• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.223-229
• /
• 2021

Classification of different blood cell types is an essential task for human's medical treatment. The white blood cells have different types of cells. Counting total White Blood Cells (WBC) and differential of the WBC types are required by the physicians to diagnose the disease correctly. This paper used transfer learning methods to the pre-trained deep learning models to classify different WBCs. The best pre-trained model was Inception ResNetV2 with Adam optimizer that produced classification accuracy of 98.4% for the dataset comprising four types of WBCs.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2707-2715
• /
• 1999

Recently, there have been researches to automate processing and analysing images in the medical field using image processing technique, a fast communication network, and high performance hardware. In this paper, we propose a system to be able to analyze morphological abnormality of red-blood cells for peripheral blood image using image processing techniques. To do this, we segment red-blood cells in the blood image acquired from microscope with CCD camera and then extract UNL fourier features to classify them into 15 classes. We reduce the number of multi-variate features using PCA to construct a more efficient classifier. Our system has the best performance in recognition rate, compared with two other algorithms, LVQ3 and k-NN. So, we show that it can be applied to a pathological guided system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1889-1891
• /
• 2004

The differential white blood cell count plays an important role in the diagnosis of different diseases. It is a tedious task to count these classes of cell manually. An automatic counter using computer vision helps to perform this medical test rapidly and accurately. Most commercial-available automatic white blood cell analysis composed mainly 3 steps including segmentation, feature extraction and classification. In this paper we concentrate on the first step in automatic white-blood-cell analysis by proposing a segmentation scheme that utilizes a benefit of active contour. Specifically, the binary image is obtained by thresolding of the input blood smear image. The initial shape of active is then placed roughly inside the white blood cell and allowed to grow to fit the shape of individual white blood cell. The white blood cell is then separated using the extracted contour. The force that drives the active contour is the combination of gradient vector flow force and balloon force. Our purposed technique can handle very promising to separate the remaining red blood cells.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.3
• /
• pp.1049-1052
• /
• 2016

Background: Myelodysplastic syndrome (MDS) is a clonal disorder of hemopoeitic stem cells, characterized by infective hematopoiesis, peripheral cytopenias along with hypercellularity of marrow and marked dysplastic features. Our aim was to study the spectrum of the WHO classification in adult Pakistani patients with MDS at disease presentation. Materials and Methods: This retrospective descriptive study was conducted at Liaquat National Hospital and Medical College, extending from January 2010 to December 2014. Patient data were retrieved from the maintained archives. Results: Overall, 45 patients were diagnosed at our institution with de novo MDS during the study period. There were 28 males and 17 females. Age ranged between 18 and 95 years with a mean of $57.6{\pm}17.4years$. The male to female ratio was 1.7:1. According to the WHO classification, 53.3% had refractory cytopenia with multilineage dysplasia, 22.2% had refractory cytopenia with unilineage dysplasia, 4.4% each had refractory anemia with excess of blasts-1 and II and 15.5% had MDS unclassified. The main presenting complaints were generalized fatigue (60%), fever (33.3%), dyspnea (15.5%), bleeding (13.3%) and weight loss (11.1%). Physical examination revealed pallor in 37.7%, followed by petechial and purpuric rashes in 20% of patients. Hemoglobin was <10 g/dl in 41 (91.1%). Pancytopenia and bicytopenia were noted in 18 (40%) and 14 (31.1%) respectively. Conclusions: MDS in our patients presents at a relatively young age. Refractory c ytopenia with multilineage dysplasia was the dominant disease variant in our setting.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.12
• /
• pp.90-97
• /
• 1999

Recently, there have been many researches to automate processing and analysing image data in medical field, due to the advance of image processing techniques, the fast communication network and high performance hardware. In this paper, we design and implement the system based on the multi-layer neural network model to be able to analyze, differentiate and count blood cells in the peripheral blood image. To do these, we segment red and white-blood cell in blood image acquired from microscope with CCD(Charge-coupled device) camera and then apply the various feature extraction algorithms to classify. In addition to, we reduce multi-variate feature number using PCA(Principle Component Analysis) to construct more efficient classifier. So, in this paper, we are sure that the proposed system can be applied to a pathological guided system.

