-
Biomedical Engineering Online Jun 2015Blood smear microscopic images are routinely investigated by haematologists to diagnose most blood diseases. However, the task is quite tedious and time consuming. An... (Comparative Study)
Comparative Study
BACKGROUND
Blood smear microscopic images are routinely investigated by haematologists to diagnose most blood diseases. However, the task is quite tedious and time consuming. An automatic detection and classification of white blood cells within such images can accelerate the process tremendously. In this paper we propose a system to locate white blood cells within microscopic blood smear images, segment them into nucleus and cytoplasm regions, extract suitable features and finally, classify them into five types: basophil, eosinophil, neutrophil, lymphocyte and monocyte.
DATASET
Two sets of blood smear images were used in this study's experiments. Dataset 1, collected from Rangsit University, were normal peripheral blood slides under light microscope with 100× magnification; 555 images with 601 white blood cells were captured by a Nikon DS-Fi2 high-definition color camera and saved in JPG format of size 960 × 1,280 pixels at 15 pixels per 1 μm resolution. In dataset 2, 477 cropped white blood cell images were downloaded from CellaVision.com. They are in JPG format of size 360 × 363 pixels. The resolution is estimated to be 10 pixels per 1 μm.
METHODS
The proposed system comprises a pre-processing step, nucleus segmentation, cell segmentation, feature extraction, feature selection and classification. The main concept of the segmentation algorithm employed uses white blood cell's morphological properties and the calibrated size of a real cell relative to image resolution. The segmentation process combined thresholding, morphological operation and ellipse curve fitting. Consequently, several features were extracted from the segmented nucleus and cytoplasm regions. Prominent features were then chosen by a greedy search algorithm called sequential forward selection. Finally, with a set of selected prominent features, both linear and naïve Bayes classifiers were applied for performance comparison. This system was tested on normal peripheral blood smear slide images from two datasets.
RESULTS
Two sets of comparison were performed: segmentation and classification. The automatically segmented results were compared to the ones obtained manually by a haematologist. It was found that the proposed method is consistent and coherent in both datasets, with dice similarity of 98.9 and 91.6% for average segmented nucleus and cell regions, respectively. Furthermore, the overall correction rate in the classification phase is about 98 and 94% for linear and naïve Bayes models, respectively.
CONCLUSIONS
The proposed system, based on normal white blood cell morphology and its characteristics, was applied to two different datasets. The results of the calibrated segmentation process on both datasets are fast, robust, efficient and coherent. Meanwhile, the classification of normal white blood cells into five types shows high sensitivity in both linear and naïve Bayes models, with slightly better results in the linear classifier.
Topics: Algorithms; Bayes Theorem; Humans; Image Processing, Computer-Assisted; Leukocytes; Linear Models; Microscopy
PubMed: 26123131
DOI: 10.1186/s12938-015-0037-1 -
Malaria Journal Aug 2011Congenital malaria has been considered a rare event; however, recent reports have shown frequencies ranging from 3% to 54.2% among newborns of mothers who had suffered...
BACKGROUND
Congenital malaria has been considered a rare event; however, recent reports have shown frequencies ranging from 3% to 54.2% among newborns of mothers who had suffered malaria during pregnancy. There are only a few references concerning the epidemiological impact of this entity in Latin-America and Colombia.
OBJECTIVE
The aim of the study was to measure the prevalence of congenital malaria in an endemic Colombian region and to determine some of its characteristics.
METHODS
A prospective, descriptive study was carried out in the mothers who suffered malaria during pregnancy and their newborns. Neonates were clinically evaluated at birth and screened for Plasmodium spp. infection by thick smear from the umbilical cord and peripheral blood, and followed-up weekly during the first 21 days of postnatal life through clinical examinations and thick smears.
RESULTS
116 newborns were included in the study and 80 umbilical cord samples were obtained. Five cases of congenital infection were identified (four caused by P. vivax and one by P. falciparum), two in umbilical cord blood and three in newborn peripheral blood. One case was diagnosed at birth and the others during follow-up. Prevalence of congenital infection was 4.3%. One of the infected newborns was severely ill, while the others were asymptomatic and apparently healthy. The mothers of the newborns with congenital malaria had been diagnosed with malaria in the last trimester of pregnancy or during delivery, and also presented placental infection.
CONCLUSIONS
Congenital malaria may be a frequent event in newborns of mothers who have suffered malaria during pregnancy in Colombia. An association was found between congenital malaria and the diagnosis of malaria in the mother during the last trimester of pregnancy or during delivery, and the presence of placental infection.
