Convolutional neural network‐based malaria diagnosis from focus stack of blood smear images acquired using custom‐built slide scanner

The present paper introduces a focus stacking‐based approach for automated quantitative detection of Plasmodium falciparum malaria from blood smear. For the detection, a custom designed convolutional neural network (CNN) operating on focus stack of images is used. The cell counting problem is addressed as the segmentation problem and we propose a 2‐level segmentation strategy. Use of CNN operating on focus stack for the detection of malaria is first of its kind, and it not only improved the detection accuracy (both in terms of sensitivity [97.06%] and specificity [98.50%]) but also favored the processing on cell patches and avoided the need for hand‐engineered features. The slide images are acquired with a custom‐built portable slide scanner made from low‐cost, off‐the‐shelf components and is suitable for point‐of‐care diagnostics. The proposed approach of employing sophisticated algorithmic processing together with inexpensive instrumentation can potentially benefit clinicians to enable malaria diagnosis.      

A quantitative method for the analysis of cell shape and locomotion

Summary A rapid, semiautomated system to quantitate and analyze leukocyte shape and locomotion was developed. Video images of moving leukocytes were obtained using a Vidicon camera mounted on a Nikon phase microscope. The video signal was either inputted directly, or indirectly via a video cassette recorder, to a Datacube video analog-digital, digital-analog converter. A Digital Equipment Corporation LSI 11/23 computer using the RT-11/TSX-Plus operating system and computer programs written in FORTRAN and MARCO assembly language permitted image segmentation, image display, and calculation of position, speed, direction of movement and orientation of each leukocyte at 10 s intervals. These data were stored on a winchester disk for subsequent evaluation of the leukocyte orientation, speed and direction of movement using statistical and graphical methods. The reproducibility of measurements made with the video system was tested by comparison with manual measurements; a correlation coefficient of 0.998 was obtained for the two methods. Rates of chemokinesis were then determined for unstimulated and chemokinetically stimulated polymorphonuclear leukocytes (PMNs) and found to average 12.8 m/min and 18.1 m/min, respectively. The high speed, ease of data analysis, and potential for multiparameter evaluation makes this system useful for directly evaluating leukocyte locomotion.In honour of Prof. P. van Duijn     

Automated region of interest retrieval and classification using spectral analysis

Efficient use of whole slide imaging in pathology needs automated region of interest (ROI) retrieval and classification, through the use of image analysis and data sorting tools. One possible method for data sorting uses Spectral Analysis for Dimensionality Reduction. We present some interesting results in the field of histopathology and cytohematology. In histopathology, we developed a Computer-Aided Diagnosis system applied to low-resolution images representing the totality of histological breast tumour sections. The images can be digitized directly at low resolution or be obtained from sub-sampled high-resolution virtual slides. Spectral Analysis is used (1) for image segmentation (stroma, tumour epithelium), by determining a "distance" between all the images of the database, (2) for choosing representative images and characteristic patterns of each histological type in order to index them, and (3) for visualizing images or features similar to a sample provided by the pathologist. In cytohematology, we studied a blood smear virtual slide acquired through high resolution oil scanning and Spectral Analysis is used to sort selected nucleated blood cell classes so that the pathologist may easily focus on specific classes whose morphology could then be studied more carefully or which can be analyzed through complementary instruments, like Multispectral Imaging or Raman MicroSpectroscopy.     

Inside Cover: A low‐cost,automated parasite diagnostic system via a portable,robotic microscope and deep learning (J. Biophotonics 9/2019)

A low‐cost, automated microscope is combined with machine learning to bring veterinary parasite diagnosis to the point of need. The authors present an inexpensive robotic microscope that automatically focuses, scans, and images a large area McMaster chamber. A deep learning image segmentation pipeline identifies and counts eggs of parasitic worms and single‐celled parasites in goats, dogs, and monkeys, yielding >96% diagnostic accuracy without the need for a trained user. Further details can be found in the article by Yaning Li, Rui Zheng, Yizhen Wu, et al. ( e201800410 ).

