Assessing Malaria using Neutral Zone Classifiers with Mixture Discriminant Analysis on 2D Images of Red Blood Cells

2019 ◽  
Author(s):  
Shariq Mohammed ◽  
Dipak K. Dey
Keyword(s):  
Discriminant Analysis ◽  
Red Blood Cells ◽  
Blood Cells ◽  
Cell Segmentation ◽  
Neutral Zone ◽  
Classification Problems ◽  
Linear Discriminant ◽  
Infected Cells ◽  
Neutral Zone Classifiers ◽  
2D Images

Background and Aim: We aim to build a classifier to distinguish between malaria-infected red blood cells (RBCs) and healthy cells using the two-dimensional (2D) microscopic images of RBCs. We demonstrate the process of cell segmentation and feature extraction from the 2D images. Methods and Materials: We describe an approach to address the problem using mixture discriminant analysis (MDA) on the 2D image profiles of the RBCs. The extracted features are used with Gaussian MDA to distinguish between healthy and malaria infected cells. We also use the neutral zone classifiers where ambiguous cases are identified separately by the classifier. Results: We compare the classification results from the regular classifiers such as linear discriminant analysis (LDA) or MDA and the methods where neutral zone classifiers are used. We see that including the neutral zone improves the classification results by controlling the false positive and false negatives. The number of misclassifications are seen to be lower than the case without neutral zone classifiers. Conclusion: This paper presents an alternative approach for classification by incorporating neutral zone classifier approach, where a prediction is not made for the ambiguous cases. From the data analysis we see that this approach based on neutral zone classifiers presents a useful alternative in classification problems for various applications.

scholarly journals An Efficient Image Classification of Malaria Parasite Using Convolutional Neural Network and ADAM Optimizer

2021 ◽  
Vol 12 (2) ◽  
pp. 3376-3384
Author(s):  
K. Kranthi Kumar, Et. al.
Keyword(s):  
Machine Learning ◽  
Red Blood Cells ◽  
Blood Cells ◽  
Information Science ◽  
Data Intensive ◽  
Learning Techniques ◽  
Protozoan Infection ◽  
Life Threatening ◽  
On Line ◽  
Infected Cells

Machine learning can be a technique of nursing lysis that automatically develops an analytical model. It is a branch of synthetic intelligence that believes that systems are going to learn information, determine patterns of information and decide with degraded human intervention. Machine learning addresses the question of how computers can be constructed that improve mechanically through knowledge. It lies at the intersection of technology and statistics and at the center of artificial data and information science, one in all the quickest increasing technical fields of nowadays. Recent advances in machine learning were driven by the event of latest learning and theories also as by the constant explosion. The event of latest learning algorithms and also theory and the in-progress growth within the accessibility of on-line information also as low-priced computation crystal rectifier to recent progress within the field of machine learning. Additional evidence-based decision-making could be carried out in science, technology and trade, including healthcare, production, education and monetary modelling, enforcement and promotion, with adoption of mechanical learning techniques based on data-intensive methods. The results are also available. The infection can be a life-threatening disease. The bite of a nursing partner is often transmitted in dipterous Anopheles. In infected mosquitoes, plasmodium parasite is a gift. The parasite is discharged into your blood after you bite this dipterous insect once it bites you. Once your body is composed of the parasites, they mature into the liver. The mature parasites enter the blood for several days when red blood cells start to infect. In red blood cells, parasites increase over 48-72 hours, causing infected cells to divide. The parasites still infect red blood cells, which last 2 to 3 days in cycles. This paper is used for observation of protozoan infection with a deep learning idea.

Segmentation of Overlapping Red Blood Cells for Malaria Blood Smear Images by U-Net Architecture

2021 ◽  
Vol 11 (8) ◽  
pp. 2126-2129
Author(s):  
Fatih Veysel Nurçin ◽  
Elbrus Imanov
Keyword(s):  
Deep Learning ◽  
Red Blood Cells ◽  
Blood Cells ◽  
Blood Smear ◽  
White Blood Cells ◽  
Similarity Index ◽  
Cell Segmentation ◽  
Learning Approach ◽  
Automated Segmentation ◽  
Jaccard Similarity

Automated segmentation of red blood cells is a widely applied task in order to evaluate red blood cells for certain diseases. Counting of malaria parasites requires individual red blood cell segmentation in order to evaluate the severity of infection. For such an evaluation, correct segmentation of red blood cells is required. However, it is a difficult task due to the presence of overlapping red blood cells. Existing methodologies employ preprocessing steps in order to segment red blood cells. We propose a deep learning approach that has a U-Net architecture to provide fully automated segmentation of red blood cells without any initial preprocessing. While red blood cells were segmented, irrelevant objects such as white blood cells, platelets and artifacts were removed. The network was trained and tested on 5600 and 600 samples respectively. Segmentation of overlapping red blood cells was achieved with 93.8% Jaccard similarity index. To the best of our knowledge, our results surpassed previous outcomes.