Topics: Adolescent; Adult; Blood; Colombia; Female; Humans; Infant, Newborn; Malaria, Falciparum; Malaria, Vivax; Male; Parasitemia; Plasmodium falciparum; Plasmodium vivax; Pregnancy; Prospective Studies; Young Adult
PubMed: 21846373
DOI: 10.1186/1475-2875-10-239 -
Computational and Mathematical Methods... 2021For the analysis of medical images, one of the most basic methods is to diagnose diseases by examining blood smears through a microscope to check the morphology, number,...
For the analysis of medical images, one of the most basic methods is to diagnose diseases by examining blood smears through a microscope to check the morphology, number, and ratio of red blood cells and white blood cells. Therefore, accurate segmentation of blood cell images is essential for cell counting and identification. The aim of this paper is to perform blood smear image segmentation by combining neural ordinary differential equations (NODEs) with U-Net networks to improve the accuracy of image segmentation. In order to study the effect of ODE-solve on the speed and accuracy of the network, the ODE-block module was added to the nine convolutional layers in the U-Net network. Firstly, blood cell images are preprocessed to enhance the contrast between the regions to be segmented; secondly, the same dataset was used for the training set and testing set to test segmentation results. According to the experimental results, we select the location where the ordinary differential equation block (ODE-block) module is added, select the appropriate error tolerance, and balance the calculation time and the segmentation accuracy, in order to exert the best performance; finally, the error tolerance of the ODE-block is adjusted to increase the network depth, and the training NODEs-UNet network model is used for cell image segmentation. Using our proposed network model to segment blood cell images in the testing set, it can achieve 95.3% pixel accuracy and 90.61% mean intersection over union. By comparing the U-Net and ResNet networks, the pixel accuracy of our network model is increased by 0.88% and 0.46%, respectively, and the mean intersection over union is increased by 2.18% and 1.13%, respectively. Our proposed network model improves the accuracy of blood cell image segmentation and reduces the computational cost of the network.
Topics: Algorithms; Blood Cells; Computational Biology; Deep Learning; Humans; Image Processing, Computer-Assisted; Neural Networks, Computer
PubMed: 34413897
DOI: 10.1155/2021/5590180 -
Zhongguo Dang Dai Er Ke Za Zhi =... Nov 2012Although thrombotic thrombocytopenic purpura (TTP) is rarely seen in pediatric patients, failure to recognize this condition often leads to severe consequences and poor... (Review)
Review
Although thrombotic thrombocytopenic purpura (TTP) is rarely seen in pediatric patients, failure to recognize this condition often leads to severe consequences and poor outcomes. Classic features of TTP include thrombocytopenia, microangiopathic hemolytic anemia, acute kidney injury, fever, and central nervous system involvement. However, patients suffering from this condition may not present with all of the symptoms simultaneously. Therefore, it is of utmost importance for healthcare providers to have a high index of suspicion. Laboratory investigations may reveal the presence of schistocytes on peripheral blood smear, negative Coombs test, high lactate dehydrogenase levels and severely low platelet counts. The etiology of TTP is mainly due to insufficient cleavage of the large multimers of von Willebrand factor (vWF) secondary to decreased activity of ADAMTS13 (a disintegrin and metalloprotease with Thrombospondin type 1 repeats, member 13). TTP can be broadly classified into familial TTP (Upshaw Schulman syndrome) and non-familial TTP. Familial TTP is due to a congenital deficiency of ADAMTS13. Its mainstay of therapy is initiation of plasmapheresis during the acute phase, followed by regular fresh frozen plasma (FFP) infusions. Alternatively, non-familial TTP is due to a decrease in ADAMTS13 activity secondary to the presence of anti-ADAMTS13 antibodies. Once again, the primary treatment is plasmapheresis; however, recent anecdotal data also supports the use of rituximab in select cases.
Topics: ADAM Proteins; ADAMTS13 Protein; Antibodies, Monoclonal, Murine-Derived; Child; Humans; Plasmapheresis; Purpura, Thrombotic Thrombocytopenic; Rituximab
PubMed: 23146723
DOI: No ID Found -
International Journal of Laboratory... Dec 2021Current digital cell imaging systems perform peripheral blood smear (PBS) analysis in limited regions of the PBS and require the support of manual microscopy without...
Evaluation of Scopio Labs X100 Full Field PBS: The first high-resolution full field viewing of peripheral blood specimens combined with artificial intelligence-based morphological analysis.