     

Raman detection and identification of normal and leukemic hematopoietic cells

The analysis of leukocytes of peripheral blood is a crucial step in hematologic exams commonly used for disease diagnosis and, typically, requires molecular labelling. In addition, only a detailed, laborious phenotypic analysis allows identifying the presence and stage of specific pathologies such as leukemia. Most of the biochemical information is lost in the routine blood tests. In the present study, we tackle 2 important issues of label‐free biochemical identification and classification of leukocytes using Raman spectroscopy (RS). First, we demonstrate that leukocyte subpopulations of lymphocytes (B, T and NK cells), monocytes and granulocytes can be identified by the unsupervised statistical approach of principal component analysis and classified by linear discriminant analysis with approximately 99% of accuracy. Second, we apply the same procedure to identify and discriminate normal B cells and transformed MN60 lymphocyte leukemic cell lines. In addition, we demonstrate that RS can be efficiently used for monitoring the cell response to low‐dose chemotherapy treatment, experimentally eliciting the sensitivity to a dose‐dependent cell response, which is of fundamental importance to determine the efficacy of any treatment. These results largely expand established Raman‐based research protocols for label‐free analysis of white blood cells, leukemic cells and chemotherapy treatment follow‐up.      

A quantitative method for the analysis of cell shape and locomotion

A rapid, semiautomated system to quantitate and analyze leukocyte shape and locomotion was developed. Video images of moving leukocytes were obtained using a Vidicon camera mounted on a Nikon phase microscope. The video signal was either inputted directly, or indirectly via a video cassette recorder, to a Datacube video analog-digital, digital-analog converter. A Digital Equipment Corporation LSI 11/23 computer using the RT-11/TSX-Plus operating system and computer programs written in FORTRAN and MARCO assembly language permitted image segmentation, image display, and calculation of position, speed, direction of movement and orientation of each leukocyte at 10 s intervals. These data were stored on a winchester disk for subsequent evaluation of the leukocyte orientation, speed and direction of movement using statistical and graphical methods. The reproducibility of measurements made with the video system was tested by comparison with manual measurements; a correlation coefficient of 0.998 was obtained for the two methods. Rates of chemokinesis were then determined for unstimulated and chemokinetically stimulated polymorphonuclear leukocytes (PMNs) and found to average 12.8 micron/min and 18.1 micron/min, respectively. The high speed, ease of data analysis, and potential for multiparameter evaluation makes this system useful for directly evaluating leukocyte locomotion.     

Segmentation of complex cell clusters in microscopic images: application to bone marrow samples.

BACKGROUND: Morphologic examination of bone marrow and peripheral blood samples continues to be the cornerstone in diagnostic hematology. In recent years, interest in automatic leukocyte classification using image analysis has increased rapidly. Such systems collect a series of images in which each cell must be segmented accurately to be classified correctly. Although segmentation algorithms have been developed for sparse cells in peripheral blood, the problem of segmenting the complex cell clusters characterizing bone marrow images is harder and has not been addressed previously. METHODS: We present a novel algorithm for segmenting clusters of any number of densely packed cells. The algorithm first oversegments the image into cell subparts. These parts are then assembled into complete cells by solving a combinatorial optimization problem in an efficient way. RESULTS: Our experimental results show that the algorithm succeeds in correctly segmenting densely clustered leukocytes in bone marrow images. CONCLUSIONS: The presented algorithm enables image analysis-based analysis of bone marrow samples for the first time and may also be adopted for other digital cytometric applications where separation of complex cell clusters is required.     