• Journal of fish pathology
• /
• v.8 no.1
• /
• pp.47-55
• /
• 1995

Classification of peripheral leucocytes in Korean catfish (Silurus asotus) were performed. The leucocytes were classified on the basis of their morphological, cytochemieal and phagocytic characteristics. Four types of leucocytes were observed in the peripheral blood. Neutrophils were round and 12 - $15{\mu}m$ in diameter with round, oval or 2 - 3 segmented neuclei. Their cytoplam was stained whitish or grey. Lymphocytes were round and 5.5 - $8{\mu}m$ in diameter with large round neuclei which occupied most of the cells. Monocytes were round or irregular cells and 12 - $15{\mu}m$ in diameter with bean - shaped or irreular neuclei. Thrombocytes were oval or spindle - shaped cells with oval or spindle - neucle. The cells with greyish cytoplasm ranged 7.2 to $14.4{\mu}m$ in length and 5.8 to $7.2{\mu}m$ in width. Only neutrophils showed positive reaction in peroxidase and PAS. Neutrophils and monocytes showed active phagocytosis. As the results it is concluded that peripheral leucocytes of Koran catfish could be classified as lymphocytes, neutrophils, monocytes and thrombocytes.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.5
• /
• pp.637-644
• /
• 2006

Biomedical image is often complex. An applied image analysis system should deal with the images which are of quite low quality and are challenging to segment. This paper presents a framework for color cell image segmentation by learning and classification online. It is a robust two-stage scheme using kernel method and watershed transform. In first stage, a two-class SVM is employed to discriminate the pixels of object from background; where the SVM is trained on the data which has been analyzed using the mean shift procedure. A real-time training strategy is also developed for SVM. In second stage, as the post-processing, local watershed transform is used to separate clustering cells. Comparison with the SSF (Scale space filter) and classical watershed-based algorithm (those are often employed for cell image segmentation) is given. Experimental results demonstrate that the new method is more accurate and robust than compared methods.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.12
• /
• pp.6527-6531
• /
• 2012

Purpose: Complement receptor 1 (CR1) is induced by Epstein-Barr virus (EBV) and may be a potential biomarker of nasopharyngeal carcinoma (NPC). We conducted the present study to evaluate the association of CR1 expression with clinicopathological features and prognosis of NPC. Methods: We enrolled 145 NPC patients and 110 controls. Expression levels of CR1 in peripheral blood mononuclear cells (PBMCs) were detected using quantitative real-time PCR and associations with clinicopathological features and prognosis were examined. Results: CR1 levels in the NPC group [3.54 (3.34, 3.79)] were slightly higher than those in the controls [3.33 (3.20, 3.47)] (P<0.001). Increased CR1 expression was associated with histology classification (type III vs. type II, P=0.002), advanced clinical stage (P=0.003), high T stage (P=0.017), and poor overall survival (HR, 4.89; 95% CI, 1.23-19.42; P=0.024). However, there were no statistically significant differences in CR1 expression among N or M stages. Conclusion: These findings indicate that CR1 expression in PBMCs may be a new biomarker for prognosis of NPC and a potential therapeutic target.

