scholarly journals Blob Detection and Deep Learning for Leukemic Blood Image Analysis

2020 ◽  
Vol 10 (3) ◽  
pp. 1176
Author(s):  
Cecilia Di Ruberto ◽  
Andrea Loddo ◽  
Giovanni Puglisi
Keyword(s):  
Blood Cells ◽  
Complete Blood Count ◽  
State Of The Art ◽  
White Blood Cells ◽  
Blob Detection ◽  
Manual Inspection ◽  
Blood Smear Examination ◽  
Novel Method ◽  
Public Datasets ◽  
Processing Techniques

In microscopy, laboratory tests make use of cell counters or flow cytometers to perform tests on blood cells, like the complete blood count, rapidly. However, a manual blood smear examination is still needed to verify the counter results and to monitor patients under therapy. Moreover, the manual inspection permits the description of the cells’ appearance, as well as any abnormalities. Unfortunately, manual analysis is long and tedious, and its result can be subjective and error-prone. Nevertheless, using image processing techniques, it is possible to automate the entire workflow, both reducing the operators’ workload and improving the diagnosis results. In this paper, we propose a novel method for recognizing white blood cells from microscopic blood images and classify them as healthy or affected by leukemia. The presented system is tested on public datasets for leukemia detection, the SMC-IDB, the IUMS-IDB, and the ALL-IDB. The results are promising, achieving 100% accuracy for the first two datasets and 99.7% for the ALL-IDB in white cells detection and 94.1% in leukemia classification, outperforming the state-of-the-art.

scholarly journals New Segmentation and Feature Extraction Algorithm for the Classification of White Blood Cells in Peripheral Smear Images

2021 ◽  
Author(s):  
Eslam Tavakoli ◽  
Ali Ghaffari ◽  
Seyedeh-Zahra Mousavi Kouzehkanan ◽  
Reshad Hosseini
Keyword(s):  
Blood Cells ◽  
White Blood Cells ◽  
Dice Similarity Coefficient ◽  
Second Phase ◽  
Peripheral Smear ◽  
Color Features ◽  
Svm Model ◽  
Extraction Algorithm ◽  
Processing Techniques

This article addresses a new method for classification of white blood cells (WBCs) using image processing techniques and machine learning methods. The proposed method consists of three steps: detecting the nucleus and cytoplasm, extracting features, and classification. At first, a new algorithm is designed to segment the nucleus. For the cytoplasm to be detected, only a part of it which is located inside the convex hull of the nucleus is involved in the process. This attitude helps us overcome the difficulties of segmenting the cytoplasm. In the second phase, three shape and four novel color features are devised and extracted. Finally, by using an SVM model, the WBCs are classified. The segmentation algorithm can detect the nucleus with a dice similarity coefficient of 0.9675. The proposed method can categorize WBCs in Raabin-WBC, LISC, and BCCD datasets with accuracies of 94.47 %, 92.21 %, and 94.20 %, respectively. It is worth mentioning that the hyperparameters of the classifier are fixed only with Raabin-WBC dataset, and these parameters are not readjusted for LISC and BCCD datasets. The obtained results demonstrate that the proposed method is robust, fast, and accurate.

scholarly journals Klasifikasi Sel Darah Putih dan Sel Limfoblas Menggunakan Metode Multilayer Perceptron Backpropagation

2019 ◽  
Vol 9 (2) ◽  
pp. 173
Author(s):  
Apri Nur Liyantoko ◽  
Ika Candradewi ◽  
Agus Harjoko
Keyword(s):  
Blood Cell ◽  
White Blood Cell ◽  
Blood Cells ◽  
White Blood Cells ◽  
Back Propagation ◽  
Cell Types ◽  
Diagnostic Process ◽  
The Subject ◽  
Processing Techniques

 Leukemia is a type of cancer that is on white blood cell. This disease are characterized by abundance of abnormal white blood cell called lymphoblast in the bone marrow. Classification of blood cell types, calculation of the ratio of cell types and comparison with normal blood cells can be the subject of diagnosing this disease. The diagnostic process is carried out manually by hematologists through microscopic image. This method is likely to provide a subjective result and time-consuming.The application of digital image processing techniques and machine learning in the process of classifying white blood cells can provide more objective results. This research used thresholding method as segmentation and  multilayer method of back propagation perceptron with variations in the extraction of textural features, geometry, and colors. The results of segmentation testing in this study amounted to 68.70%. Whereas the classification test shows that the combination of feature extraction of GLCM features, geometry features, and color features gives the best results. This test produces an accuration value 91.43%, precision value of 50.63%, sensitivity 56.67%, F1Score 51.95%, and specitifity 94.16%.

