scholarly journals Methodical Approaches of Image Analysis on Malarial Parasites Identification and Categorization in Thick Blood Smears-A Review

2018 ◽  
Vol 4 (2) ◽  
pp. 5-28
Author(s):  
C Berin Jones ◽  
◽  
T Susitha ◽  
Keyword(s):  
Image Analysis ◽  
Blood Smears

scholarly journals Image Analysis Using Machine Learning for Automated Detection of Hemoglobin H Inclusions in Blood Smears - A Method for Morphologic Detection of Rare Cells

2021 ◽  
Vol 12 (1) ◽  
pp. 18
Author(s):  
ShirYing Lee ◽  
CrystalM E Chen ◽  
ElaineY P Lim ◽  
Liang Shen ◽  
Aneesh Sathe ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Analysis ◽  
Automated Detection ◽  
Blood Smears ◽  
Rare Cells

Percentage of Smudge Cells Predicting Prognosis In Chronic Lymphocytic Leukemia

Blood ◽  
2010 ◽  
Vol 116 (21) ◽  
pp. 4624-4624
Author(s):  
Ravikumar Paluri ◽  
Supriya Koya ◽  
Randall S. Davis ◽  
Fun Jun Li ◽  
Alan B Cantor ◽  
...  
Keyword(s):  
Image Analysis ◽  
Chronic Lymphocytic Leukemia ◽  
Lymphocytic Leukemia ◽  
Cell Counting ◽  
Lower Percentage ◽  
Categorical Variables ◽  
Clinical Parameters ◽  
Computerized Image Analysis ◽  
Cell Percentage ◽  
Blood Smears

Abstract Abstract 4624 Background: Identifying prognostic markers is important for clinical and pathological course of chronic lymphocytic leukemia. Percentage of smudge cells in CLL patients has recently been reported as a novel prognostic factor. We present here the preliminary results of the retrospective cohort study of 90 patients diagnosed with CLL at a major referral center in the state of Alabama between 1997 and 2009. Methods: Smudge cell percentage (ratio of smudge cells to combined smudge cells and intact cells) was calculated by microscopic evaluation of archived Wright-Giemsa stained blood smears. A total of 200 cell differential was counted for inter-observer consistency. For the first time, the concordance between observers was assessed by quantization of morphological parameters of lymphocytes using computerized image analysis. Medical records of above mentioned patients were reviewed for molecular, genetic and clinical parameters including CD38, ZAP 70 expression, immunocytopenias and response to first treatment. Primary endpoint of this analysis was time to initiation of chemotherapy for first treatment (TIFT). It was calculated from date of first diagnosis until first dose of chemotherapy. Untreated patients in the follow up were censored. Kaplan Meier survival analysis and log rank test were used for statistical analysis. Prognostic factors for TIFT were analyzed with Cox's proportional hazards regression. Wilcoxon rank sum test and Fishers exact test were used to evaluate differences between groups for continuous and categorical variables, respectively. We had more than 90% Power to detect an association between smudge cell percentage and TIFT. Results: Of the 160 treatment naïve CLL patients enrolled for the study, 90 had archived blood smears available for evaluation. Patient characteristics include Rai stage 0 or 1 disease (87%), CD 38+ (30%), Zap 70 + (35%), 13q Del + (26%). Percentage of smudge cells ranged from 2 to 90 % (median 34%). Patients with CD38+ and ZAP 70+ on flow cytometry had lower percentage of smudge cell than those with negative markers and are trending towards significance (p=0.08). Our cohort included 16% of African American population and had no significant difference in TIFT when compared to Caucasians. In univariate analysis smudge cell percentage (stratified as less than or more than 30) was significantly associated with TIFT (p=0.04). Rai stages 0, 1 and 2 were significantly associated with longer TIFT than stage 3 and 4 (p= 0.01). Genetic parameters- deletion 13 q and 11q were associated with significantly greater TIFT (p= 0.008 and P=0.001 respectively). Patients who developed immunocytopenias during the course of study had shorter TIFT (p=0.01). We performed Step wise multivariate Cox regression analysis and identified del11q (HR=0.02, p=0.001) and Rai stage (HR=0.008, p <0.0001) as independent predictors of TIFT. Patients with longer TIFT had better response to treatment when compared to shorter TIFT (68% vs 32%, p=0.05). Contrary to our expectation, we found that, in multivariate analysis, we found smudge cell percentage is not significantly associated with TIFT (p= 0.75). Conclusion: Time for initiation of first treatment is significantly shorter in CLL patients with del11q and del13q and those who develop immunocytopenias. Smudge cell percentage did not significantly predict TIFT in this single center study. We speculate this could be due to subjective decision on initiation of chemotherapy by physicians, based on several other clinical parameters and co-morbidities. Larger studies are needed that concurrently assess any confounders between smudge cell percentage and TIFT. Alternatively, computerized image analysis is superior to observer measurements and can be considered for accuracy and reproducibility of cytological evaluation. It can ascertain the objectivity of concordance in differential cell counting in similar studies. Disclosures: No relevant conflicts of interest to declare.

