scholarly journals AI-enabled microscopic blood analysis for microfluidic COVID-19 haematology

Author(s):  
Tiancheng Xia ◽  
Richard Fu ◽  
Nanlin Jin ◽  
Paul Chazot ◽  
Plamen Angelov ◽  
...  

Microscopic blood cell analysis is an important methodology for medical diagnosis, and complete blood cell counts (CBCs) are one of the routine tests operated in hospitals. Results of the CBCs include amounts of red blood cells, white blood cells and platelets in a unit blood sample. It is possible to diagnose diseases such as anemia when the numbers or shapes of red blood cells become abnormal. The percentage of white blood cells is one of the important indicators of many severe illnesses such as infection and cancer. The amounts of platelets are decreased when the patient suffers hemophilia. Doctors often use these as criteria to monitor the general health conditions and recovery stages of the patients in the hospital. However, many hospitals are relying on expensive hematology analyzers to perform these tests, and these procedures are often time consuming. There is a huge demand for an automated, fast and easily used CBCs method in order to avoid redundant procedures and minimize patients’ burden on costs of healthcare. In this research, we investigate a new CBC detection method by using deep neural networks, and discuss state of the art machine learning methods in order to meet the medical usage requirements. The approach we applied in this work is based on YOLOv3 algorithm, and our experimental results show the applied deep learning algorithms have a great potential for CBCs tests, promising for deployment of deep learning methods into microfluidic point-of-care medical devices. As a case of study, we applied our blood cell detector to the blood samples of COVID-19 patients, where blood cell clots are a typical symptom of COVID-19.

2020 ◽  
Author(s):  
Tiancheng Xia ◽  
Richard Fu ◽  
Nanlin Jin ◽  
Paul Chazot ◽  
Plamen Angelov ◽  
...  

Microscopic blood cell analysis is an important methodology for medical diagnosis, and complete blood cell counts (CBCs) are one of the routine tests operated in hospitals. Results of the CBCs include amounts of red blood cells, white blood cells and platelets in a unit blood sample. It is possible to diagnose diseases such as anemia when the numbers or shapes of red blood cells become abnormal. The percentage of white blood cells is one of the important indicators of many severe illnesses such as infection and cancer. The amounts of platelets are decreased when the patient suffers hemophilia. Doctors often use these as criteria to monitor the general health conditions and recovery stages of the patients in the hospital. However, many hospitals are relying on expensive hematology analyzers to perform these tests, and these procedures are often time consuming. There is a huge demand for an automated, fast and easily used CBCs method in order to avoid redundant procedures and minimize patients’ burden on costs of healthcare. In this research, we investigate a new CBC detection method by using deep neural networks, and discuss state of the art machine learning methods in order to meet the medical usage requirements. The approach we applied in this work is based on YOLOv3 algorithm, and our experimental results show the applied deep learning algorithms have a great potential for CBCs tests, promising for deployment of deep learning methods into microfluidic point-of-care medical devices. As a case of study, we applied our blood cell detector to the blood samples of COVID-19 patients, where blood cell clots are a typical symptom of COVID-19.


2020 ◽  
Vol 2 (1) ◽  
pp. 76
Author(s):  
Fatemeh Sharifi ◽  
Armin Sedighi ◽  
Mubashar Rehman

Hematology tests, considered as an initial step in the patient diagnostic process, require laboratory equipment and technicians which is a time- and labor-consuming procedure. Such facilities may be available in a few central laboratories in under-resourced countries. The growing need for low cost and rapid diagnostic tests contributes to point-of-care (POC) medical diagnostic devices providing convenient and rapid test tools particularly in areas with limited medical resources. In the present study, a comprehensive numerical simulation of a POC blood cell separation device (POC-BCS) has been modeled using a finite element method. Tag-less separation of blood cells, i.e., platelets, red blood cells, and white blood cells, was carried out using standing surface acoustic waves (SSAWs) generated by interdigital transducers (IDTs) located at lateral sides of the microfluidic channel. Blood sample intake along with sheath flow was introduced via two symmetrical tilted angle inlets and a middle inlet, respectively. Superposition of acoustic radiation force applied by SSAWs accompanied by drag force caused by medium flow drove the blood cells toward different path lines correlated to their size. White blood cells were sorted out in the middle outlet and red blood cells and platelets were sorted out through the separate locations of the side outlets. Each cell was then guided to their respected visualization chamber for further image processing analysis. The results of the presented numerical study would be very promising in designing and optimizing the POC blood testing device.


Author(s):  
Thanh Tran ◽  
Lam Binh Minh ◽  
Suk-Hwan Lee ◽  
Ki-Ryong Kwon

Clinically, knowing the number of red blood cells (RBCs) and white blood cells (WBCs) helps doctors to make the better decision on accurate diagnosis of numerous diseases. The manual cell counting is a very time-consuming and expensive process, and it depends on the experience of specialists. Therefore, a completely automatic method supporting cell counting is a viable solution for clinical laboratories. This paper proposes a novel blood cell counting procedure to address this challenge. The proposed method adopts SegNet - a deep learning semantic segmentation to simultaneously segment RBCs and WBCs. The global accuracy of the segmentation of WBCs, RBCs, and the background of peripheral blood smear images obtains 89% when segment WBCs and RBCs from the background of blood smear images. Moreover, an effective solution to separate grouped or overlapping cells and cell count is presented using Euclidean distance transform, local maxima, and connected component labeling. The counting result of the proposed procedure achieves an accuracy of 93.3% for red blood cell count using dataset 1 and 97.38% for white blood cell count using dataset 2.