scholarly journals A MATLAB model for diagnosing sickle cells and other blood abnormalities using image processing

2021 ◽  
Vol 11 (6) ◽  
pp. 5060
Author(s):  
Mohammed Al-Momin ◽  
Ammar Almomin
Keyword(s):  
Image Processing ◽  
Blood Cells ◽  
White Blood Cells ◽  
Problem Of Time ◽  
Blood Constituents ◽  
Sickle Cells ◽  
Blood Disorder ◽  
Blood Smears ◽  
High Level ◽  
Processing Techniques

<span lang="EN-US">The conventional method for detecting blood abnormality is time consuming and lacks the high level of accuracy. In this paper a MATLAB based solution has been suggested to tackle the problem of time consumption and accuracy. Three types of blood abnormality have been covered here, namely, anemia which is characterized by low count of red blood cells (RBCs), Leukemia which is depicted by increasing the number of white blood cells (WBCs), and sickle cell blood disorder which is caused by a deformation in the shape of red cells. The algorithm has been tested on different images of blood smears and noticed to give an acceptable level of accuracy. Image processing techniques has been used here to detect the different types of blood constituents. Unlike many other researches, this research includes the blood sickling disorder which is epidemic in certain regions of the world, and offers a more accuracy than other algorithms through the use of detaching overlapped cells strategy.</span>

scholarly journals Hematologic Changes in Patients with Graves’ disease in Gorgan During 2014-2015

2017 ◽  
Vol 2 (3) ◽  
pp. 106
Author(s):  
Maryam Zahedi ◽  
Farzam Mirkamali ◽  
Sharabeh Hezarkhani ◽  
Armineh Motiee ◽  
Arash Rezaei Shahmirzadi ◽  
...  
Keyword(s):  
Blood Cells ◽  
Complete Blood Count ◽  
Statistical Significance ◽  
White Blood Cells ◽  
P Value ◽  
Graves Disease ◽  
Thyroid Disorder ◽  
Cross Sectional ◽  
Mild Anemia ◽  
Before And After

Background: The most common cause of hyperthyroidism in areas without iodine deficiency is Graves’ disease. There are reports of some hematological alterations in hyperthyroidism. This study was designed to measure the hematologic profile in the patients with Graves’ disease before and after the treatment.Methods: In this cross-sectional study, 100 patients were selected with convenience sampling that diagnosed as autoimmune Graves’ disease in our academic endocrinology clinic during 2014-2015. Inclusion criteria included autoimmune hyperthyroidism in patients who were referred to this center during the study period. Patients who refused to take part in the research, had recent infections disease, malignancies, surgical procedures, severe trauma, received immunosuppressive drugs or corticosteroids, high erythrocyte sedimentation rate (ESR) values during the last six months, and not responded to treatment with methimazole were excluded from the study. The simple sampling technique was used to select the patients.   A complete blood count (CBC) was taken before and after treatment. The P-value less than 0.05 was considered as the statistical significance level. All data were analyzed using the Statistical Package for the Social Sciences 16.0 (SPSS Inc., Chicago, IL, USA) software.Results: One hundred patients with a mean age of 38 ± 9.8 years were included. There were no significant changes in the white blood cells (WBC) count, red blood cells (RBC) count, and platelets. Mild anemia (Hb=12.16±1.23) present before treating the hyperthyroidism that was significantly improved after treatment (P= 0.000). Conclusions: Our results showed that the only significant hematologic change in patients with Graves’ disease was mild anemia that improves after treating the underlying thyroid disorder. 

scholarly journals Haematological Changes in Donors Post Apheresis

2021 ◽  
Author(s):  
. Nikhil ◽  
Subhashish Das ◽  
. Snigdha
Keyword(s):  
Platelet Count ◽  
Blood Cells ◽  
Complete Blood Count ◽  
White Blood Cells ◽  
Haemoglobin Concentration ◽  
Point Of View ◽  
Haematological Parameters ◽  
Cross Sectional ◽  
Wbc Count ◽  
Rbc Count