Automated Detection of B Cell and T Cell Acute Lymphoblastic Leukaemia Using Deep Learning

PurposeLeukaemia is diagnosed conventionally by observing the peripheral blood and bone marrow smear using a microscope and with the help of advanced laboratory tests. Image processing-based methods, which are simple, fast, and cheap, can be used to detect and classify leukemic cells by processing and analysing images of microscopic smear. The proposed study aims to classify Acute Lymphoblastic Leukaemia (ALL) by Deep Learning (DL) based techniques.ProceduresThe study used Deep Convolutional Neural Networks (DNNs) to classify ALL according to WHO classification scheme without using any image segmentation and feature extraction that involves intense computations. Images from an online image bank of American Society of Haematology (ASH) were used for the classification.FindingsA classification accuracy of 94.12% is achieved by the study in isolating the B-cell and T-cell ALL images using a pretrained CNN AlexNet as well as LeukNet, a custom-made deep learning network designed by the proposed work. The study also compared the classification performances using three different training algorithms.ConclusionsThe paper detailed the use of DNNs to classify ALL, without using any image segmentation and feature extraction techniques. Classification of ALL into subtypes according to the WHO classification scheme using image processing techniques is not available in literature to the best of the knowledge of the authors. The present study considered the classification of ALL only, and detection of other types of leukemic images can be attempted in future research.     

Heterogeneity of respiratory dendritic cell subsets and lymphocyte populations in inbred mouse strains

Background

Inbred mouse strains are used in different models of respiratory diseases but the variation of critical respiratory leukocyte subpopulations across different strains is unknown.

Methods

By using multiparameter flow cytometry we have quantitated respiratory leukocyte subsets including dendritic cells subpopulations, macrophages, classical T and B cells, natural killer cells, γδTCR+ T cells and lineage-negative leukocytes in the five most common inbred mouse strains BALB/c, C57BL/6, DBA/2, 129SV and C3H. To minimize confounding environmental factors, age-matched animals were received from the same provider and were housed under identical specific-pathogen-free conditions.

Results

Results revealed significant strain differences with respect to respiratory neutrophils (p=0.005; up to 1.4 fold differences versus C57BL/6 mice), eosinophils (p=0.029; up to 2.7 fold), certain dendritic cell subsets (p≤0.0003; up to 3.4 fold), T (p<0.001; up to 1.6 fold) and B lymphocyte subsets (p=0.005; up to 0.4 fold), γδ T lymphocytes (p=0.003; up to 1.6 fold), natural killer cells (p<0.0001; up to 0.6 fold) and lineage-negative innate leukocytes (p≤0.007; up to 3.6 fold). In contrast, total respiratory leukocytes, macrophages, total dendritic cells and bronchoalveolar lavage leukocytes did not differ significantly. Stimulation of respiratory leukocytes via Toll-like receptor 4 and 9 as well as CD3/CD28 revealed significant strain differences of TNF-α and IL-10 production.

Conclusion

Our study demonstrates significant strain heterogeneity of respiratory leukocyte subsets that may impact respiratory immunity in different disease models. Additionally, the results may help identification of optimal strains for purification of rare respiratory leukocyte subsets for ex vivo analyses.     

Segmentation of stained blood cell images measured at high scanning density with high magnification and high numerical aperture optics

In hematological morphology, it is necessary to resolve and analyze the smallest possible cellular details appearing in the light microscope. A prerequisite for computer-aided analysis of subtle morphological features is measuring the cells at a high scanning density with high magnification and high numerical aperture optics. Contrary to visual observations, the information content in a measured picture can be increased by setting the condensor's numerical aperture (NA) greater than the objective's NA. The complexity and heterogeneity of such cell images necessitate a new segmentation method that conserves the morphological information required in the subsequent image analysis, feature extraction, and cell classification. In our segmentation strategy, characteristic color difference thresholds for each nucleus and cytoplasm are combined with geometric operations, probability functions, and a cell model. All thresholds are repeatedly recalculated during the successive improvements of the image masks. None of the thresholds are fixed. This strategy segments blood cell images containing touching cells and large variations in staining, texture, size, and shape. Biological inconsistencies in the calculated cell masks are eliminated by comparing each mask with the cell model criteria integrated into the entire segmentation process. All 20,000 leukocyte images from 120 smears in our leukemia project were segmented with this method.     

