Plasmodium life cycle stage classification based quantification of malaria parasitaemia in thin blood smears

Visual inspection for the quantification of malaria parasitaemiain (MP) and classification of life cycle stage are hard and time taking. Even though, automated techniques for the quantification of MP and their classification are reported in the literature. However, either reported techniques are imperfect or cannot deal with special issues such as anemia and hemoglobinopathies due to clumps of red blood cells (RBCs). The focus of the current work is to examine the thin blood smear microscopic images stained with Giemsa by digital image processing techniques, grading MP on independent factors (RBCs morphology) and classification of its life cycle stage. For the classification of the life cycle of malaria parasite the k‐nearest neighbor, Naïve Bayes and multi‐class support vector machine are employed for classification based on histograms of oriented gradients and local binary pattern features. The proposed methodology is based on inductive technique, segment malaria parasites through the adaptive machine learning techniques. The quantification accuracy of RBCs is enhanced; RBCs clumps are split by analysis of concavity regions for focal points. Further, classification of infected and non‐infected RBCs has been made to grade MP precisely. The training and testing of the proposed approach on benchmark dataset with respect to ground truth data, yield 96.75% MP sensitivity and 94.59% specificity. Additionally, the proposed approach addresses the process with independent factors (RBCs morphology). Finally, it is an economical solution for MP grading in immense testing .     

An automatic vision‐based malaria diagnosis system

Malaria is a worldwide health problem with 225 million infections each year. A fast and easy‐to‐use method, with high performance is required to differentiate malaria from non‐malarial fevers. Manual examination of blood smears is currently the gold standard, but it is time‐consuming, labour‐intensive, requires skilled microscopists and the sensitivity of the method depends heavily on the skills of the microscopist. We propose an easy‐to‐use, quantitative cartridge‐scanner system for vision‐based malaria diagnosis, focusing on low malaria parasite densities. We have used special finger‐prick cartridges filled with acridine orange to obtain a thin blood film and a dedicated scanner to image the cartridge. Using supervised learning, we have built a Plasmodium falciparum detector. A two‐step approach was used to first segment potentially interesting areas, which are then analysed in more detail. The performance of the detector was validated using 5 420 manually annotated parasite images from malaria parasite culture in medium, as well as using 40 cartridges of 11 780 images containing healthy blood. From finger prick to result, the prototype cartridge‐scanner system gave a quantitative diagnosis in 16 min, of which only 1 min required manual interaction of basic operations. It does not require a wet lab or a skilled operator and provides parasite images for manual review and quality control. In healthy samples, the image analysis part of the system achieved an overall specificity of 99.999978% at the level of (infected) red blood cells, resulting in at most seven false positives per microlitre. Furthermore, the system showed a sensitivity of 75% at the cell level, enabling the detection of low parasite densities in a fast and easy‐to‐use manner. A field trial in Chittagong (Bangladesh) indicated that future work should primarily focus on improving the filling process of the cartridge and the focus control part of the scanner.     

Automated system for characterization and classification of malaria‐infected stages using light microscopic images of thin blood smears

In this paper, we propose a comprehensive image characterization cum classification framework for malaria‐infected stage detection using microscopic images of thin blood smears. The methodology mainly includes microscopic imaging of Leishman stained blood slides, noise reduction and illumination correction, erythrocyte segmentation, feature selection followed by machine classification. Amongst three‐image segmentation algorithms (namely, rule‐based, Chan–Vese‐based and marker‐controlled watershed methods), marker‐controlled watershed technique provides better boundary detection of erythrocytes specially in overlapping situations. Microscopic features at intensity, texture and morphology levels are extracted to discriminate infected and noninfected erythrocytes. In order to achieve subgroup of potential features, feature selection techniques, namely, F‐statistic and information gain criteria are considered here for ranking. Finally, five different classifiers, namely, Naive Bayes, multilayer perceptron neural network, logistic regression, classification and regression tree (CART), RBF neural network have been trained and tested by 888 erythrocytes (infected and noninfected) for each features’ subset. Performance evaluation of the proposed methodology shows that multilayer perceptron network provides higher accuracy for malaria‐infected erythrocytes recognition and infected stage classification. Results show that top 90 features ranked by F‐statistic (specificity: 98.64%, sensitivity: 100%, PPV: 99.73% and overall accuracy: 96.84%) and top 60 features ranked by information gain provides better results (specificity: 97.29%, sensitivity: 100%, PPV: 99.46% and overall accuracy: 96.73%) for malaria‐infected stage classification.     

