BackgroundMultispectral imaging microscopy is a novel microscopic technique that integrates spectroscopy with optical imaging to record both spectral and spatial information of a specimen. This enables acquisition of a large and more informative dataset than is achievable in conventional optical microscopy. However, such data are characterized by high signal correlation and are difficult to interpret using univariate data analysis techniques.MethodsIn this work, the development and application of a novel method which uses principal component analysis (PCA) in the processing of spectral images obtained from a simple multispectral-multimodal imaging microscope to detect Plasmodium parasites in unstained thin blood smear for malaria diagnostics is reported. The optical microscope used in this work has been modified by replacing the broadband light source (tungsten halogen lamp) with a set of light emitting diodes (LEDs) emitting thirteen different wavelengths of monochromatic light in the UV–vis-NIR range. The LEDs are activated sequentially to illuminate same spot of the unstained thin blood smears on glass slides, and grey level images are recorded at each wavelength. PCA was used to perform data dimensionality reduction and to enhance score images for visualization as well as for feature extraction through clusters in score space.ResultsUsing this approach, haemozoin was uniquely distinguished from haemoglobin in unstained thin blood smears on glass slides and the 590–700 spectral range identified as an important band for optical imaging of haemozoin as a biomarker for malaria diagnosis.ConclusionThis work is of great significance in reducing the time spent on staining malaria specimens and thus drastically reducing diagnosis time duration. The approach has the potential of replacing a trained human eye with a trained computerized vision system for malaria parasite blood screening.

Accurate identification of disease vector insects is crucial when collecting epidemiological data. Traditionally, mosquitoes that transmit diseases like malaria, yellow fever, chikungunya, and dengue fever have been identified by looking at their external morphological features at different life cycle stages. This process is tedious and labour intensive.In this paper, the potential of Raman spectroscopy in combination with Linear and Quadratic Discriminant Analysis to classify three mosquito species, namely: Aedes aegypti, Anopheles gambiae and Culex quinquefasciatus, was explored. The classification was based on the mosquitoes’ cuticular melanin. The three mosquito species represented two subfamilies of medically important mosquitoes, i.e. the Anophelinae and the Culicinae. The housefly (Musca domestica) was included as a ‘control’ group to assess the discrimination ability of the classifiers. This study is the first to use Raman spectroscopy to classify mosquitoes. Fresh mosquitoes were anaesthetized with chloroform, and a dispersive Raman microscope was used to capture spectra from their legs. Broad melanin peaks centred around 1400 cm-1, 1590 cm-1, and 2060 cm-1 dominated the spectra. Variance Threshold (VT) and Principal Component Analysis (PCA) were used for feature selection and feature extraction respectively from the preprocessed data. The extracted features were then used to train and test Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA) classifiers.The VT/PCA/QDA classification model performed better than VT/PCA/LDA. VT/PCA/QDA achieved an overall accuracy of 94%, sensitivity of 87% and specificity of 96%, whereas VT/PCA/LDA attained an accuracy of 85%, a sensitivity of 69% and a specificity of 90%. The success of these relatively simple classification models on Raman spectroscopy data lays the groundwork for future development of models for discriminating morphologically indistinguishable insect species.

Accurate identification of disease vectors is crucial when collecting epidemiological data. In mosquitoes, which transmit diseases like malaria, yellow fever, chikungunya, and dengue fever, identification mainly relies on the observation of external morphological features at different life cycle stages. This process is tedious and labor-intensive. In this paper, the utility of Raman spectroscopy to discriminate and classify three mosquito species, namely, Aedes aegypti, Anopheles gambiae, and Culex quinquefasciatus, is presented. The three species were chosen to represent two subfamilies of medically important mosquitoes, that is, the Anophelinae and the Culicinae. The study is primarily a proof of concept on the potential of Raman spectroscopy in mosquito taxonomy. A dispersive Raman microscope was used to record spectra from the legs (femur and tibia) of fresh anesthetized laboratory-bred mosquitoes. Broad peaks centered around 1400, 1590, and 2060 cm À1 dominated the spectra. These peaks, attributed to cuticular melanin, were important in mosquito discrimination.Variance threshold (VT) and principal component analysis (PCA) were used for feature selection and feature extraction, respectively. The extracted features were then used to train and test linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) classifiers. VT/PCA/QDA achieved an overall accuracy of 94%, a sensitivity of 87%, and a specificity of 96%, whereas VT/PCA/LDA attained an accuracy of 85%, a sensitivity of 69%, and a specificity of 90%. The success of these relatively simple classification models on Raman spectroscopy data lays the ground for future development of machine learning models that may include discrimination of cryptic species.

Background Identification of malaria vectors is an important exercise that can result in the deployment of targeted control measures and monitoring the susceptibility of the vectors to control strategies. Although known to possess distinct biting behaviours and habitats, the African malaria vectors Anopheles gambiae and Anopheles arabiensis are morphologically indistinguishable and are known to be discriminated by molecular techniques. In this paper, Raman spectroscopy is proposed to complement the tedious and time-consuming Polymerase Chain Reaction (PCR) method for the rapid screening of mosquito identity. Methods A dispersive Raman microscope was used to record spectra from the legs (femurs and tibiae) of fresh anaesthetized laboratory-bred mosquitoes. The scattered Raman intensity signal peaks observed were predominantly centered at approximately 1400 cm− 1, 1590 cm− 1, and 2067 cm− 1. These peaks, which are characteristic signatures of melanin pigment found in the insect cuticle, were important in the discrimination of the two mosquito species. Principal Component Analysis (PCA) was used for dimension reduction. Four classification models were built using the following techniques: Linear Discriminant Analysis (LDA), Logistic Regression (LR), Quadratic Discriminant Analysis (QDA), and Quadratic Support Vector Machine (QSVM). Results PCA extracted twenty-one features accounting for 95% of the variation in the data. Using the twenty-one principal components, LDA, LR, QDA, and QSVM discriminated and classified the two cryptic species with 86%, 85%, 89%, and 93% accuracy, respectively. Conclusion Raman spectroscopy in combination with machine learning tools is an effective, rapid and non-destructive method for discriminating and classifying two cryptic mosquito species, Anopheles gambiae and Anopheles arabiensis. belonging to the Anopheles gambiae complex.