Optical effects on the surrounding structure during quantitative analysis using indocyanine green videoangiography: A phantom vessel study

Various reports have been published regarding quantitative evaluations of intraoperative fluorescent intensity studies using indocyanine green (ICG) with videoangiography (VAG). The effects of scattering and point‐spread functions (PSF) on quantitative ICG‐VAG evaluations have not been investigated. Clinically, when ICG is administered through the peripheral vein, it reaches the tissue intra‐arterially. To achieve more reliable intraoperative quantitative intensity evaluations, we examined the impact of high‐intensity structures on close areas. The study was conducted using a phantom model and surgical fluorescent microscope. A region of interest (ROI) was created for the vessel model and another ROI was created within 3 cm of that. With an ROI of 6.8 mm in the vessel phantom model, 10% intensity was confirmed, even though there was no fluorescent structure. Intensity decreased gradually as the ROI moved further from the vessel model. Our study results suggest that the presence of a high‐intensity structure and the size of the ROI may affect quantitative intensity evaluations using ICG‐VAG. Results of linear regression analysis indicate that the relationship of intensity (Y) and distance (X) is as follows: Y(real/A) = 29 Exp(?0.062X) + 164.3 Exp(?1.81X). The optical effect should be considered when performing an intraoperative intensity study with a surgical microscope.      

A Framework for White Blood Cell Segmentation in Microscopic Blood Images Using Digital Image Processing

Evaluation of blood smear is a commonly clinical test these days. Most of the time, the hematologists are interested on white blood cells (WBCs) only. Digital image processing techniques can help them in their analysis and diagnosis. For example, disease like acute leukemia is detected based on the amount and condition of the WBC. The main objective of this paper is to segment the WBC to its two dominant elements: nucleus and cytoplasm. The segmentation is conducted using a proposed segmentation framework that consists of an integration of several digital image processing algorithms. Twenty microscopic blood images were tested, and the proposed framework managed to obtain 92% accuracy for nucleus segmentation and 78% for cytoplasm segmentation. The results indicate that the proposed framework is able to extract the nucleus and cytoplasm region in a WBC image sample.     

Multimodal and multiplex spectral imaging of rat cornea ex vivo using a white‐light laser source

We applied our multimodal nonlinear spectral imaging microscope to the measurement of rat cornea. We successfully obtained multiple nonlinear signals of coherent anti‐Stokes Raman scattering (CARS), third‐order sum frequency generation (TSFG), and second harmonic generation (SHG). Depending on the nonlinear optical processes, the cornea tissue was visualized with different image contrast mechanism simultaneously. Due to white‐light laser excitation, multiplex CARS and TSFG spectra were obtained. Combined multimodal and spectral analysis clearly elucidated the layered structure of rat cornea with molecular structural information. This study indicates that our multimodal nonlinear spectral microscope is a promising bioimaging method for tissue study.

Multimodal nonlinear spectral images of rat cornea at corneal epithelium and corneal stroma in the in‐plane (XY) direction. With use of the combinational analysis of different nonlinear optical processes, detailed molecular structural information is available without staining or labelling.     