Comparisons of the topographic characteristics and electrical charge distributions among Babesia‐infected erythrocytes and extraerythrocytic merozoites using AFM

Tick‐borne Babesia parasites are responsible for costly diseases worldwide. Improved control and prevention tools are urgently needed, but development of such tools is limited by numerous gaps in knowledge of the parasite–host relationships. We hereby used atomic force microscopy (AFM) and frequency‐modulated Kelvin probe potential microscopy (FM‐KPFM) techniques to compare size, texture, roughness and surface potential of normal and infected Babesia bovis, B. bigemina and B. caballi erythrocytes to better understand the physical properties of these parasites. In addition, AFM and FM‐KPFM allowed a detailed view of extraerythrocytic merozoites revealing shape, topography and surface potential of paired and single parasites. B. bovis‐infected erythrocytes display distinct surface texture and overall roughness compared to noninfected erythrocytes. Interestingly, B. caballi‐infected erythrocytes do not display the surface ridges typical in B. bovis parasites. Observations of extraerythrocytic B. bovis, B. bigemina and B. caballi merozoites using AFM revealed differences in size and shape between these three parasites. Finally, similar to what was previously observed for Plasmodium‐infected erythrocytes, FM‐KPFM images reveal an unequal electric charge distribution, with higher surface potential above the erythrocyte regions that are likely associated with Babesia parasites than over its remainder regions. In addition, the surface potential of paired extraerythrocytic B. bovis Mo7 merozoites revealed an asymmetric potential distribution. These observations may be important to better understand the unique cytoadhesive properties of B. bovis‐infected erythrocytes, and to speculate on the role of differences in the distribution of surface charges in the biology of the parasites.     

Extrinsic parameter's adjustment and potential implications in Plasmodium falciparum malaria diagnosis

Malaria is a major public health concern, affecting over 3.2 billion people in 91 countries. The advent of digital microscopy and Machine learning with the aim of automating Plasmodium falciparum diagnosis extensively depends on the extracted image features. The color of the cells, plasma, and stained artifacts influence the topological, geometrical, and statistical parameters being used to extract image features. During microscopic image acquisition, custom adjustments to the condenser and color temperature controls often have an influence on the extracted statistical features. But, our human visual system sub-consciously adjusts the color and retains the originality in a different lighting environment. Despite the use of appropriate image preprocessing, findings from the literature indicate that statistical feature variations exist, allowing the risk of P. falciparum misinterpretation. In order to eliminate this pervasive variation, the current work focuses on preprocessing the extracted statistical features rather than the prepossessing of the source image. It begins with the augmentation of series images for a microscopic field by inducing illumination variations during the microscopic image acquisition stage. A set of such image series is analyzed using a Nonlinear Regression Model to generalize the relationship between microscopic images acquired with variable ambient brightness and a specific feature. The projection point of the centroid feature onto the brightness parameter is identified in the model and it is denoted as the optimum brightness factor (OBF). Using the model, the feature correction factor (CF) is calculated from the rate of change of feature values over the interval OBF, and the brightness of the test image is processed. The present work has investigated OBF for selected image textural features, namely Contrast, Homogeneity, Entropy, Energy, and Correlation individually from its co-occurrence matrices. For performance analysis, the best state-of-the-art method uses selected texture as a subset feature to evaluate the effectiveness of P. falciparum malaria classification. Then, the impact of proposed feature processing is evaluated on 274 blood smear images with and without Feature Correction (FC). As a result, the “p” value is less than .05, which leads to the result that it is highly significant and the classification accuracy and F-score of P. falciparum malaria are increased.     

