device (PAD) for phenotyping red blood cell (RBC) antigens. Using this Rh typing format, 5 Rh antigens on RBCs can be simultaneously detected and macroscopically visualized within 12 min. The proposed Rh phenotyping relies on the presence or absence of hemagglutination in the sample zones after immobilizing the antibodies targeting each Rh antigen. The PAD was optimized in terms of filter paper type, antibodies, and distance of the visualization zone. In this study, the optimal conditions were Whatman filter paper Grade 4; anti-D, -C, -E, -c, and -e antibodies; RBC suspension of 30%; and a visualization zone of 1 cm above the sample zone. The accuracy of simultaneously phenotyping the five Rh RBC antigens in the blood samples (n = 4692) was 99.19%, comparable with the accuracy of the gold-standard tube method used by blood bank laboratories in several regions of Thailand. Furthermore, decision making based on this method can be assisted by deep learning. After implementing a two-stage objective detection algorithm (YOLO v4-tiny) and classification model (DenseNet-201), the ambiguous images (n = 48) were interpreted with 100% accuracy. The PAD integrated with customized-region convolutional neural networks can reduce the interpretation discrepancies in RBC antigen phenotyping in any laboratory.

Automatic recognition of parasitic products in stool examination using object detection approach.

Background: Object detection is a new artificial intelligence approach to morphological recognition and labeling parasitic pathogens. Due to the lack of equipment and trained personnel, artificial intelligence innovation for searching various parasitic products in stool examination will enable patients in remote areas of undeveloped countries to access diagnostic services. Because object detection is a developing approach that has been tested for its effectiveness in detecting intestinal parasitic objects such as protozoan cysts and helminthic eggs, it is suitable for use in rural areas where many factors supporting laboratory testing are still lacking. Based on the literatures, the YOLOv4-Tiny produces faster results and uses less memory with the support of low-end GPU devices. In comparison to the YOLOv3 and YOLOv3-Tiny models, this study aimed to propose an automated object detection approach, specifically the YOLOv4-Tiny model, for automatic recognition of intestinal parasitic products in stools. Methods: To identify protozoan cysts and helminthic eggs in human feces, the three YOLO approaches; YOLOv4-Tiny, YOLOv3, and YOLOv3-Tiny, were trained to recognize 34 intestinal parasitic classes using training of image dataset. Feces were processed using a modified direct smear method adapted from the simple direct smear and the modified Kato-Katz methods. The image dataset was collected from intestinal parasitic objects discovered during stool examination and the three YOLO models were trained to recognize the image datasets. Results: The non-maximum suppression technique and the threshold level were used to analyze the test dataset, yielding results of 96.25% precision and 95.08% sensitivity for YOLOv4-Tiny. Additionally, the YOLOv4-Tiny model had the best AUPRC performance of the three YOLO models, with a score of 0.963. Conclusion: This study, to our knowledge, was the first to detect protozoan cysts and helminthic eggs in the 34 classes of intestinal parasitic objects in human stools.

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.

Deep learning approaches for challenging species and gender identification of mosquito vectors.

Microscopic observation of mosquito species, which is the basis of morphological identification, is a time-consuming and challenging process, particularly owing to the different skills and experience of public health personnel. We present deep learning models based on the well-known you-only-look-once (YOLO) algorithm. This model can be used to simultaneously classify and localize the images to identify the species of the gender of field-caught mosquitoes. The results indicated that the concatenated two YOLO v3 model exhibited the optimal performance in identifying the mosquitoes, as the mosquitoes were relatively small objects compared with the large proportional environment image. The robustness testing of the proposed model yielded a mean average precision and sensitivity of 99% and 92.4%, respectively. The model exhibited high performance in terms of the specificity and accuracy, with an extremely low rate of misclassification. The area under the receiver operating characteristic curve (AUC) was 0.958 ± 0.011, which further demonstrated the model accuracy. Thirteen classes were detected with an accuracy of 100% based on a confusion matrix. Nevertheless, the relatively low detection rates for the two species were likely a result of the limited number of wild-caught biological samples available. The proposed model can help establish the population densities of mosquito vectors in remote areas to predict disease outbreaks in advance.

Identification of blood meal of field caught Aedes aegypti (L.) by multiplex PCR.

Laboratory bred female Aedes aegypti (L.) was used to determine sensitivity of multiplex PCR for detecting human blood meal. Human blood DNA was detected in live fully fed mosquitoes until 3 days after blood feeding, and for 4 weeks when stored at -20 degrees C. Among 890 field caught female mosquito samples examined for vertebrate DNA by multiplex PCR, results were positive for human, pig, dog, cow and mixture of 2 host DNA at 86.1, 3.4, 2.1, 1.0 and 3.6%, respectively, while 3.9% of the samples were negative. Blood feeding pattern must be considered when mosquito control strategies become employed.