Performance of a cost‐effective and automated blood counting system for resource‐limited settings operated by trained and untrained users

Current flow‐based blood counting devices require expensive and centralized medical infrastructure and are not appropriate for field use. In this article we report a streamlined, easy‐to‐use method to count red blood cells (RBC), white blood cells (WBC), platelets (PLT) and 3‐part WBC differential through a cost‐effective and automated image‐based blood counting system. The approach consists of using a compact, custom‐built microscope with large field‐of‐view to record bright‐field and fluorescence images of samples that are diluted with a single, stable reagent mixture and counted using automatic algorithms. Sample collection utilizes volume‐controlled capillary tubes, which are then dropped into a premixed, shelf‐stable solution to stain and dilute in a single step. Sample measurement and analysis are fully automated, requiring no input from the user. Cost of the system is minimized through the use of custom‐designed motorized components. We compare the performance of our system, as operated by trained and untrained users, to the clinical gold standard on 120 adult blood samples, demonstrating agreement within Clinical Laboratory Improvement Amendments guidelines, with no statistical difference in performance among different operator groups. The system's cost‐effectiveness, automation and performance indicate that it can be successfully translated for use in low‐resource settings where central hematology laboratories are not accessible.      

Large‐depth‐of‐field full‐field optical angiography

A large‐depth‐of‐field full‐field optical angiography (LD‐FFOA) method is developed to expand the depth‐of‐field (DOF) using a contrast pyramid fusion algorithm (CPFA). The absorption intensity fluctuation modulation effect is utilized to obtain full‐field optical angiography (FFOA) images at different focus positions. The CPFA is used to process these FFOA images with different focuses. By selecting high‐contrast areas, the CPFA can highlight the characteristics and details of blood vessels to obtain LD‐FFOA images. In the optimal case of the proposed method, the DOF for FFOA is more than tripled using 10 differently focused FFOA images. Both the phantom and animal experimental results show that the LD‐FFOA resolves FFOA defocusing issues induced by surface and thickness inhomogeneities in biological samples. The proposed method can be potentially applied to practical biological experiments.      

aBEAT: A Toolbox for Consistent Analysis of Longitudinal Adult Brain MRI

Longitudinal brain image analysis is critical for revealing subtle but complex structural and functional changes of brain during aging or in neurodevelopmental disease. However, even with the rapid increase of clinical research and trials, a software toolbox dedicated for longitudinal image analysis is still lacking publicly. To cater for this increasing need, we have developed a dedicated 4D Adult Brain Extraction and Analysis Toolbox (aBEAT) to provide robust and accurate analysis of the longitudinal adult brain MR images. Specially, a group of image processing tools were integrated into aBEAT, including 4D brain extraction, 4D tissue segmentation, and 4D brain labeling. First, a 4D deformable-surface-based brain extraction algorithm, which can deform serial brain surfaces simultaneously under temporal smoothness constraint, was developed for consistent brain extraction. Second, a level-sets-based 4D tissue segmentation algorithm that incorporates local intensity distribution, spatial cortical-thickness constraint, and temporal cortical-thickness consistency was also included in aBEAT for consistent brain tissue segmentation. Third, a longitudinal groupwise image registration framework was further integrated into aBEAT for consistent ROI labeling by simultaneously warping a pre-labeled brain atlas to the longitudinal brain images. The performance of aBEAT has been extensively evaluated on a large number of longitudinal MR T1 images which include normal and dementia subjects, achieving very promising results. A Linux-based standalone package of aBEAT is now freely available at http://www.nitrc.org/projects/abeat.     

Bone‐specific kinetic model to quantify periosteal and endosteal blood flow using indocyanine green in fluorescence guided orthopedic surgery

This letter describes a hybrid plug/compartment (HyPC) kinetic model to fit dynamic indocyanine green fluorescence data acquired in a porcine model of long bone traumatic fracture. Parametric images of periosteal blood flow, endosteal blood flow, total bone blood flow and fraction of endosteal‐to‐periosteal flow were obtained by applying the HyPC model on a pixel‐by‐pixel basis. Intraoperative discrimination between healthy and damaged bone could facilitate debridement reducing post‐operative complications from non‐union and infection. The ability to quantify periosteal and endosteal blood flow could inform nail vs. plate‐and‐screw decisions to avoid further compromising cortical blood supply.      

