scholarly journals Automated Detection Model in Classification of B-Lymphoblast Cells from Normal B-Lymphoid Precursors in Blood Smear Microscopic Images Based on the Majority Voting Technique

2022 ◽  
Vol 2022 ◽  
pp. 1-8
Author(s):  
Mustafa Ghaderzadeh ◽  
Azamossadat Hosseini ◽  
Farkhondeh Asadi ◽  
Hassan Abolghasemi ◽  
Davood Bashash ◽  
...  
Keyword(s):  
Blood Smear ◽  
Lymphoblastic Leukemia ◽  
Poor Performance ◽  
Peripheral Blood Smear ◽  
Ensemble Classifier ◽  
Majority Voting ◽  
Laboratory Equipment ◽  
Normal Cells ◽  
Model Based

Introduction. Acute lymphoblastic leukemia (ALL) is the most common type of leukemia, a deadly white blood cell disease that impacts the human bone marrow. ALL detection in its early stages has always been riddled with complexity and difficulty. Peripheral blood smear (PBS) examination, a common method applied at the outset of ALL diagnosis, is a time-consuming and tedious process that largely depends on the specialist’s experience. Materials and Methods. Herein, a fast, efficient, and comprehensive model based on deep learning (DL) was proposed by implementing eight well-known convolutional neural network (CNN) models for feature extraction on all images and classification of B-ALL lymphoblast and normal cells. After evaluating their performance, four best-performing CNN models were selected to compose an ensemble classifier by combining each classifier’s pretrained model capabilities. Results. Due to the close similarity of the nuclei of cancerous and normal cells, CNN models alone had low sensitivity and poor performance in diagnosing these two classes. The proposed model based on the majority voting technique was adopted to combine the CNN models. The resulting model achieved a sensitivity of 99.4, specificity of 96.7, AUC of 98.3, and accuracy of 98.5. Conclusion. In classifying cancerous blood cells from normal cells, the proposed method can achieve high accuracy without the operator’s intervention in cell feature determination. It can thus be recommended as an extraordinary tool for the analysis of blood samples in digital laboratory equipment to assist laboratory specialists.

scholarly journals Automated Detection Model in Classification B-Lymphoblast Cell from Normal B-Lymphoid Precursors in Blood Smear Microscopic Images Based on the Majority Voting Technique

2021 ◽  
Author(s):  
Mustafa Ghaderzadeh ◽  
Azamossadat Hosseini ◽  
Farkhondeh Asadi ◽  
Hassan Abolghasemi ◽  
Arash Roshanpour
Keyword(s):  
Artificial Intelligence ◽  
Lymphoblastic Leukemia ◽  
Model Performance ◽  
Ensemble Classifier ◽  
Majority Voting ◽  
Classification Model ◽  
Laboratory Equipment ◽  
Detection Model ◽  
Model Based ◽  
B Lymphoid

Introduction: Acute Lymphoblastic Leukemia (ALL) is a deadly white blood cell disease that affects the human bone marrow. Detection of ALL, the most common type of leukemia, has been always riddled with complexity and difficulty in its early stages. Peripheral blood examination as a common method at the beginning of the ALL diagnosis process is a time-consuming, tedious process and greatly depends on the experts' experience, keeping up with the advances in artificial intelligence in the diagnosis process. Keeping up with the growth and development of artificial intelligence algorithms a model was developed to classify B-ALL lymphoblast cells from lymphocytes. Materials and Methods: A Fast, efficient and comprehensive model based on Deep Learning (DL) was proposed by implementing eight well-known Convolutional Neural Network (CNN) models for feature extraction on all images and evaluating in classifying B-ALL lymphoblast and Normal. After evaluating their performance, four best-performing CNN models were selected to compose an ensemble classifier, by combining the model performance of each classifier. Results: Due to the close similarity of the nuclei of cancerous and normal blood B-ALL cells, the state-of-the-art CNN models alone did not achieve acceptable performance in diagnosing these two classes and their sensitivity was low. The proposed classification model Based on the majority voting technique was adopted to combine the CNN models. The sensitivity of 99.4, the specificity of 96.7, AUC of 98.3, and accuracy of 98.5 were obtained for the proposed model. Conclusion: To classify blood cancerous cells from normal cells, the proposed method can achieve high accuracy without the intervention of the operator in cell feature determination. Thus, the DL-based model can be recommended as an extraordinary tool for the analysis of blood samples in digital laboratory equipment to assist laboratory specialists.