2018 ◽  
Vol 1 (5) ◽  
Author(s):  
Junbei Bai

Objective To observe the national elite male rowers blood, red blood cell activity and serum copper, zinc, calcium, magnesium and iron content of the five elements, and compared with the ordinary people. Aimed to investigate the between athletes, athletes and ordinary differences between the two sets of indicators and to explore the impact of element contents in red blood cell activity and five factors. Trying to bring two sets of indicators and specific combining ability, used in training on the monitoring function, and for the future to provide some references for further study. Methods It was included 22 athletes and 22 ordinary men, as the research object, in the collection of blood, measuring red blood cell activity in the blood content of the five elements, simultaneous measurement of physical indicators , will be doing all the data at the differences between the two groups compared to the group to do correlation analysis. The recent record of 2000m, 6000m rowing Dynamometer test results, and red blood cell activity associated with the five elements of content analysis. Results 1. Athletes indicators related to aerobic exercise were significantly higher than ordinary people. The white blood cells of athletes group were average.It shows that athletes have high aerobic capacity, while white blood cells are more stable than normal people. The members of the national rowing men's iron, magnesium content was significantly higher than ordinary group, the iron content is higher than the normal reference value; blood calcium levels were significantly lower than ordinary people, and lower than the normal reference value. The total number of red blood cells and the number of living cells was very significant positive correlation in two groups subjects; Red blood cell activity and red blood cell diameter is proportional, and red blood cell roundness in inverse proportion to the relationship; from this experiment a special ability to see red blood cell activity and there is no correlation. In both groups, hemoglobin was positively correlated with iron content, while iron was positively correlated with copper content. Conclusions 1. Increasing the number and volume of red blood cells can effectively increase the activity of red blood cells; red blood cell activity has no correlation with specific ability, and can not be used as an indicator to determine specific ability. The content of iron and magnesium in rowers is higher than that in ordinary people, which indicates that the adjustment of aerobic capacity and nerve control is very effective. The lower calcium content indicates that the injury caused by calcium loss should be prevented and the urgency of calcium supplementation should be emphasized. In training, we should pay attention to increasing hemoglobin content and aerobic capacity by supplementing iron. We can further consider the effect of supplementing copper to promote iron supplementation.


2017 ◽  
Vol 24 (04) ◽  
pp. 612-616
Author(s):  
Faisal Irshad ◽  
Hina Mawani ◽  
Sana Naz

Objectives: To determine the effects of Allium sativum essential oil (ASEO)phytotherapy on serum triglycerides, total cholesterol, HDLc, LDLc and blood cell counts inalbino rat model. Study design: Experimental study. Setting and Duration: Animal House,Sindh Agriculture University and Isra University Hyderabad from May 2014 to January 2015.Materials and Methods: 60 albino rats were divided into four groups. Controls were givenPlacebo. Experimental rat groups were given ASEO 100 mg/kg, 200 mg/kg and 300 mg/kgorally for 30 days. Cardiac puncture was performed for blood sampling. Research variableswere analyzed on Statistix 10.0 (USA). Results: Blood lipids showed significant reduction invarious blood lipid fractions. Serum LDLc exhibited with a concomitant rise in serum HDLc (p=0.0001) in high ASEO treated rats. Red blood cells, white blood cells and platelet showedsignificant improvement ASEO fed rats (p=0.001). Conclusion: Allium sativum essential oil(ASEO) phytotherapy showed a rise in HDLc and a reduction in LDLc, triglycerides and totalcholesterol with improvement in red blood cell counts.


Blood ◽  
1949 ◽  
Vol 4 (5) ◽  
pp. 505-510 ◽  
Author(s):  
ROBERT S. FADEM

Abstract 1. A patient has been presented whose circulating red blood cells were composed of 65-84 per cent ovalocytes, 3-11 per cent sickled cells, and some normal appearing discoid cells. 2. The red blood cell counts and the blood indices were within normal limitations. 3. The red blood cells showed an increased resistance to hypotonic saline solutions. See PDF for Table See PDF for Table See PDF for Table 4. The peripheral blood showed a daily variation in the percentage of circulating ovalocytes, from 65 per cent to 84 per cent, and in the percentage of circulating sickle cells, from 3 per cent to 11 per cent. 5. After 72 hours in fresh wet preparations the per cent of ovalocytes remained essentially unchanged from that of fresh fixed blood. 6. The percentage of sickled cells was found to be increased after 18, 24, and 72 hours in fresh wet preparations as compared to the percentage of sickled cells found in fresh fixed preparations. 7. Some of the normal appearing discoid red blood cells were observed to sickle in fresh wet preparations within 18 hours.