Imprint cytology‐based breast malignancy screening: an efficient nuclei segmentation technique

Imprint cytology (IC) refers to one of the most reliable, rapid and affordable techniques for breast malignancy screening; where shape variation of H&E stained nucleus is examined by the pathologists. This work aims at developing an automated and efficient segmentation algorithm by integrating Lagrange's interpolation and superpixels in order to delineate overlapped nuclei of breast cells (normal and malignant). Subsequently, a computer assisted IC tool has been designed for breast cancer (BC) screening. The proposed methodology consists of mainly three subsections: gamma correction for preprocessing, single nuclei segmentation and segmentation of overlapping nuclei. Single nuclei segmentation combines histogram‐based thresholding and morphological operations; where segmentation of overlapping nuclei includes concave point detection, Lagrange's interpolation for overlapping arc area detection and the fine segmentation of overlapped arc area by superpixels. Total 16 significant features (p < 0.05) quantifying shape and texture of nucleus were extracted, and random forest (RF) classifier was skilled for automated screening. The proposed methodology has been tested on 120 IC images (approximately 12 000 nuclei); where 98% segmentation accuracy and 99% classification accuracy were achieved. Besides, performance evaluation was studied by using Jaccard's index (= 94%), correlation coefficient (= 95%), Dice similarity coefficient (= 97%) and Hausdorff distance (= 43%). The proposed approach could offer benefit to the pathologists for confirmatory BC screening with improved accuracy and could potentially lead to a better shape understanding of malignant nuclei.     

Robust fluorescent labelling of micropipettes for use in fluorescence microscopy: application to the observation of a mosquito borne parasite infection

The ability to monitor micropipette injections with a high‐resolution fluorescent microscope has utility for a variety of applications. Herein, different approaches were tested for creating broad‐band fluorescently labelled glass micropipettes including: UV cured glass glues, baked glass enamel containing fluorescent dyes as well as nanodiamonds attached during pipette formation in the microforge. The most robust and simplest approach was to use labelled baked enamel on the exterior of the pipette. This approach was tested using pipettes designed to mimic a mosquito proboscis for the injection of the malaria parasite, Plasmodium spp., into the dermis of a living mouse ear. The pipette (～30 micron diameter) was easily detected in the microscopy field of view and tolerated multiple insertions through the skin. This simple inexpensive approach to fluorescently labelling micropipettes will aid in the development of procedures under the fluorescent microscope.     

Automated discrimination of dicentric and monocentric chromosomes by machine learning‐based image processing

Dose from radiation exposure can be estimated from dicentric chromosome (DC) frequencies in metaphase cells of peripheral blood lymphocytes. We automated DC detection by extracting features in Giemsa‐stained metaphase chromosome images and classifying objects by machine learning (ML). DC detection involves (i) intensity thresholded segmentation of metaphase objects, (ii) chromosome separation by watershed transformation and elimination of inseparable chromosome clusters, fragments and staining debris using a morphological decision tree filter, (iii) determination of chromosome width and centreline, (iv) derivation of centromere candidates, and (v) distinction of DCs from monocentric chromosomes (MC) by ML. Centromere candidates are inferred from 14 image features input to a Support Vector Machine (SVM). Sixteen features derived from these candidates are then supplied to a Boosting classifier and a second SVM which determines whether a chromosome is either a DC or MC. The SVM was trained with 292 DCs and 3135 MCs, and then tested with cells exposed to either low (1 Gy) or high (2‐4 Gy) radiation dose. Results were then compared with those of 3 experts. True positive rates (TPR) and positive predictive values (PPV) were determined for the tuning parameter, σ. At larger σ, PPV decreases and TPR increases. At high dose, for σ = 1.3, TPR = 0.52 and PPV = 0.83, while at σ = 1.6, the TPR = 0.65 and PPV = 0.72. At low dose and σ = 1.3, TPR = 0.67 and PPV = 0.26. The algorithm differentiates DCs from MCs, overlapped chromosomes and other objects with acceptable accuracy over a wide range of radiation exposures. Microsc. Res. Tech. 79:393–402, 2016. © 2016 Wiley Periodicals, Inc.     

Morphological variations on microscopy in oocysts of coccidian parasites: A prospective study from a tertiary care hospital in north India

The modified acid fast staining technique is a commonly used procedure for the detection of coccidian parasites in developing countries. The morphological variations observed in these parasites play a significant role to some extent in both identification and diagnosis of these parasitic infections. A prospective cross sectional study was performed over three years. The fecal smears were stained by modified Kinyoun acid‐fast staining technique and were extensively studied for morphological variations in the coccidian parasites. Out of a total of two thousand one hundred fifty one (n = 2,151) fecal samples received during the study period, 259 samples (12%) were positive for any one of the coccidian parasites. Morphological variations, especially in the staining character was noted in all the three coccidian parasites. This study was an attempt to characterize different variations in size, shape and staining characteristics of the three coccidian parasites.     