A CLINICOPATHOLOGICAL STUDY OF ACUTE AND CHRONIC LEUKEMIA IN A TERTIARY CARE HOSPITAL

2021 ◽  
pp. 72-74
Author(s):  
Sarat Das ◽  
Prasanta Kr. Baruah ◽  
Sandeep Khakhlari ◽  
Gautam Boro
Keyword(s):  
Acute Myeloid Leukemia ◽  
Acute Lymphoblastic Leukemia ◽  
Peripheral Blood ◽  
Myeloid Leukemia ◽  
Blood Smear ◽  
Lymphoblastic Leukemia ◽  
Peripheral Blood Smear ◽  
Care Hospital ◽  
Cytochemical Study ◽  
Acute Myeloid

Introduction: Leukemias are neoplastic proliferations of haematopoietic stem cells and form a major proportion of haematopoietic neoplasms that are diagnosed worldwide. Typing of leukemia is essential for effective therapy because prognosis and survival rate are different for each type and sub-type Aims: this study was carried out to determine the frequency of acute and chronic leukemias and to evaluate their clinicopathological features. Methods: It was a hospital based cross sectional study of 60 patients carried out in the department of Pathology, JMCH, Assam over a period of one year between February 2018 and January 2019. Diagnosis was based on peripheral blood count, peripheral blood smear and bone marrow examination (as on when available marrow sample) for morphology along with cytochemical study whenever possible. Results: In the present study, commonest leukemia was Acute myeloid leukemia (AML, 50%) followed by Acute lymphoblastic leukemia (ALL 26.6%), chronic myeloid leukemia (CML, 16.7%) and chronic lymphocytic leukemia (CLL, 6.7%). Out of total 60 cases, 36 were male and 24 were female with Male:Female ratio of 1.5:1. Acute lymphoblastic leukemia was the most common type of leukemia in the children and adolescents. Acute Myeloid leukemia was more prevalent in adults. Peripheral blood smear and bone Conclusion: marrow aspiration study still remains the important tool along with cytochemistry, immunophenotyping and cytogenetic study in the diagnosis and management of leukemia.

scholarly journals Acute Lymphoblastic Leukemia Presenting as Fanconi Syndrome

2018 ◽  
Vol 11 (1) ◽  
pp. 63-67
Author(s):  
Tatsunori Yoshida ◽  
Hiroshi Tsujimoto ◽  
Takayuki Ichikawa ◽  
Shinji Kounami ◽  
Hiroyuki Suzuki
Keyword(s):  
Acute Lymphoblastic Leukemia ◽  
Renal Tubular Acidosis ◽  
Fanconi Syndrome ◽  
Blood Smear ◽  
Lymphoblastic Leukemia ◽  
Peripheral Blood Smear ◽  
Leukemic Cells ◽  
Laboratory Examinations ◽  
Renal Tubular ◽  
Electrolyte Abnormalities

Acute lymphoblastic leukemia (ALL) presenting as Fanconi syndrome (FS) is extremely rare. Here, we report a case of ALL presenting as bilateral nephromegaly following FS. A 2-year-old girl was unexpectedly diagnosed with bilateral nephromegaly. After 2 weeks, she developed general fatigue, thirst, and polyuria. Laboratory examinations revealed renal tubular acidosis, hypokalemia, hypophosphatemia, and aminoaciduria, and FS was diagnosed. Replacement of bicarbonate and potassium did not improve her condition. Two weeks after the onset of FS, leukemic cells appeared on a peripheral blood smear, and the patient was diagnosed with precursor B-cell ALL presenting as nephromegaly and FS. Chemotherapy brought about a prompt resolution of acidosis and electrolyte abnormalities, without renal dysfunction. The patient remains well 4 years after the onset of the disease. Although extremely rare, FS should be recognized as one of the emerging renal complications of ALL.

scholarly journals ACQUIRED β−THALASSEMIA IN CHILDREN WITH ACUTE LYMPHOBLASTIC LEUKEMIA (ALL)

2016 ◽  
Vol 20 (1) ◽  
pp. 58
Author(s):  
Maria Christina Shanty Larasati ◽  
Mangihut Rumiris ◽  
Mia Ratwita Andarsini ◽  
I Dewa Gede Ugrasena ◽  
Bambang Permono
Keyword(s):  
Peripheral Blood ◽  
Blood Smear ◽  
Lymphoblastic Leukemia ◽  
Genetic Disorders ◽  
Globin Gene ◽  
Maintenance Phase ◽  
Peripheral Blood Smear ◽  
Altered Expression ◽  
First Case ◽  
Thalassemia Trait

