scholarly journals An Aggregated-Based Deep Learning Method for Leukemic B-lymphoblast Classification

Diagnostics ◽  
2020 ◽  
Vol 10 (12) ◽  
pp. 1064
Author(s):  
Payam Hosseinzadeh Kasani ◽  
Sang-Won Park ◽  
Jae-Won Jang
Keyword(s):  
Bone Marrow ◽  
Deep Learning ◽  
Blood Cells ◽  
Data Augmentation ◽  
Learning Strategy ◽  
Bone Marrow Failure ◽  
Lymphoblastic Leukemia ◽  
Test Accuracy ◽  
Clinical Factor ◽  
Major Interest

Leukemia is a cancer of blood cells in the bone marrow that affects both children and adolescents. The rapid growth of unusual lymphocyte cells leads to bone marrow failure, which may slow down the production of new blood cells, and hence increases patient morbidity and mortality. Age is a crucial clinical factor in leukemia diagnosis, since if leukemia is diagnosed in the early stages, it is highly curable. Incidence is increasing globally, as around 412,000 people worldwide are likely to be diagnosed with some type of leukemia, of which acute lymphoblastic leukemia accounts for approximately 12% of all leukemia cases worldwide. Thus, the reliable and accurate detection of normal and malignant cells is of major interest. Automatic detection with computer-aided diagnosis (CAD) models can assist medics, and can be beneficial for the early detection of leukemia. In this paper, a single center study, we aimed to build an aggregated deep learning model for Leukemic B-lymphoblast classification. To make a reliable and accurate deep learner, data augmentation techniques were applied to tackle the limited dataset size, and a transfer learning strategy was employed to accelerate the learning process, and further improve the performance of the proposed network. The results show that our proposed approach was able to fuse features extracted from the best deep learning models, and outperformed individual networks with a test accuracy of 96.58% in Leukemic B-lymphoblast diagnosis.

scholarly journals Clinicopathological study of patients with pancytopenia

2020 ◽  
Vol 9 (1) ◽  
pp. 169
Author(s):  
Y. Srinivas ◽  
Mohammed Elyas
Keyword(s):  
Bone Marrow ◽  
Blood Cells ◽  
Reticulocyte Count ◽  
Megaloblastic Anemia ◽  
Bone Marrow Failure ◽  
General Medicine ◽  
Large Sample Size ◽  
Age Group ◽  
Common Causes ◽  
The Common

Background: Pancytopenia is due to bone marrow failure characterized by anemia, leukopenia, and thrombocytopenia. It a common hematological disorder. Low blood counts in the bone marrow failure disease result from deficient hematopoiesis. Marrow damage and dysfunction also may be secondary to infection, inflammation, or cancer. Pancytopenia has an extensive differential diagnosis and it can result from damage to bone marrow destruction of preformed blood cells peripherally with increased reticulocyte count. Aim of the study were to study the different etiological conditions and clinical features of pancytopenia in rural medical college.Methods: This study has been conducted in the department of general medicine in association with the pathology department and between March 2019 to February 2020, 45 patients were included in this study. males were 27 and females were 18. The age group is between 20 years and 60 years. 2 ml of anticoagulant blood send for HB% total count, platelet count, packed cell volume, and RBC indices.Results: The total no. of patients included in this study were 45 among these 45 patients, males were 27, and females were 18. The common age group is between 20 and 60 years and the common causes of aplastic anemia in our study are megaloblastic anemia.Conclusions: Pancytopenia is a common hematological problem in India. In our study megaloblastic anemia is the most common cause of pancytopenia females are affected during pregnancy. So, periodical clinically examined and investigations may reduce the incidence. of further research with a large sample size and meticulous investigations required to replicate the finding of the study.

Parvovirus B19 and Aplastic Anemia: Case Control Study: Preliminary Report from the ITESM Hematology Study Group.