Automated identification of neurons and their locations

Individual locations of many neuronal cell bodies (>10⁴) are needed to enable statistically significant measurements of spatial organization within the brain such as nearest‐neighbour and microcolumnarity measurements. In this paper, we introduce an Automated Neuron Recognition Algorithm (ANRA) which obtains the (x, y) location of individual neurons within digitized images of Nissl‐stained, 30 μm thick, frozen sections of the cerebral cortex of the Rhesus monkey. Identification of neurons within such Nissl‐stained sections is inherently difficult due to the variability in neuron staining, the overlap of neurons, the presence of partial or damaged neurons at tissue surfaces, and the presence of non‐neuron objects, such as glial cells, blood vessels, and random artefacts. To overcome these challenges and identify neurons, ANRA applies a combination of image segmentation and machine learning. The steps involve active contour segmentation to find outlines of potential neuron cell bodies followed by artificial neural network training using the segmentation properties (size, optical density, gyration, etc.) to distinguish between neuron and non‐neuron segmentations. ANRA positively identifies 86 ± 5% neurons with 15 ± 8% error (mean ± SD) on a wide range of Nissl‐stained images, whereas semi‐automatic methods obtain 80 ± 7%/17 ± 12%. A further advantage of ANRA is that it affords an unlimited increase in speed from semi‐automatic methods, and is computationally efficient, with the ability to recognize ～100 neurons per minute using a standard personal computer. ANRA is amenable to analysis of huge photo‐montages of Nissl‐stained tissue, thereby opening the door to fast, efficient and quantitative analysis of vast stores of archival material that exist in laboratories and research collections around the world.     

Morphological and functional characterization of circulating hemocytes using microscopy techniques

In the present study, Microscopy studies were performed to characterize the blood cells of the mangrove crab Episesarma tetragonum. Three types of hemocytes were observed: granulocytes, semi‐granulocytes, and hyalinocytes or agranulocytes. Hyalinocytes have a distinguished nucleus surrounded by the cytoplasm, and a peculiar cell type was present throughout the cytosol, lysosomes with hemocyte types (granules) stained red (pink). Giemsa staining was used to differentiate between the large and small hemocytes. Ehrlich's staining was used to differentiate granule‐containing cells in acidophils (55%), basophils (44%), and neutrophils (<1%). Periodic acid–Schiff staining was used to identify the sugar molecules in the cytoplasm. Cell‐mediated immune reactions including phagocytosis, encapsulation, agglutination, and peroxidase‐mediated cell adhesion are the functions of hemocytes. Agglutination reaction involves both kind of cells involved in yeast and heme‐agglutination responses in invertebrates. The beta glucan outer layer of yeast cells was recognized by hemocyte receptors. Human RBC cells were agglutinated via granulocytes. E. tetragonum hemocytes are an important animal model for studying both ultrastructural and functional activity of circulating cells. In addition, E. tetragonum hemocytes exhibited excellent antibacterial and antibiofilm activities were studied through plating and microplate assays. Biofilm inhibition was also visualized through changes in biochemical assays and morphological variations were visualized through levels in in situ microscopy analysis.     

Morphological redescription and phylogenetic assessment of Spauligodon aspiculus (Oxyuroidea: Pharyngodonidae) infecting the white‐spotted gecko,Tarentola annularis (Squamata: Gekkonidae)

Thirty white‐spotted geckos, Tarentola annularis, from the South Sinai desert in Egypt, were examined for helminth parasites. Spauligodon aspiculus was observed to infect 19 geckos with 63.33% as a prevalence of parasitic infection. The present nematode species is separated from congeners by morphological and metrical characteristics such as lateral alae, aspinose filamentous tail, and no spicule, and three pairs of caudal papillae with posterior pair excluded from envelopment by the caudal alae in the male worms, and knobbed eggs, and postbulbar vulva in females. It compared morphometrically with other Spauligodon species described previously and showed few differences in measurements. Molecular characterization based on the partial 28S rRNA nuclear ribosomal gene sequence showed that there was a close identity, up to 72%, with other sequences retrieved from GenBank. Phylogenetic analysis showed that the parasite sequence in conjunction with existing data facilitates the investigation of the placement of this pharyngodonid species within Oxyuridae. The present species is deeply embedded in the genus Spauligodon with close relationships to previously described Spauligodon nicolauensis (gb| JN619349.1, and JF829243.1) as more related sister taxa. This study highlights the importance of combining genetic and morphological data with taxonomy in pharyngodonid species.     