Thalassemias are heterogeneous group of genetic disorders. β-thalassemia is existed due to impaired production of beta globins chains, which leads to a relative excess of alpha globin chains. The abnormalities of haemoglobin synthesis are usually inherited but may also arise as a secondary manifestation of another disease, most commonly haematological neoplasia. This article presenting two cases of acquired β-thalassemia in children with ALL focusing on the diagnosis and the possible relationship between the two haematological diseases. The first case is a four (4) year old boy with ALL-L1 type at maintenance phase of chemotherapy, he suffered from anaemia with Hb 8.0 g/dL, WBC 22,600/mm3 and platelets count of 200,000/mm3, peripheral blood smear revealed anisocytosis, polychromes, hypochromia, basophilic stippling, and normoblastocytes. The result of Hb electrophoresis of Hb A of 54.9%, Hb F of 29.4%, Hb E of 13.4% and Hb A2 of 2.3%. The patient was diagnosed as ALL-L1 type and β-thalassemia. The second case, is a 13 year old girl with remission ALL-L1 type after chemotherapy, she suffered from anaemia with Hb 6.7 g/dL, WBC 12,400/mm3, platelet count was 200,000/mm3, and peripheral blood smear obtained anisocytosis, hypochromia, normoblastocytes, myelocytes and basophilic stippling. The result of Hb electrophoresis are: Hb F 0.41%, Hb A1c 0.78%, Hb A2 2.95% with the conclusion of a β-thalassemia trait, this patient was diagnosed with ALL-L1 type remission + β-thalassemia trait. The case reviewers assume that acquired β-thalassemia which happened in those patients were the altered expression of globin chain which mechanism for this syndrome might be the acquisition of a mutation that affects RNA or proteins involved in β-globin gene regulation and resulting the reduction of the (α/β)-globin biosynthetic ratios, or/and associated with chemotherapy-inducement.

Clinical Characteristics of Patients with a RBC Fragment Flag on the Advia® 2120 Automated Hematology Analyzer.

Blood ◽  
2007 ◽  
Vol 110 (11) ◽  
pp. 5153-5153
Author(s):  
Jonathan Ben-Ezra
Keyword(s):  
Iron Deficiency ◽  
Iron Deficiency Anemia ◽  
Peripheral Blood ◽  
Blood Smear ◽  
Lymphoblastic Leukemia ◽  
Peripheral Blood Smear ◽  
Deficiency Anemia ◽  
Clinical Criteria ◽  
Hematology Analyzer ◽  
Automated Hematology Analyzer

The clinical diagnosis of thrombotic thrombocytopenia purpura (TTP) is a difficult one to make. It is based on clinical criteria, one of which is a microangiopathic hemolytic anemia, characterized morphologically by the presence of schistocytes on the peripheral blood smear. The ADVIA 2120 automated hematology analyzer is able to quantify the presence of red blood cell (RBC) fragments. We studied the ability of the ADVIA 2120 to be able to detect RBC fragments in the blood of TTP patients, and the characteristics of all patients in whom RBC fragments were obtained. During the study period, 6 TTP patients were studied. The initial numbers of RBC fragments ranged from 0.02–0.05 × 106 cells/μl. During the course of plasmapheresis, these numbers decreased to 0.00–0.02 × 106 cells/μl, corresponding to a rise in the platelet count. Figure Figure In the course of a month, 52 blood samples on 39 patients were flagged by the hematology analyzer to have RBC fragments (0.01–0.12 × 106 cells/μl). 52 Samples with RBC Fragment Flag Hemoglobin Platelets RDW Range 4– 14.3 g/dl 5–906 × 103/ul 13.9– 28.6% Number Abnormal 46 (<13.0 g/dl) 23 (<160 × 103/ul) 51 (>14.1%) Within this population, there were two patients with TTP, and one with DIC. Four of the samples did not have detectable schistocytes upon visual inspection of the peripheral blood smear. There were 19 samples from 14 patients who had RBC fragment counts ≥ 0.04 × 106 cells/μl. 19 Specimens with RBC Fragments ≥ 0.04 × 106/ul Hemoglobin Platelets RDW Range 8– 14.1 g/dl 59– 906 × 103/ul 16.4– 25.3% Number Abnormal 15 (<13 g/dl) 4 (<160 × 103/ul) 19 (>14.1%) The diagnoses in these 14 patients were iron deficiency anemia (4 patients), thalassemia trait (2), acute lymphoblastic leukemia (2), and one each with TTP, sickle cell anemia, heart failure, kidney stone, cerebrovascular accident (CVA), and end stage renal disease. We conclude that the RBC fragment flag on the ADVIA 2120 is nonspecific. Although it does detect schistocytes in TTP, these are often present in low numbers. Quantitatively, the most numerous RBC fragments are found in diseases with marked anisopoikilocytosis, such as iron deficiency anemia.

Sign in / Sign up

Export Citation Format

Share Document