Introduction: The productivity, quality of platelet apheresis collection has improved because of the considerable advancement in the automated cell separators. Automated cell separators have lot of sizeable scientific advances, but the alertness has been centered to Platelet Concentrates (PCs) quality than on safety of donor. Aim: To find the changes in haematological parameters and the consequences of apheresis and plateletpheresis on donor’s health. Materials and Methods: It was observational cross-sectional study done in laboratory at RL Jalappa Blood Bank, Tamaka, Kolar, Karnataka, India. The study was done from March 2019 to August 2020. A total of 300 healthy donors (plateletpheresis donors) were involved in the study. The plateletpheresis (Haemonetics MCS), predonation and postdonation haematological parameters such as haemoglobin concentration, Haematocrit (Hct), platelet, white and red blood cell count were calculated in all donors. The samples for Complete Blood Count (CBC) were secured from the donors, at the beginning and end of the procedure. Postdonation haematological parameters such as platelet count, haemoglobin, haematocrit, White Blood Cells (WBC), Red Blood Cells (RBC) counts of the donor was inscribed and comparison was done with the pre donation haematological parameters. Quality control of all Single Donor Platelet (SDP) products was done. All donors were evaluated for adverse donor reactions. The mean pre and post plateletpheresis values comparison was done utilising paired t-test. Statistical analysis was accomplished utilising Statistical Package for the Social Sciences (SPSS) software version 16.0. Results: Platelet count, haemoglobin, WBC count, RBC count and haematocrit were jotted down from 262 donors and a significant decrease was noticed in these parameters postdonation. Donor parameter platelet count (lac/mL) value was decreased from 273.57-224.28 whereas WBC count (cu/mm) predonation value decreased from 9.91-8.86 Postdonation, haemoglobin (g/dL) value decreased from 14.46-12.91, haematocrit (%) decreased slightly from 45.19-44.19, RBC count (million/mm3) decreased from 5.21-5.01. This concluded that the values decreased postdonation. Conclusion: The study conducted was safe from donor’s point of view. SDP is very effective in treatment of thrombocytopenia and is safe from recipient’s point of view.

scholarly journals Enhancing Label Representations with Relational Inductive Bias Constraint for Fine-Grained Entity Typing

2021 ◽  
Author(s):  
Jinqing Li ◽  
Xiaojun Chen ◽  
Dakui Wang ◽  
Yuwei Li
Keyword(s):  
State Of The Art ◽  
Phase 1 ◽  
Phase 2 ◽  
Two Phase ◽  
Inductive Bias ◽  
Fine Grained ◽  
Wide Range ◽  
Dynamic Experiments ◽  
Novel Method ◽  
Public Datasets

Fine-Grained Entity Typing (FGET) is a task that aims at classifying an entity mention into a wide range of entity label types. Recent researches improve the task performance by imposing the label-relational inductive bias based on the hierarchy of labels or label co-occurrence graph. However, they usually overlook explicit interactions between instances and labels which may limit the capability of label representations. Therefore, we propose a novel method based on a two-phase graph network for the FGET task to enhance the label representations, via imposing the relational inductive biases of instance-to-label and label-to-label. In the phase 1, instance features will be introduced into label representations to make the label representations more representative. In the phase 2, interactions of labels will capture dependency relationships among them thus make label representations more smooth. During prediction, we introduce a pseudo-label generator for the construction of the two-phase graph. The input instances differ from batch to batch so that the label representations are dynamic. Experiments on three public datasets verify the effectiveness and stability of our proposed method and achieve state-of-the-art results on their testing sets.

Application of Biomedical Image Processing in Blood Cell Counting using Hough Transform

2016 ◽  
pp. 359-378 ◽  
Author(s):  
Manali Mukherjee ◽  
Kamarujjaman ◽  
Mausumi Maitra
Keyword(s):  
Blood Cell ◽  
Blood Cells ◽  
Complete Blood Count ◽  
White Blood Cells ◽  
Blood Stream ◽  
Cell Counting ◽  
Biomedical Image Processing ◽  
Microscopic Images ◽  
Biomedical Image ◽  
Rapid Heart Rate

In the field of biomedicine, blood cells are complex in nature. Nowadays, microscopic images are used in several laboratories for detecting cells or parasite by technician. The microscopic images of a blood stream contain RBCs, WBCs and Platelets. Blood cells are produced in the bone marrow and regularly released into circulation. Blood counts are monitored with a laboratory test called a Complete Blood Count (CBC). However, certain circumstances may cause to have fewer cells than is considered normal, a condition which is called “low blood counts”.This can be accomplished with the administration of blood cell growth factors. Common symptoms due to low red blood cells are:fatigue or tiredness, trouble breathing, rapid heart rate, difficulty staying warm, pale skin etc. Common symptoms due to low white blood cells are: infection, fever etc. It is important to monitor for low blood cell count because conditions could increase the risk of unpleasant and sometimes life-threatening side effects.