Tanshinone IIA protects intestinal epithelial cells from ferroptosis through the upregulation of <i>GPX4</i> and <i>SLC7A11</i>

Background: Inflammatory bowel disease (IBD) is a chronic inflammatory disease of the gastrointestinal tract. The destruction of the intestinal epithelial barrier is one of the major pathological processes in IBD pathology. Growing evidence indicated that epithelial cell ferroptosis is linked to IBD and is considered a target process. Methods: RAS-selective lethal 3 (RSL3) was used to induce ferroptosis in intestinal epithelial cell line No. 6 (IEC-6) cells, and cell ferroptosis and the effects of tanshinone IIA (Tan IIA) were determined by cell counting kit-8 (CCK-8), reactive oxygen species (ROS) staining, Giemsa staining and transmission electron microscope (TEM). The cell viability of natural product library compounds was determined by CCK-8. The expression of ferroptosis-related genes were detected by real-time quantitative polymerase chain reaction (RT-qPCR) and western blot. Results: Treatment of IEC-6 cells results in the accumulation of ROS and typical morphological characteristics of ferroptosis. RSL3 treatment caused rapid cellular cytotoxicity which could be reversed by ferrostatin-1 (Fer-1) in IEC-6 cells. Natural product library screening revealed that Tan IIA is a potent inhibitor of IEC-6 cell ferroptosis. Tan IIA could significantly protect the RSL3-induced ferroptosis of IEC-6 cells. Furthermore, the ferroptosis suppressors, glutathione peroxidase 4 (GPX4), solute carrier family 7 member 11 (SLC7A11), and miR-17-92 were found to be early response genes in RSL3-treated cells. Treatment of IEC-6 cells with Tan IIA resulted in upregulation of GPX4, SLC7A11, and miR-17-92. Conclusion: Our study demonstrated that Tan IIA protects IEC-6 cells from ferroptosis through the upregulation of GPX4, SLC7A11, and miR-17-92. The findings might provide a theoretical grounding for the future application of Tan IIA to treat or prevent IBD.     

Accurate automatic detection of acute lymphatic leukemia using a refined simple classification

An improved classification technique is presented to identify automatically the acute lymphatic leukemia (ALL) subtypes. An adaptive segmentation procedure is performed on peripheral blood smear images to extract the main features (10 geometric features) from the segmented images of white blood cell (WBC), nucleus, and cytoplasm. To show the importance of the different extracted features for the diagnostic accuracy, a comprehensive study is made on all the possible permutation cases of the features using powerful classifiers which are K‐nearest neighbor (KNN) at different metric functions, support vector machine (SVM) with different kernels, and artificial neural network (ANN). This procedure enables us to construct a feature map depending only on least number of features which lead to the highest diagnostic accuracy. It is found that the features map regarding the vacuoles in the cytoplasm and the regularity of the nucleus membrane gives the highest accurate results. The automatic classification for ALL subtypes based only on these two effective features is assessed using the receiver operating characteristic (ROC) curve and F ₁ ‐score measures. It is confirmed that the present technique is highly accurate, and saves the effort and time of training.     

融合下补偿结构的眼底血管图像分割网络研究

眼底血管图像在临床中通常被用于眼部疾病的诊断及监测，其中血管的形态结构能够反映疾病的重要特征，因此，眼底血管图像的分割处理对眼部疾病的诊断和预防具有十分重要的医学意义。针对目前人工智能主流算法中卷积和池化操作会导致很多特征丢失，提取特征时会忽视图像中的空间信息，图像中的细小血管很难分割出来等问题，基于U-net模型进行了相关研究，结合空间注意力模块对空间特征进行细化，同时提出了一种下补偿结构LCSAnet。该结构能够减少网络提取特征信息过程中的特征损失，从而提高分割精度。研究实验在DRIVE数据集上完成，LC-SAnet的分割准确率达到96.97%,F1值达到74.36%。结果证明，LC-SAnet表现出更好的分割性能，对细小血管的结构识别更加准确。     