Blood ◽  
2005 ◽  
Vol 106 (11) ◽  
pp. 3765-3765
Author(s):  
Jose R. Borbolla Escoboza ◽  
Marcos E. Garza-Madrid ◽  
Luis Villela ◽  
Manuel A. Lopez-Hernandez ◽  
Jorge Vela-Ojeda
Keyword(s):  
Bone Marrow ◽  
Aplastic Anemia ◽  
Peripheral Blood ◽  
Blood Cells ◽  
Parvovirus B19 ◽  
Bone Marrow Failure ◽  
Control Group ◽  
Number Of Patients ◽  
Two Samples ◽  
Sense Primer

Abstract Aplastic anemia (AA) is a classic bone marrow failure syndrome simply defined as peripheral blood pancytopenia and a hypocelular bone marrow, yet the diagnosis must be made by excluding other causes of bone marrow failure. The incidence rate of AA reported by the International Aplastic Anemia and Agranulocytosis Study (IAAAS) in the 1980s was 2 cases per 1 million people. This disease is known to be caused by exposure to radiation, chemotherapy and some viral agents, yet most of the cases are idiopathic. Epstein Barr virus and non-A, non-B or non-C Hepatitis virus have classically been related to the development of some AA cases. Recently there have been some reports of AA following Parvovirus B19 (PvB19) infection. This virus, the only parvoviridae virus capable of infecting humans, attacks erythrocyte precursors attaching to the P antigen in their surface and requiring Beta1 integrin for viral entry. Although PvB19 seems to infect only erytroid precursors, it is widely recognized that the infection with this virus can cause not only anemia, but neutropenia and thrombocytopenia as well, producing aplastic crisis of varying intensity. A correlation has recently been found between PvB19 DNA in peripheral blood and AA in children. We pretend to corroborate this observation and include adult patients in order to improve our understanding of the relationship between PvB19 and AA. So far we have taken peripheral blood samples from 9 AA patients and 9 controls paired by age, sex and community; we plan to include 100 AA patients and their controls from several hospitals around Mexico. DNA was extracted using the PUREGENE DNA extraction kit (Gentra, Minneapolis MN). Nested PCR was performed using the sense primer (P1) 5-AATACACTGTGGTTTTATGGGCCG-3, antisense (P2) 5-CCATTGCTGGTTATAACCACAGGT-3 for the first round and the sense primer (P3) 5-AATGAAAACTTTCCATTTAATGATGTAG-3 and antisense primer (P4) 5-CTAAAATGGCTTTTGCAGCTTCTAC-3for the second round. A DNA sample from a patient with active infectious mononucleosis with positive IgG and IgM against PvB19 in serum was used as positive control. Two samples from the AA group (22%) and 1 from the control group (11%) have turned positive for PvB19 DNA. The reported incidence for the presence of this virusDNA in the peripheral blood of the population is 3%. We expect that, as the number of patients grows, the percentage of positive samples in the control group will decrease, while the percentage of positive samples in the AA group will rise or be sustained. Our partial results point towards a possible relationship between AA and the presence of PvB19 DNA in the peripheral blood cells. It is possible that this virus is one of many factors capable of precipitating the development of AA by limiting the bone marrows capacity to produce blood cells. We are in the process of gathering more samples to prove if a relationship really exists and, if so, future studies will likely shed light upon the mechanism by which PvB19 contributes to the development of AA and other marrow failure syndromes.

Hematopoietic Stem Cell Differentiation Pathway in Humans Deduced From the Lineage Diversity of PNH-Type Cells in Patients with Bone Marrow Failure.