2020 ◽  
Vol 8 (1) ◽  
pp. 55-64
Author(s):  
Bestoon T. Mustafa ◽  
Sardar P. Yaba ◽  
Asaad H. Ismail

This study was undertaken to investigate the influence of a homogenous and uniform static magnetic field (SMF) on the main blood cell counts in vitro experiment. Fresh blood samples were collected from albino rats and exposed to SMF (2.4, 6, 25, 50, 75, and 100 mT) versus 15–60 min. Results showed a significant change of blood counts under the low field effects. A 2.4 mT was a trend of white blood cells (WBCs) count increase non-linearly. However, a 6 mT exposure reduced WBCs with about 39%. Other variations fluctuated within 30%. The 25 mT decreased red blood cells (RBCs), hemoglobin, and hematocrit levels with 13% similarly. The lower exposure field, (2.4 and 6) mT, and effects on RBCs were 6% fluctuation. The 6 mT reduced platelet counts with half in comparison to control blood samples. About 20% increase obtained due to 50 mT exposure during all period. None of 75 and 100 mT exposures dominated blood counts alterations. The quiet magnetic field exposure for a certain time can be interesting to control blood cell count-related diseases.


1997 ◽  
Vol 272 (6) ◽  
pp. H2875-H2884 ◽  
Author(s):  
T. Wollny ◽  
L. Iacoviello ◽  
W. Buczko ◽  
G. de Gaetano ◽  
M. B. Donati

The present study was aimed at clarifying the interaction between red blood cell trauma and bleeding observed in some clinical conditions. Acute hemolysis provoked by distilled water injection was followed by a significant prolongation of the "template" bleeding time in rats. Comparable effects were observed after injection of an isotonic lysate of washed red blood cells. N omega-nitro-L-arginine methyl ester (L-NAME), an inhibitor of nitric oxide (NO) formation from L-arginine, normalized bleeding time when given to rats before hemolysis induction. The occurrence of hemolysis decreased ex vivo platelet adhesion to collagen without affecting platelet aggregation and induced a transient drop in blood pressure, the latter occurring during the first minute after injection. L-NAME pretreatment increased ex vivo platelet adhesion but did not affect either platelet aggregation or fall in blood pressure. All the effects of L-NAME were blunted by treating the animals with the NO precursor L-arginine but not D-arginine. Incubation of the erythrocyte lysate with apyrase prevented the prolongation of bleeding time induced by the hemolysate. Moreover, ADP administration, at doses that did not increase hemoglobin levels, induced effects similar to those observed after hemolysis (on template bleeding time and ex vivo platelet adhesion), which were also reversed by L-NAME and restored by L-arginine. ADP is abundantly released from (hemo)lysed red blood cells and is known to stimulate release of NO, a potent vasodilator and inhibitor of platelet adhesion. ADP-dependent NO release could be responsible for bleeding time prolongation, due to abnormalities in platelet-vessel wall interaction, during acute hemolysis. Lysis of white blood cells may also contribute to prolongation of bleeding time. Because ADP could not be detected in these cells, we postulate that other mechanisms also can be involved in bleeding time prolongation after blood cell activation in vivo.


2020 ◽  
Vol 98 (Supplement_4) ◽  
pp. 291-292
Author(s):  
Elle Rottman ◽  
Alisun N Watson ◽  
Catherine Buck ◽  
Tsungcheng Tsai ◽  
Jeffery J Chewning ◽  
...  

Abstract Complete blood cell counts have been used as a diagnostic tool across many animal species including swine. To investigate the factors that cause variation in complete blood cell count results, a total of 2,284 whole blood samples were collected from 2012 to 2019 in preweaning piglets (n = 518), nursery pigs (n = 1,704), and grower pigs (n = 60). Whole blood was collected into K2EDTA blood collection tubes and assayed using an automatic hematologic analyzer within 6 hours of collection. Data were analyzed by Mixed procedure of SAS with gender, parity group, and farrowing season as fixed effects. Body weight and age of pigs served as covariances. Farrowing season was grouped into summer (born during May to October) or winter (or November to April). Pigs that were born from first, second, and third parity, and four and above parity sows were assorted into parity group 1, 2 to 3, and 4+, respectively. Barrows had a greater concentration of total white blood cells (P < 0.01), lymphocytes (P < 0.01), and neutrophils (P < 0.01) compared to gilts. Barrows had lower mean corpuscular volume (P = 0.03), mean corpuscular hemoglobin (P < 0.01), and mean corpuscular hemoglobin concentration (P = 0.02) compared to gilts. Pigs that were farrowed in the winter season had a greater concentration of white blood cells (P = 0.01), neutrophils (P = 0.01), and the percentage of neutrophils (P = 0.03), but were lower in the percentage of lymphocytes (P = 0.03) compared to pigs farrowed during summer. Pigs born to parity four and above sows obtained a greater lymphocyte count (P = 0.01), percentage of neutrophils (P = 0.02), and percentage of lymphocytes (P = 0.01). We concluded that peripheral complete blood cells count results were affected by gender, farrowing season, and sow parity.


Sign in / Sign up

Export Citation Format

Share Document