BACKGROUND
Current digital cell imaging systems perform peripheral blood smear (PBS) analysis in limited regions of the PBS and require the support of manual microscopy without achieving full digital microscopy. We report a multicenter study that validated the Scopio Labs X100 Full Field PBS, a novel digital imaging system that utilizes a full field view approach for cell recognition and classification, in a decision support system mode.
METHODS
We analyzed 335 normal and 310 abnormal PBS from patients with various clinical conditions and compared the performance of Scopio's Full Field PBS as the test method, with manual PBS analysis as the reference method. Deming regression analysis was utilized for comparisons of WBC and platelet estimates. Measurements of WBC and platelet estimation accuracy along with the agreement on RBC morphology evaluation were performed. Reproducibility and repeatability (R&R) of the system were also evaluated.
RESULTS
Scopio's Full Field PBS WBC accuracy was evaluated with an efficiency of 96.29%, sensitivity of 87.86%, and specificity of 97.62%. The agreement between the test and reference method for RBC morphology reached 99.77%, and the accuracy for platelet estimation resulted in an efficiency of 94.89%, sensitivity of 90.00%, and specificity of 96.28%, with successful R&R tests. The system enabled a comprehensive review of full field PBS as shown in representative samples.
CONCLUSIONS
Scopio's Full Field PBS showed a high degree of correlation of all tested parameters with manual microscopy. The novel full field view of specimens facilitates the long-expected disengagement between the digital application and the manual microscope.
Topics: Artificial Intelligence; Blood Cell Count; Blood Cells; Humans; Image Processing, Computer-Assisted; Microscopy; Reproducibility of Results
PubMed: 34546630
DOI: 10.1111/ijlh.13681 -
British Journal of Haematology Feb 2023Numerous studies have shown peculiar morphological anomalies in COVID-19 patients' smears. We searched all the peer-reviewed scientific publications that explicitly... (Review)
Review
Numerous studies have shown peculiar morphological anomalies in COVID-19 patients' smears. We searched all the peer-reviewed scientific publications that explicitly reference the cytomorphological alterations on peripheral blood smears of patients with COVID-19. We extracted data from sixty-five publications (case reports, patient group studies, reviews, and erythrocyte morphology studies). The results show that frequent alterations concern the morphology of lymphocytes (large lymphocytes with weakly basophilic cytoplasm, plasmacytoid lymphocytes, large granular lymphocytes). Neutrophils display abnormal nuclei and cytoplasm in a distinctive cytomorphological picture. Besides a left shift in maturation, granulations can be increased (toxic type) or decreased with areas of basophilia. Nuclei are often hyposegmented (pseudo-Pelger-Huёt anomaly). Apoptotic or pycnotic cells are not uncommon. Monocytes typically have a large cytoplasm loaded with heterogeneous and coalescing vacuoles. Platelets show large and giant shapes. The presence of erythrocyte fragments and schistocytes is especially evident in the forms of COVID-19 that are associated with thrombotic microangiopathies. Such atypia of blood cells reflects the generalized activation in severe COVID-19, which has been demonstrated with immunophenotypic, molecular, genetic, and functional methods. Neutrophils, in particular, are involved in the pathophysiology of hyperinflammation with cytokine storm, which characterizes the most unfavorable evolution.
Topics: Humans; COVID-19; Pelger-Huet Anomaly; Neutrophils; Monocytes; Killer Cells, Natural
PubMed: 36203344
DOI: 10.1111/bjh.18489 -
Oncology (Williston Park, N.Y.) Sep 2002The hallmark of hemolysis is shortened red blood cell survival in the peripheral blood. Hemolysis results in anemia only when bone marrow cannot keep up with the rate of... (Review)
Review
The hallmark of hemolysis is shortened red blood cell survival in the peripheral blood. Hemolysis results in anemia only when bone marrow cannot keep up with the rate of red cell destruction. Even though anemia is very commonly observed in most cancer patients, hemolytic anemias are rather rare. Acute or chronic hemolysis, when present can impact on quality of life adversely, especially when bone marrow has limited compensation capacity. The underlying etiologies and pathophysiologies of the varying types of hemolytic anemias differ vastly, and there are numerous disorders causing red blood cell destruction that result in a similar clinical presentation. Careful review of the peripheral blood smear can provide invaluable information in diagnosing the underlying disorder. The majority of the nonhemolytic anemias have a chronic and stable course. In hemolytic disorders, however, the severity of the hemolysis can also create life-threatening emergencies. Management of hemolytic anemias depend on the diagnosis. Thus clinicians often face added pressure to determine the causative disorder rapidly so that timely interventions can be planned. Thus, even though they are not very common, hemolytic anemias remain a big challenge in the practice of hematology and oncology.