Blood ◽  
2009 ◽  
Vol 114 (22) ◽  
pp. 1489-1489
Author(s):  
Takamasa Katagiri ◽  
Zhirong Qi ◽  
Yu Kiyu ◽  
Naomi Sugimori ◽  
J. Luis Espinoza ◽  
...  
Keyword(s):  
Bone Marrow ◽  
T Cells ◽  
Stem Cell ◽  
Hematopoietic Stem Cell ◽  
Peripheral Blood ◽  
Blood Cells ◽  
Bone Marrow Failure ◽  
Stem Cell Differentiation ◽  
Refractory Anemia ◽  
Hematopoietic Stem

Abstract Abstract 1489 Poster Board I-512 The hematopoietic stem cell (HSC) differentiation pathway in humans remains largely unknown due to the lack of an appropriate in vivo assay allowing the growth of HSCs as well as of clonal markers that enable the tracing of their progenies. Small populations of blood cells deficient in glycosylphosphatidylinositol-anchored proteins (GPI-APs) such as CD55 and CD59 are detectable in approximately 50% of patients with aplastic anemia (AA) and 15% of patients with refractory anemia (RA) of myelodysplastic syndrome defined by the FAB classification. Such blood cells with the paroxysmal nocturnal hemoglobinuria (PNH) phenotype (PNH-type cells) are derived from single PIGA mutant HSCs and their fate depends on the proliferation and self-maintenance properties of the individual HSCs that undergo PIG-A mutation by chance (Blood 2008;112:2160, Br J Haematol 2009 in press) Analyses of the PNH-type cells from a large number of patients on the diversity of lineage combination may help clarify the HSC differentiation pathway in humans because PIG-A mutant HSCs in patients with bone marrow failure appear to reflect the kinetics of healthy HSCs. Therefore, different lineages of peripheral blood cells were examined including glycophorin A+ erythrocytes (E), CD11b+ granulocytes (G), CD33+ monocytes (M), CD3+ T cells (T), CD19+ B cells (B), and NKp46+ NK cells (Nk) from 527 patients with AA or RA for the presence of CD55−CD59− cells in E and G, and CD55−CD59−CD48− cells in M,T, B, Nk with high sensitivity flow cytometry. Two hundred and twenty-eight patients (43%) displayed 0.003% to 99.1% PNH-type cells in at least one lineage of cells. The lineage combination patterns of PNH-type cells in these patients included EGM in 71 patients (31%), EGMTBNk in 43 (19%), EG in 37 (16%), T alone 14 (6%), EGMBNk in 11 (5%), G alone in 10 (4%), GM in 10 (4%), EGMNk in 7 (3%), EGMT in 7 (3%), EGMB in 6 (3%), EM in 5 (2%), EGMTB in 3 (1%), EGNk in 1 (0.4%), EGMTNk in 1 (0.4%), GMTB in 1 (0.4%), and GT in 1 (0.4%) (Table). All patterns included G or M, except for 14 patients displaying PNH-type T cells alone. No patients showed TB or TBNk patterns suggestive of the presence of common lymphoid progenitor cells. Peripheral blood specimens from 123 patients of the 228 patients possessing PNH-type cells were examined again after 3 to 10 months and all patients showed the same combination patterns as those revealed by the first examination. PIG-A gene analyses using sorted PNH-type cells from 3 patients revealed the same mutation in G and Nk for 1 patient and in G and T for 2 patients. These findings indicate that human HSCs may take a similar differentiation pathway to that of murine HSCs, the ‘myeloid-based model’ that was recently proposed by Kawamoto et al. (Nature 2008; 10:452), though the cases with PNH-type T cells alone remain to be elucidated. Table. Lineages of cells containing PNH-type cells in patients with AA or RA. The number in the parenthesis denotes the proportion of patients showing each combination pattern in the total patients possessing PNH-type cells. (+ ; presence of PNH-type cells) Disclosures No relevant conflicts of interest to declare.

scholarly journals Multiple Osteolytic Lesions Causing Hypercalcemia: A Rare Presentation of Acute Lymphoblastic Leukemia

2017 ◽  
Vol 2017 ◽  
pp. 1-3 ◽  
Author(s):  
Khalid Mahmood ◽  
Muhammad Ubaid ◽  
Syeda Taliya Rizvi
Keyword(s):  
Bone Marrow ◽  
Acute Lymphoblastic Leukemia ◽  
Blood Cells ◽  
Hematological Malignancy ◽  
Lymphoblastic Leukemia ◽  
White Blood Cells ◽  
Peripheral Smear ◽  
Rare Presentation ◽  
Osteolytic Lesions ◽  
Severe Hypercalcemia