Changes in the membrane microviscosity of mouse red blood cells infected with Plasmodium berghei detected using n-(9-anthroyloxy) fatty acid fluorescent probes

Parasitology ◽  
1980 ◽  
Vol 80 (2) ◽  
pp. 331-342 ◽  
Author(s):  
R. J. Howard ◽  
W. H. Sawyer
Keyword(s):  
Fatty Acids ◽  
Red Blood Cells ◽  
Outer Membrane ◽  
Fluorescent Probes ◽  
Plasmodium Berghei ◽  
Blood Cells ◽  
Normal Mouse ◽  
Membrane Microviscosity ◽  
Infected Blood ◽  
Infected Cells

SummaryA set of n-(9-anthroyloxy) fatty acids (n = 2, 6, 9, 12, 16) have been used as fluorescent probes to examine the lipid environment at different depths in the outer membrane of normal mouse erythrocytes and red blood cells from Plasmodium berghei-infected blood. Fluorescent polarization experiments with normal mouse erythrocytes have demonstrated a typical gradient in microviscosity from the surface to the centre of the bilayer as a consequence of the motional properties of the C-atoms of the phospholipid acyl chains. The fluorescent probes rotate faster in the membrane of purified pluriparasitized cells (> 90% purity) than with the remaining fraction of red blood cells from infected blood (20–40% immature, infected red cells, and uninfected red cells), or normal mouse erythrocytes. This increase in fluidity with heavily infected cells occurs predominantly at the centre of the lipid bilayer, rather than at the membrane surface. A comparison of the polarization values of intact and lysed infected cells indicates that the fluorescent fatty acids preferentially label the plasma membrane rather than the internal membranes of infected cells. The results suggest that P. berghei infection causes a change in the composition and/or organization of the outer membrane of pluriparasitized cells which produces a decrease in membrane microviscosity.

scholarly journals Deep Regularized Discriminative Network

2021 ◽  
Vol 2 (4) ◽  
Author(s):  
Nazneen N. Sultana ◽  
Bappaditya Mandal ◽  
N. B. Puhan
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Discriminant Analysis ◽  
Convolutional Neural Network ◽  
Space Representation ◽  
Classification Problems ◽  
Linear Discriminant ◽  
Class Separability ◽  
Latent Space ◽  
Classification Tasks

AbstractTraditional linear discriminant analysis (LDA) approach discards the eigenvalues which are very small or equivalent to zero, but quite often eigenvectors corresponding to zero eigenvalues are the important dimensions for discriminant analysis. We propose an objective function which would utilize both the principal as well as nullspace eigenvalues and simultaneously inherit the class separability information onto its latent space representation. The idea is to build a convolutional neural network (CNN) and perform the regularized discriminant analysis on top of this and train it in an end-to-end fashion. The backpropagation is performed with a suitable optimizer to update the parameters so that the whole CNN approach minimizes the within class variance and maximizes the total class variance information suitable for both multi-class and binary class classification problems. Experimental results on four databases for multiple computer vision classification tasks show the efficacy of our proposed approach as compared to other popular methods.

scholarly journals Local Hematocrit Fluctuation Induced by Malaria-Infected Red Blood Cells and Its Effect on Microflow

2018 ◽  
Vol 2018 ◽  
pp. 1-14
Author(s):  
Tong Wang ◽  
Zhongwen Xing
Keyword(s):  
Blood Flow ◽  
Plasmodium Falciparum ◽  
Red Blood Cells ◽  
Blood Cells ◽  
Volume Fraction ◽  
Numerical Approach ◽  
Infected Rbcs ◽  
Infected Cells ◽  
Slow Moving ◽  
Cell Free Layer

We investigate numerically the microscale blood flow in which red blood cells (RBCs) are partially infected byPlasmodium falciparum, the malaria parasite. The infected RBCs are modeled as more rigid cells with less deformability than healthy ones. Our study illustrates that, in a 10 μm microvessel in low-hematocrit conditions (18% and 27%), thePlasmodium falciparum-infected red blood cells (Pf-IRBCs) and healthy ones first form a train of cells. Because of the slow moving of thePf-IRBCs, the local hematocrit (Hct) near thePf-IRBCs is then increased, to approximately40%or even higher values. This increase of the local hematocrit is temporary and is kept for a longer length of time because of the long RBC train formed in 27%-Hctcondition. Similar hematocrit elevation at the downstream region with 45%-Hctin the same 10 μm microvessel is also observed with the cells randomly located. In 20 μm microvessels with 45%-Hct, thePf-IRBCs slow down the velocity of the healthy red blood cells (HRBCs) around them and then locally elevate the volume fraction and result in the accumulation of the RBCs at the center of the vessels, thus leaving a thicker cell free layer (CFL) near the vessel wall than normal. Variation of wall shear stress (WSS) is caused by the fluctuation of localHctand the distance between the wall and the RBCs. Moreover, in high-hematocrit condition (45%), malaria-infected cells have a tendency to migrate to the edge of the aggregates which is due to the uninterrupted hydrodynamic interaction between the HRBCs andPf-IRBC. Our results suggest that the existence of Pf-IRBCs is a nonnegligible factor for the fluctuation of hematocrit and WSS and also contributes to the increase of CFL of pathological blood flow in microvessels. The numerical approach presented has the potential to be utilized to RBC disorders and other hematologic diseases.