Topics: Anemia, Hemolytic; Bone Marrow Examination; Erythrocytes; Erythropoiesis; Hemoglobins; Humans
PubMed: 12380967
DOI: No ID Found -
PloS One 2019Microscopic examination of peripheral blood plays an important role in the field of diagnosis and control of major diseases. Peripheral leukocyte recognition by manual...
Microscopic examination of peripheral blood plays an important role in the field of diagnosis and control of major diseases. Peripheral leukocyte recognition by manual requires medical technicians to observe blood smears through light microscopy, using their experience and expertise to discriminate and analyze different cells, which is time-consuming, labor-intensive and subjective. The traditional systems based on feature engineering often need to ensure successful segmentation and then manually extract certain quantitative and qualitative features for recognition but still remaining a limitation of poor robustness. The classification pipeline based on convolutional neural network is of automatic feature extraction and free of segmentation but hard to deal with multiple object recognition. In this paper, we take leukocyte recognition as object detection task and apply two remarkable object detection approaches, Single Shot Multibox Detector and An Incremental Improvement Version of You Only Look Once. To improve recognition performance, some key factors involving these object detection approaches are explored and the detection models are generated using the train set of 14,700 annotated images. Finally, we evaluate these detection models on test sets consisting of 1,120 annotated images and 7,868 labeled single object images corresponding to 11 categories of peripheral leukocytes, respectively. A best mean average precision of 93.10% and mean accuracy of 90.09% are achieved while the inference time is 53 ms per image on a NVIDIA GTX1080Ti GPU.
Topics: Algorithms; Bioengineering; Deep Learning; Humans; Image Processing, Computer-Assisted; Leukocytes; Microscopy; Neural Networks, Computer
PubMed: 31237896
DOI: 10.1371/journal.pone.0218808 -
Turkish Journal of Haematology :... Dec 2023
Topics: Humans; Erythrocytes; Neutrophils; Epithelial Cells
PubMed: 37723855
DOI: 10.4274/tjh.galenos.2023.2023.0268 -
Malaria Journal Nov 2017Optical detection of circulating haemozoin has been suggested as a needle free method to diagnose malaria using in vivo microscopy. Haemozoin is generated within...
BACKGROUND
Optical detection of circulating haemozoin has been suggested as a needle free method to diagnose malaria using in vivo microscopy. Haemozoin is generated within infected red blood cells by the malaria parasite, serving as a highly specific, endogenous biomarker of malaria. However, phagocytosis of haemozoin by white blood cells which persist after the infection is resolved presents the potential for false positive diagnosis; therefore, the focus of this work is to identify a feature of the haemozoin signal to discriminate between infected red blood cells and haemozoin-containing white blood cells.
METHODS
Conventional brightfield microscopy of thin film blood smears was used to analyse haemozoin absorbance signal in vitro. Cell type and parasite maturity were morphologically determined using colocalized DAPI staining. The ability of features to discriminate between infected red blood cells and haemozoin-containing white blood cells was evaluated using images of smears from subjects infected with two species of Plasmodium, Plasmodium yoelii and Plasmodium falciparum. Discriminating features identified by blood smear microscopy were characterized in vivo in P. yoelii-infected mice.
RESULTS
Two features of the haemozoin signal, haemozoin diameter and normalized intensity difference, were identified as potential parameters to differentiate infected red blood cells and haemozoin-containing white blood cells. Classification performance was evaluated using the area under the receiver operating characteristic curve, with area under the curve values of 0.89 for the diameter parameter and 0.85 for the intensity parameter when assessed in P. yoelii samples. Similar results were obtained from P. falciparum blood smears, showing an AUC of 0.93 or greater for both classification features. For in vivo investigations, the intensity-based metric was the best classifier, with an AUC of 0.91.
CONCLUSIONS
This work demonstrates that size and intensity features of haemozoin absorbance signal collected by in vivo microscopy are effective classification metrics to discriminate infected red blood cells from haemozoin-containing white blood cells. This reduces the potential for false positive results associated with optical imaging strategies for in vivo diagnosis of malaria based on the endogenous biomarker haemozoin.
Topics: Diagnostic Tests, Routine; Erythrocytes; Hemeproteins; Humans; Intravital Microscopy; Leukocytes; Malaria
PubMed: 29115957
DOI: 10.1186/s12936-017-2096-1