A new strategy for canine visceral leishmaniasis diagnosis based on FTIR spectroscopy and machine learning

A deep learning-based model for detecting Leishmania amastigotes in microscopic slides: a new approach to telemedicine

BACKGROUND

Leishmaniasis, an illness caused by protozoa, accounts for a substantial number of human fatalities globally, thereby emerging as one of the most fatal parasitic diseases. The conventional methods employed for detecting the Leishmania parasite through microscopy are not only time-consuming but also susceptible to errors. Therefore, the main objective of this study is to develop a model based on deep learning, a subfield of artificial intelligence, that could facilitate automated diagnosis of leishmaniasis.

METHODS

In this research, we introduce LeishFuNet, a deep learning framework designed for detecting Leishmania parasites in microscopic images. To enhance the performance of our model through same-domain transfer learning, we initially train four distinct models: VGG19, ResNet50, MobileNetV2, and DenseNet 169 on a dataset related to another infectious disease, COVID-19. These trained models are then utilized as new pre-trained models and fine-tuned on a set of 292 self-collected high-resolution microscopic images, consisting of 138 positive cases and 154 negative cases. The final prediction is generated through the fusion of information analyzed by these pre-trained models. Grad-CAM, an explainable artificial intelligence technique, is implemented to demonstrate the model's interpretability.

RESULTS

The final results of utilizing our model for detecting amastigotes in microscopic images are as follows: accuracy of 98.95 1.4%, specificity of 98 2.67%, sensitivity of 100%, precision of 97.91 2.77%, F1-score of 98.92 1.43%, and Area Under Receiver Operating Characteristic Curve of 99 1.33.

CONCLUSION

The newly devised system is precise, swift, user-friendly, and economical, thus indicating the potential of deep learning as a substitute for the prevailing leishmanial diagnostic techniques.

Diagnosis of Cutaneous Leishmaniasis Using FTIR Spectroscopy and Machine Learning: An Animal Model Study

Cutaneous leishmaniasis (CL) is a polymorphic and spectral skin disease caused by Leishmania spp. protozoan parasites. CL is difficult to diagnose because conventional methods are time-consuming, expensive, and low-sensitive. Fourier transform infrared spectroscopy (FTIR) with machine learning (ML) algorithms has been explored as an alternative to achieve fast and accurate results for many disease diagnoses. Besides the high accuracy demonstrated in numerous studies, the spectral variations between infected and noninfected groups are too subtle to be noticed. Since variability in sample set characteristics (such as sex, age, and diet) often leads to significant data variance and limits the comprehensive understanding of spectral characteristics and immune responses, we investigate a novel methodology for diagnosing CL in an animal model study. Blood serum, skin lesions, and draining popliteal lymph node samples were collected from Leishmania (Leishmania) amazonensis-infected BALB/C mice under experimental conditions. The FTIR method and ML algorithms accurately differentiated between infected (CL group) and noninfected (control group) samples. The best overall accuracy (∼72%) was obtained in an external validation test using principal component analysis and support vector machine algorithms in the 1800-700 cm-1 range for blood serum samples. The accuracy achieved in analyzing skin lesions and popliteal lymph node samples was satisfactory; however, notable disparities emerged in the validation tests compared to results obtained from blood samples. This discrepancy is likely attributed to the elevated sample variability resulting from molecular compositional differences. According to the findings, the successful functioning of prediction models is mainly related to data analysis rather than the differences in the molecular composition of the samples.

Turning chaotic sample group clusterization into organized ones by feature selection: Application on photodiagnosis of Brucella abortus serological test

Bovine brucellosis diagnosis is a major problem to be solved; the disease has a tremendous economic impact with significant losses in meat and dairy products, besides the fact that it can be transmitted to humans. The sanitary measures instituted in Brazil are based on disease control through diagnosis, animal sacrifice, and vaccination. Although the currently available diagnostic tests show suitable quality parameters, they are time-consuming, and the incidence of false-positive and/or false-negative results is still observed, hindering effective disease control. The development of a low-cost, fast, and accurate brucellosis diagnosis test remains a need for proper sanitary measures at a large-scale analysis. In this context, spectroscopy techniques associated with machine learning tools have shown great potential for use in diagnostic tests. In this study, bovine blood serum was investigated by UV-vis spectroscopy and machine learning algorithms to build a prediction model for Brucella abortus diagnosis. Here we first pre-treated the UV raw data by using Standard Normal Deviate method to remove baseline deviation, then apply principal component analysis - a clustering method - to observe the group formation tendency; the first results showed no clustering tendency with a messy sample score distribution, then we properly select the main principal components to improve clusterization. Finally, by using machine learning algorithms (SVM and KNN), the predicting models achieved a 92.5% overall accuracy. The present methodology provides a test result in an average time of 5 min, while the standard diagnosis, with the screening and confirmatory tests, can take up to 48 h. The present result demonstrates the method's viability for diagnosing bovine brucellosis, which can significantly contribute to disease control programs in Brazil and other countries.

Machine Learning Enhanced Optical Spectroscopy for Disease Detection

Optical spectroscopy plays an important role in disease detection. Improving the sensitivity and specificity of spectral detection has great importance in the development of accurate diagnosis. The development of artificial intelligence technology provides a great opportunity to improve the detection accuracy through machine learning methods. In this Perspective, we focus on the combination of machine learning methods with the optical spectroscopy methods widely used for disease detection, including absorbance, fluorescence, scattering, FTIR, terahertz, etc. By comparing the spectral analysis with different machine learning methods, we illustrate that the support vector machine and convolutional neural network are most effective, which have potential to further improve the classification accuracy to distinguish disease subtypes if these machine learning methods are used. This Perspective broadens the scope of optical spectroscopy enhanced by machine learning and will be useful for the development of disease detection.

Diagnostic Classification of Cases of Canine Leishmaniasis Using Machine Learning

Proposal techniques that reduce financial costs in the diagnosis and treatment of animal diseases are welcome. This work uses some machine learning techniques to classify whether or not cases of canine visceral leishmaniasis are present by physical examinations. For validation of the method, four machine learning models were chosen: K-nearest neighbor, Naïve Bayes, support vector machine and logistic regression models. The tests were performed on three hundred and forty dogs, using eighteen characteristics of the animal and the ELISA (enzyme-linked immunosorbent assay) serological test as validation. Logistic regression achieved the best metrics: Accuracy of 75%, sensitivity of 84%, specificity of 67%, a positive likelihood ratio of 2.53 and a negative likelihood ratio of 0.23, showing a positive relationship in the evaluation between the true positives and rejecting the cases of false negatives.