• Journal of Chest Surgery
• /
• v.31 no.10
• /
• pp.973-981
• /
• 1998

Background: About 30% to 40% of the patients with pathologic stage I non-small cell lung cancer (NSCLC) die within 5 years after complete resection. The identification of poor prognostic factors and the application of additional treatment are very important to improve the survival rate in resected stage I NSCLC. Materials and methods: Sixty-eight(68) patients who had been diagnosed postoperatively between Janury 1989 and December 1995 as having stage I non-small cell lung cancer according to the TNM classification were studied. The postoperative 5-year survival rate was calculated with the Kaplan-Meier method, and clinico- histopathologic factors including age, sex, operative method, type of tumor cell, T factor, grade of the differentiation in a squamous cell carcinoma, invasion of blood vessel and expression of the nm23-H1 protein were investigated and analyzed. Results: The median survival of the entire group of patients was 58$\pm$3 months, with a 5-year survival of 58.9%. In univariate analysis, invasion of blood vessel and poor differentiation of the tumor cell in a squamous cell carcinoma significantly worsened the survival. In multivariate analysis, invasion of blood vessel and grade of the differentiation of the tumor cells in a squamous cell carcinoma remained independent prognostic factors. High expression of the nm23-H1 protein was related to a high postoperative 5-year survival in comparision with low expression of the nm23-H1 pretein (73.0% vs 50.7%), but there was no statistical significance. Conclusions: These results highlight the negative prognostic value of poor differentiation of tumor cells in a squamous cell carcinoma and invasion of blood vessel in stage I non-small cell lung cancer. Also, further studies are necessary to be determined prognostic value of the T factor and expression of the nm23 protein in non-small cell lung cancer.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.22 no.6
• /
• pp.1579-1584
• /
• 2008

Anemia are often detected among many patients who are treated in oriental traditional medicine hospitals in Korea through blood tests which are taken to diagnose the patients' general state, and most of them are diagnosed to have iron deficiency anemia. This study amis the effect of herbal medicine on the RBC count, hemoglobin, hematocrits and indices of red blood cells such as mean corpuscular volume(MCV), mean corpuscular hemoglobin(MCH), mean corpuscular hemoglobin concentration(MCHC), serum iron, and total iron binding capacity(TIBC) among patients who were treated in oriental medical hospital and diagnosed to have anemia through blood tests other than main symptoms. The subjects of this study were 29 patients(male 7, female 22, mean age: 56.24${\pm}$19.11years) who were chosen ones, they has below hemoglobin 12 gm/dL, serum iron 70 IU/L, MCV 80 fL on laboratory screening test when they first visits our hospital. As a result, the volume of red blood cell(RBC), hematocrit(HCT), and hemoglobin(Hb) in peripheral blood increased from $348.27{\pm}8.95{\times}10^5$ /UL, 28.82${\pm}$0.56%, 9.24${\pm}$0.22 g/dL to $375.62{\pm}9.11{\times}10^5$ /UL, 31.36${\pm}$0.68%, 10.31${\pm}$0.25 g/dL comparing before and after oriental medicine treatment. After the treatment, MCH, MCHC, and MCV also increased from 26.98${\pm}$0.84 Pg, 32.62${\pm}$0.45 g/dl, 79.26${\pm}$0.17 fL to 27.74${\pm}$0.74 Pg, 32.84${\pm}$0.33 g/dl, 84.15${\pm}$1.67 fL. There was statistically significant increase in MCH, MCV(P<0.05); however, there was no significant change in MCHC(P>0.05). The amount of iron in blood increased from 32.96${\pm}$4.20 ug/dL to 67.22${\pm}$7.18 ug/dL, which showed a statistically significant increase(P<0.05). On the other hand, TIBC decreased from 325.08${\pm}$13.97 ug/dL to 315.61${\pm}$18.79 ug/dL, which was not a statistically significant change(P>0.05). Like this, all the patients showed favorable results in anemia based on the measurements of indices of red blood cells except MCHC. According to the classification of herbal medicines, in strengthening energy group(補氣), replenishing blood group(補血), and replenishing both energy and blood group(補氣血), the volume of RBC, HCT, and hemoglobin showed significant increases. Furthermore, in herbal medicines strengthening blood(補血) and replenishing both energy and blood group(補氣血), serum iron also relatively increased compare to strengthening energy group(補氣).