Multifractal characterization of morphology of human red blood cells membrane skeleton

The purpose of this paper is to show applicability of multifractal analysis in investigations of the morphological changes of ultra‐structures of red blood cells (RBCs) membrane skeleton measured using atomic force microscopy (AFM). Human RBCs obtained from healthy and hypertensive donors as well as healthy erythrocytes irradiated with neutrons (45 μGy) were studied. The membrane skeleton of the cells was imaged using AFM in a contact mode. Morphological characterization of the three‐dimensional RBC surfaces was realized by a multifractal method. The nanometre scale study of human RBCs surface morphology revealed a multifractal geometry. The generalized dimensions D_q and the singularity spectrum f(α) provided quantitative values that characterize the local scale properties of their membrane skeleton organization. Surface characterization was made using areal ISO 25178‐2: 2012 topography parameters in combination with AFM topography measurement. The surface structure of human RBCs is complex with hierarchical substructures resulting from the organization of the erythrocyte membrane skeleton. The analysed AFM images confirm a multifractal nature of the surface that could be useful in histology to quantify human RBC architectural changes associated with different disease states. In case of very precise measurements when the red cell surface is not wrinkled even very fine differences can be uncovered as was shown for the erythrocytes treated with a very low dose of ionizing radiation.     

Rouleaux red blood cells splitting in microscopic thin blood smear images via local maxima,circles drawing,and mapping with original RBCs

Splitting the rouleaux RBCs from single RBCs and its further subdivision is a challenging area in computer‐assisted diagnosis of blood. This phenomenon is applied in complete blood count, anemia, leukemia, and malaria tests. Several automated techniques are reported in the state of art for this task but face either under or over splitting problems. The current research presents a novel approach to split Rouleaux red blood cells (chains of RBCs) precisely, which are frequently observed in the thin blood smear images. Accordingly, this research address the rouleaux splitting problem in a realistic, efficient and automated way by considering the distance transform and local maxima of the rouleaux RBCs. Rouleaux RBCs are splitted by taking their local maxima as the centres to draw circles by mid‐point circle algorithm. The resulting circles are further mapped with single RBC in Rouleaux to preserve its original shape. The results of the proposed approach on standard data set are presented and analyzed statistically by achieving an average recall of 0.059, an average precision of 0.067 and F‐measure 0.063 are achieved through ground truth with visual inspection.     

Fast,high-precision autofocus on a motorised microscope: Automating blood sample imaging on the OpenFlexure Microscope

The OpenFlexure Microscope is a 3D-printed, low-cost microscope capable of automated image acquisition through the use of a motorised translation stage and a Raspberry Pi imaging system. This automation has applications in research and healthcare, including in supporting the diagnosis of malaria in low-resource settings. The plasmodium parasites that cause malaria require high magnification imaging, which has a shallow depth of field, necessitating the development of an accurate and precise autofocus procedure. We present methods of identifying the focal plane of the microscope, and procedures for reliably acquiring a stack of focused images on a system affected by backlash and drift. We also present and assess a method to verify the success of autofocus during the scan. The speed, reliability and precision of each method are evaluated, and the limitations discussed in terms of the end users' requirements.     

A prototype system of three-dimensional non-contact measurement

A prototype 3D measurement system is proposed in this paper which consists of a 1D laser displacement sensor, a 2D image system and a servo controlX,Y-table. The laser sensor and CCD camera are installed on theZ-axis perpendicular to theX,Y-table. The image-processing system employs the adaptive resonant theory (ART) neural networks to classify the outer shape of the measured object. The edge values of the object are then obtained by using the image processing procedures of sliding, stretching, edge enhancement and binary disposal. The 2D dimensions of the object are searched by employing the Hough theory based upon the edge values. The 3D dimensions of the object are measured and assembled by combining theX,Y-coordinates of the table and the scanning results of the 1D laser for the height of theZ-axis. A 3D plaster model is chosen as the specimen for non-contact measurement to verify the feasibility of this approach. The limitations and resolution of the 3D measurement of this system are discussed.