Detection of microfilariae in peripheral blood smears using image analysis

2013 ◽  
Author(s):  
Sudaraka Mallawaarachchi ◽  
G. V. A. Premalal ◽  
K. W. S. S. Wimalana ◽  
A. S. Liyanage ◽  
Sagarika Samarasinghe ◽  
...  
Keyword(s):  
Image Analysis ◽  
Peripheral Blood ◽  
Blood Smears ◽  
Peripheral Blood Smears

Automated Image Analysis Of Nuclear And Cytoplasmic Changes In Exfoliated Cells From Tracheas Treated With Carcinogen

1977 ◽  
Vol 35 ◽  
pp. 220-221
Author(s):  
S.F. Stinson ◽  
J.C. Lilga ◽  
M.B. Sporn
Keyword(s):  
Image Analysis ◽  
Pattern Analysis ◽  
Relative Proportion ◽  
Automated Image Analysis ◽  
Image Analyzer ◽  
Cross Sectional ◽  
Exfoliated Cells ◽  
Neoplastic Lesions ◽  
Analysis System ◽  
Morphologic Criterion

Increased nuclear size, resulting in an increase in the relative proportion of nuclear to cytoplasmic sizes, is an important morphologic criterion for the evaluation of neoplastic and pre-neoplastic cells. This paper describes investigations into the suitability of automated image analysis for quantitating changes in nuclear and cytoplasmic cross-sectional areas in exfoliated cells from tracheas treated with carcinogen.Neoplastic and pre-neoplastic lesions were induced in the tracheas of Syrian hamsters with the carcinogen N-methyl-N-nitrosourea. Cytology samples were collected intra-tracheally with a specially designed catheter (1) and stained by a modified Papanicolaou technique. Three cytology specimens were selected from animals with normal tracheas, 3 from animals with dysplastic changes, and 3 from animals with epidermoid carcinoma. One hundred randomly selected cells on each slide were analyzed with a Bausch and Lomb Pattern Analysis System automated image analyzer.

Progress In The Practical Application Of Automated Image Analysis To Tem Negatives

1977 ◽  
Vol 35 ◽  
pp. 214-217
Author(s):  
F. A. Heckman ◽  
E. Redman ◽  
J.E. Connolly
Keyword(s):  
Image Analysis ◽  
Image Quality ◽  
Exposure Time ◽  
Image Contrast ◽  
Automated Image Analysis ◽  
Practical Application ◽  
Factors Affecting ◽  
High Image Quality ◽  
Qualitative Evidence ◽  
Comprehensive Study

In our initial publication on this subject1) we reported results demonstrating that contrast is the most important factor in producing the high image quality required for reliable image analysis. We also listed the factors which enhance contrast in order of the experimentally determined magnitude of their effect. The two most powerful factors affecting image contrast attainable with sheet film are beam intensity and KV. At that time we had only qualitative evidence for the ranking of enhancing factors. Later we carried out the densitometric measurements which led to the results outlined below.Meaningful evaluations of the cause-effect relationships among the considerable number of variables in preparing EM negatives depend on doing things in a systematic way, varying only one parameter at a time. Unless otherwise noted, we adhered to the following procedure evolved during our comprehensive study:Philips EM-300; 30μ objective aperature; magnification 7000- 12000X, exposure time 1 second, anti-contamination device operating.

A New System For Optomanual Semiautomatic Quantitative Image Analysis

1977 ◽  
Vol 35 ◽  
pp. 210-211
Author(s):  
H.P. Rohr
Keyword(s):  
Image Analysis ◽  
Volume Density ◽  
List Type ◽  
Distribution Analysis ◽  
Type Number ◽  
Point Counting ◽  
Human Eye ◽  
Quantitative Image ◽  
Point Density ◽  
Electronic Counting

Today, in image analysis the broadest possible rationalization and economization have become desirable. Basically, there are two approaches for image analysis: The image analysis through the so-called scanning methods which are usually performed without the human eye and the systems of optical semiautomatic analysis completely relying on the human eye.The new MOP AM 01 opto-manual system (fig.) represents one of the very promising approaches in this field. The instrument consists of an electronic counting and storing unit, which incorporates a microprocessor and a keyboard for choice of measuring parameters, well designed for easy use.Using the MOP AM 01 there are three possibilities of image analysis:the manual point counting,the opto-manual point counting andthe measurement of absolute areas and/or length (size distribution analysis included).To determine a point density for the calculation of the corresponding volume density the intercepts lying within the structure are scanned with the light pen.

Application of Modified Bloch Waves to Image Analysis of Extended Linear Defects

1974 ◽  
Vol 32 ◽  
pp. 402-403
Author(s):  
S. Nakahara ◽  
D. M. Maher
Keyword(s):  
Image Analysis ◽  
Computational Approach ◽  
Dislocation Loops ◽  
Plane Wave Expansion ◽  
Dynamical Equations ◽  
Bloch Waves ◽  
Linear Defects ◽  
Imperfect Crystal ◽  
Localized Defects ◽  
Defective Crystals

Since Head first demonstrated the advantages of computer displayed theoretical intensities from defective crystals, computer display techniques have become important in image analysis. However the computational methods employed resort largely to numerical integration of the dynamical equations of electron diffraction. As a consequence, the interpretation of the results in terms of the defect displacement field and diffracting variables is difficult to follow in detail. In contrast to this type of computational approach which is based on a plane-wave expansion of the excited waves within the crystal (i.e. Darwin representation ), Wilkens assumed scattering of modified Bloch waves by an imperfect crystal. For localized defects, the wave amplitudes can be described analytically and this formulation has been used successfully to predict the black-white symmetry of images arising from small dislocation loops.

Sign in / Sign up

Export Citation Format

Share Document