Detection and measurement of a single blood cell surface antigen by thermal lens microscopy

A highly sensitive method for detection of antigens on the surface of a single blood cell using thermal lens microscopy is described. Colloidal gold, coated with antibody, was used to stain membrane antigens of leukocytes. Human leukocyte antigens on the lymphocytes and mononuclear leukocytes were observed by new thermal lens microscopy, which involves spectrometry using a laser-induced thermal-lens effect. Antigens of HLA-A, -B, and -C loci on the lymphocytes were identified and quantitated using a single cell. The image of HLA-A, -B, and -C antigen distribution on a mononuclear leukocyte was obtained. Our laser microscope, newly devised for measuring convex surface cells, is a powerful analytical tool for detecting and quantitating localized antigens in a single cell and/or cell-surface-associated molecules.     

Automated three‐dimensional cell counting method for grading uveitis of rodent eye in vivo with optical coherence tomography

In preclinical vision research, cell grading in small animal models is essential for the quantitative evaluation of intraocular inflammation. Here, we present a new and practical optical coherence tomography (OCT) image analysis method for the automated detection and counting of aqueous cells in the anterior chamber (AC) of a rodent model of uveitis. Anterior segment OCT images are acquired with a 100 kHz swept‐source OCT system. The proposed method consists of 2 steps. In the first step, we first despeckle and binarize each OCT image. After removing AS structures in the binary image, we then apply area thresholding to isolate cell‐like objects. Potential cell candidates are selected based on their best fit to roundness. The second step performs the cell counting within the whole AC, in which additional cell tracking analysis is conducted on the successive OCT images to eliminate redundancy in cell counting. Finally, 3D cell grading using the proposed method is demonstrated in longitudinal OCT imaging of a mouse model of anterior uveitis in vivo. Rendering of anterior segment (orange) of mouse eye and automatically counted anterior chamber cells (green). Inset is a top view of the rendering, showing the cell distribution across the anterior chamber.      

Increased recruitment but impaired function of leukocytes during inflammation in mouse models of type 1 and type 2 diabetes

Background

Patients suffering from diabetes show defective bacterial clearance. This study investigates the effects of elevated plasma glucose levels during diabetes on leukocyte recruitment and function in established models of inflammation.

Methodology/Principal Findings

Diabetes was induced in C57Bl/6 mice by intravenous alloxan (causing severe hyperglycemia), or by high fat diet (moderate hyperglycemia). Leukocyte recruitment was studied in anaesthetized mice using intravital microscopy of exposed cremaster muscles, where numbers of rolling, adherent and emigrated leukocytes were quantified before and during exposure to the inflammatory chemokine MIP-2 (0.5 nM). During basal conditions, prior to addition of chemokine, the adherent and emigrated leukocytes were increased in both alloxan- (62±18% and 85±21%, respectively) and high fat diet-induced (77±25% and 86±17%, respectively) diabetes compared to control mice. MIP-2 induced leukocyte emigration in all groups, albeit significantly more cells emigrated in alloxan-treated mice (15.3±1.0) compared to control (8.0±1.1) mice. Bacterial clearance was followed for 10 days after subcutaneous injection of bioluminescent S. aureus using non-invasive IVIS imaging, and the inflammatory response was assessed by Myeloperoxidase-ELISA and confocal imaging. The phagocytic ability of leukocytes was assessed using LPS-coated fluorescent beads and flow cytometry. Despite efficient leukocyte recruitment, alloxan-treated mice demonstrated an impaired ability to clear bacterial infection, which we found correlated to a 50% decreased phagocytic ability of leukocytes in diabetic mice.

Conclusions/Significance

These results indicate that reduced ability to clear bacterial infections observed during experimentally induced diabetes is not due to reduced leukocyte recruitment since sustained hyperglycemia results in increased levels of adherent and emigrated leukocytes in mouse models of type 1 and type 2 diabetes. Instead, decreased phagocytic ability observed for leukocytes isolated from diabetic mice might account for the impaired bacterial clearance.