Evolution of the Plasmodium vivax multidrug resistance 1 gene in the Greater Mekong Subregion during malaria elimination.

BACKGROUND: The malaria elimination plan of the Greater Mekong Subregion (GMS) is jeopardized by the increasing number of Plasmodium vivax infections and emergence of parasite strains with reduced susceptibility to the frontline drug treatment chloroquine/primaquine. This study aimed to determine the evolution of the P. vivax multidrug resistance 1 (Pvmdr1) gene in P. vivax parasites isolated from the China-Myanmar border area during the major phase of elimination. METHODS: Clinical isolates were collected from 275 P. vivax patients in 2008, 2012-2013 and 2015 in the China-Myanmar border area and from 55 patients in central China. Comparison was made with parasites from three border regions of Thailand. RESULTS: Overall, genetic diversity of the Pvmdr1 was relatively high in all border regions, and over the seven years in the China-Myanmar border, though slight temporal fluctuation was observed. Single nucleotide polymorphisms previously implicated in reduced chloroquine sensitivity were detected. In particular, M908L approached fixation in the China-Myanmar border area. The Y976F mutation sharply decreased from 18.5% in 2008 to 1.5% in 2012-2013 and disappeared in 2015, whereas F1076L steadily increased from 33.3% in 2008 to 77.8% in 2015. While neutrality tests suggested the action of purifying selection on the pvmdr1 gene, several likelihood-based algorithms detected positive as well as purifying selections operating on specific amino acids including M908L, T958M and F1076L. Fixation and selection of the nonsynonymous mutations are differently distributed across the three border regions and central China. Comparison with the global P. vivax populations clearly indicated clustering of haplotypes according to geographic locations. It is noteworthy that the temperate-zone parasites from central China were completely separated from the parasites from other parts of the GMS. CONCLUSIONS: This study showed that P. vivax populations in the China-Myanmar border has experienced major changes in the Pvmdr1 residues proposed to be associated with chloroquine resistance, suggesting that drug selection may play an important role in the evolution of this gene in the parasite populations.

Genetic diversity of the Plasmodium vivax multidrug resistance 1 gene in Thai parasite populations.

Plasmodium vivax resistance to chloroquine (CQ) was first reported over 60 years ago. Here we analyzed sequence variations in the multidrug resistance 1 gene (Pvmdr1), a putative molecular marker for P. vivax CQ resistance, in field isolates collected from three sites in Thailand during 2013-2016. Several single nucleotide polymorphisms previously implicated in reduced CQ sensitivity were found. These genetic variations encode amino acids in the two nucleotide-binding domains as well as the transmembrane domains of the protein. The high level of genetic diversity of Pvmdr1 provides insights into the evolutionary history of this gene. Specifically, there was little evidence of positive selection at amino acid F1076L in global isolates to be promoted as a possible marker for CQ resistance. Population genetic analysis clearly divided the parasites into eastern and western populations, which is consistent with their geographical separation by the central malaria-free area of Thailand. With CQ-primaquine remaining as the frontline treatment for vivax malaria in all regions of Thailand, such a population subdivision could be shaped and affected by the current drugs for P. falciparum since mixed P. falciparum/P. vivax infections often occur in this region.

Substantial population structure of Plasmodium vivax in Thailand facilitates identification of the sources of residual transmission.

BACKGROUND: Plasmodium vivax transmission in Thailand has been substantially reduced over the past 10 years, yet it remains highly endemic along international borders. Understanding the genetic relationship of residual parasite populations can help track the origins of the parasites that are reintroduced into malaria-free regions within the country. METHODOLOGY/RESULTS: A total of 127 P. vivax isolates were genotyped from two western provinces (Tak and Kanchanaburi) and one eastern province (Ubon Ratchathani) of Thailand using 10 microsatellite markers. Genetic diversity was high, but recent clonal expansion was detected in all three provinces. Substantial population structure and genetic differentiation of parasites among provinces suggest limited gene flow among these sites. There was no haplotype sharing among the three sites, and a reduced panel of four microsatellite markers was sufficient to assign the parasites to their provincial origins. CONCLUSION/SIGNIFICANCE: Significant parasite genetic differentiation between provinces shows successful interruption of parasite spread within Thailand, but high diversity along international borders implies a substantial parasite population size in these regions. The provincial origin of P. vivax cases can be reliably determined by genotyping four microsatellite markers, which should be useful for monitoring parasite reintroduction after malaria elimination.