On the Trace of Scatter Matrix Difference: A Convex Approximate Discriminant Analysis Formulation and Its Mechanism Research in Imperial Examination System

2015 ◽  
Vol 24 (05) ◽  
pp. 1550015
Author(s):  
Kun Li ◽  
Yongsheng Qian ◽  
Dejie Xu ◽  
Junwei Zeng ◽  
Min Wang ◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Classification Problems ◽  
Examination System ◽  
Scatter Matrix ◽  
Linear Discriminant ◽  
Mechanism Research ◽  
Optimization Function ◽  
Imperial Examination System ◽  
Imperial Examination ◽  
Eigen Decomposition

In this paper, we present a convex discriminant analysis formulation, which is extended to solve multi-label classification problems. The original Linear Discriminant Analysis energy optimization function is turned into another form as a convex formulation (namely, convex Approximate LDA, denoted as “convexALDA” for short) using the generalized eigen-decomposition. We give applications by incorporating convexALDA as a regularizer into discriminant regression analysis. Extensive experimental results on multi-label classification tasks and an extensive application scenario on communication characteristics of imperial examination system are provided. In this way we have a brand-new comprehension for it, and a new idea and method was also put forward for studying the system.

Hemoglobin crystals of the red blood cells in the human renal cortex: electron microscopic observations of the renal lithiasis

1978 ◽  
Vol 36 (2) ◽  
pp. 480-481
Author(s):  
Kosuke Ueda ◽  
Hiroto Washida ◽  
Nakazo Watari
Keyword(s):  
Red Blood Cells ◽  
Blood Cells ◽  
Renal Cortex ◽  
Uranyl Acetate ◽  
Osmic Acid ◽  
Renal Lithiasis ◽  
Electron Microscopic ◽  
Hemoglobin C ◽  
First Case ◽  
Ultrathin Sections

IntroductionHemoglobin crystals in the red blood cells were electronmicroscopically reported by Fawcett in the cat myocardium. In the human, Lessin revealed crystal-containing cells in the periphral blood of hemoglobin C disease patients. We found the hemoglobin crystals and its agglutination in the erythrocytes in the renal cortex of the human renal lithiasis, and these patients had no hematological abnormalities or other diseases out of the renal lithiasis. Hemoglobin crystals in the human erythrocytes were confirmed to be the first case in the kidney.Material and MethodsTen cases of the human renal biopsies were performed on the operations of the seven pyelolithotomies and three ureterolithotomies. The each specimens were primarily fixed in cacodylate buffered 3. 0% glutaraldehyde and post fixed in osmic acid, dehydrated in graded concentrations of ethanol, and then embedded in Epon 812. Ultrathin sections, cut on LKB microtome, were doubly stained with uranyl acetate and lead citrate.

Densitometric Identification of Primitive Erythroblasts After Reaction With Diaminobenzidine

1973 ◽  
Vol 31 ◽  
pp. 328-329
Author(s):  
John A. Trotter
Keyword(s):  
Red Blood Cells ◽  
Analytical Method ◽  
Blood Cells ◽  
Guinea Pigs ◽  
Specific Protein ◽  
Visual Examination ◽  
Hemoglobin Synthesis ◽  
Peroxidatic Activity ◽  
Small Density

Hemoglobin is the specific protein of red blood cells. Those cells in which hemoglobin synthesis is initiated are the earliest cells that can presently be considered to be committed to erythropoiesis. In order to identify such early cells electron microscopically, we have made use of the peroxidatic activity of hemoglobin by reacting the marrow of erythropoietically stimulated guinea pigs with diaminobenzidine (DAB). The reaction product appeared as a diffuse and amorphous electron opacity throughout the cytoplasm of reactive cells. The detection of small density increases of such a diffuse nature required an analytical method more sensitive and reliable than the visual examination of micrographs. A procedure was therefore devised for the evaluation of micrographs (negatives) with a densitometer (Weston Photographic Analyzer).

Sign in / Sign up

Export Citation Format

Share Document