Performance evaluation of Sysmex XN hematology analyzer in umbilical cord blood: a comparison study with Sysmex XE-2100

2014 ◽  
Vol 52 (12) ◽  
Author(s):  
Hanah Kim ◽  
Mina Hur ◽  
Sang-Gyeu Choi ◽  
Hee-Won Moon ◽  
Yeo-Min Yun ◽  
...  
Keyword(s):  
Cord Blood ◽  
Umbilical Cord ◽  
Umbilical Cord Blood ◽  
Blood Cells ◽  
Complete Blood Count ◽  
White Blood Cells ◽  
Modular System ◽  
Hematopoietic Stem ◽  
Nucleated Red Blood Cells ◽  
Hematology Analyzer

AbstractThe Sysmex XN (XN) modular system (Sysmex, Kobe, Japan) is a new automated hematology analyzer equipped with different principles from its previous version, Sysmex XE-2100. We compared the performances of Sysmex XN and XE-2100 in umbilical cord blood (CB) specimens.In 160 CB specimens, complete blood count (CBC) parameters and white blood cells (WBC) differentials were compared between the two analyzers. Their flagging performances for blasts, abnormal/atypical lymphocytes, immature granulocytes and/or left-shift (IG), and nucleated red blood cells (NRBC) counts were compared with manual counts. For the blast flagging, Q values by Sysmex XN were further compared with manual slide review.Sysmex XN and XE-2100 showed high or very high correlations for most CBC parameters but variable correlations for WBC differentials. Compared with XE-2100, XN showed significantly different flagging performances for blasts, abnormal/atypical lymphocytes, and IG. The flagging efficiency for blasts was significantly better on Sysmex XN than on XE-2100 (85.0% vs. 38.8%): Sysmex XN showed a remarkably increased specificity of blast flag, compromising its sensitivity of blast flag. Among the 24 specimens with blasts (range, 0.5%–1.5%), only one (4.2%) showed a positive Q value.This study highlighted the remarkable differences of flagging performances between Sysmex XN and XE-2100 in CB specimens. The Sysmex XN modular system seems to be a suitable and practical option for the CB specimens used for hematopoietic stem cell transplantation as well as for the specimens from neonates.

scholarly journals Automatic Detection and Counting of Blood Cells in Smear Images Using RetinaNet

Entropy ◽  
2021 ◽  
Vol 23 (11) ◽  
pp. 1522
Author(s):  
Grzegorz Drałus ◽  
Damian Mazur ◽  
Anna Czmil
Keyword(s):  
Blood Cells ◽  
Complete Blood Count ◽  
White Blood Cells ◽  
Relevant Information ◽  
Disease Diagnosis ◽  
Cell Counting ◽  
Additional Advantage ◽  
Manual Counting ◽  
Detection And Counting ◽  
Deep Learning Network

A complete blood count is one of the significant clinical tests that evaluates overall human health and provides relevant information for disease diagnosis. The conventional strategies of blood cell counting include manual counting as well as counting using the hemocytometer and are tedious and time-consuming tasks. This research-based paper proposes an automatic software-based alternative method to count blood cells accurately using the RetinaNet deep learning network, which is used to recognize and classify objects in microscopic images. After training, the network automatically recognizes and counts red blood cells, white blood cells, and platelets. We tested a model trained on smear images and found that the trained model has generalized capabilities. We assessed the quality of detection and cell counting using performance measures, such as accuracy, sensitivity, precision, and F1-score. Moreover, we studied the dependence of the confidence thresholds and the number of learning epochs on the obtained results of recognition and counting. We compared the performance of the proposed approach with those obtained by other authors who dealt with the subject of cell counting and show that object detection and labeling can be an additional advantage in the task of counting objects.

scholarly journals Classification of White Blood Cell Abnormalities for Early Detection of Myeloproliferative Neoplasms Syndrome Based on K-Nearest Neighborr

2020 ◽  
Vol 7 (1) ◽  
pp. 136-142
Author(s):  
Zilvanhisna Emka Fitri ◽  
Lindri Nalentine Yolanda Syahputri ◽  
Arizal Mujibtamala Nanda Imron
Keyword(s):  
Blood Cell ◽  
White Blood Cell ◽  
Blood Cells ◽  
Myeloproliferative Neoplasms ◽  
White Blood Cells ◽  
Color Space ◽  
Hematopoietic Stem ◽  
Large Numbers ◽  
Initial Symptoms ◽  
Processing Techniques

The myeloproliferative neoplasms (MPNs) are clonal hematopoietic stem cell disorders characterized by dysregulated proliferation and expansion of one or more of the myeloid lineages. The initial symptoms of MPN is a bone marrow abnormalities when producing red blood cells, white blood cells and platelets in large numbers and uncontrolled. An automatic and accurate white blood cell abnormality classification system is needed. This research uses digital image processing techniques such as conversion to the modified CIELab color space, segmentation techniques based on threshold values and feature extraction processes that produce four morphological features consisting of area, perimeter, metric and compactness. then the four features become input to the K-Nearest Neighborr (KNN) method. The testing process is based on variations in the value of K to get the best accuracy percentage of 94.3% tested on 159 test data.

Sign in / Sign up

Export Citation Format

Share Document