Acute lymphoblastic leukemia is characterized by unchecked proliferation of malignant lymphoblasts which replaces the normal bone marrow culminating in anemia due to red blood cells inadequacy as well as in easy bruising/bleeding secondary to insufficient platelets production. Even the white blood cells which are produced excessively are immature and abnormal. ALL is the most common hematological malignancy in children. Most commonly, patients present with lymphadenopathy, recurrent infections, bleeding, fatigue, and bone pains. Bone pains, often particularly involving long bones, occur in about 21–38% of cases and are due to overcrowding of bone marrow with malignant cells. Vast majority of children with ALL have thrombocytopenia and/or anemia with a normal or mildly elevated white blood cells count with the presence of lymphoblasts on peripheral smear. About 50% of children present with bleeding while about 75% of patients have platelet count 100,000/microL. Visceromegaly is not uncommon but osteolytic lesions and hypercalcemia are rather uncommon. We present a 22-year-old gentleman with generalized fatigue and bone pains without visceromegaly. There was severe hypercalcemia with normal parathyroid levels but multiple osteolytic lesions. Peripheral smear showed anemia without blasts, whereas a bone marrow biopsy revealed > 30% blasts with interspersed CD 10 positive cells.

scholarly journals Data Augmentation Schemes for Deep Learning in an Indoor Positioning Application

Electronics ◽  
2019 ◽  
Vol 8 (5) ◽  
pp. 554 ◽  
Author(s):  
Rashmi Sharan Sinha ◽  
Sang-Moon Lee ◽  
Minjoong Rim ◽  
Seung-Hoon Hwang
Keyword(s):  
Deep Learning ◽  
Indoor Environment ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Indoor Localization ◽  
Reference Points ◽  
Test Accuracy ◽  
Learning Approach ◽  
Location Error ◽  
User Location

In this paper, we propose two data augmentation schemes for deep learning architecture that can be used to directly estimate user location in an indoor environment using mobile phone tracking and electronic fingerprints based on reference points and access points. Using a pretrained model, the deep learning approach can significantly reduce data collection time, while the runtime is also significantly reduced. Numerical results indicate that an augmented training database containing seven days’ worth of measurements is sufficient to generate acceptable performance using a pretrained model. Experimental results find that the proposed augmentation schemes can achieve a test accuracy of 89.73% and an average location error that is as low as 2.54 m. Therefore, the proposed schemes demonstrate the feasibility of data augmentation using a deep neural network (DNN)-based indoor localization system that lowers the complexity required for use on mobile devices.

scholarly journals Efficient Pneumonia Detection in Chest Xray Images Using Deep Transfer Learning

Diagnostics ◽  
2020 ◽  
Vol 10 (6) ◽  
pp. 417 ◽  
Author(s):  
Mohammad Farukh Hashmi ◽  
Satyarth Katiyar ◽  
Avinash G Keskar ◽  
Neeraj Dhanraj Bokde ◽  
Zong Woo Geem
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Data Augmentation ◽  
Medical Center ◽  
Training Dataset ◽  
Test Accuracy ◽  
X Rays ◽  
Learning Models ◽  
Novel Approach ◽  
Unseen Data

Pneumonia causes the death of around 700,000 children every year and affects 7% of the global population. Chest X-rays are primarily used for the diagnosis of this disease. However, even for a trained radiologist, it is a challenging task to examine chest X-rays. There is a need to improve the diagnosis accuracy. In this work, an efficient model for the detection of pneumonia trained on digital chest X-ray images is proposed, which could aid the radiologists in their decision making process. A novel approach based on a weighted classifier is introduced, which combines the weighted predictions from the state-of-the-art deep learning models such as ResNet18, Xception, InceptionV3, DenseNet121, and MobileNetV3 in an optimal way. This approach is a supervised learning approach in which the network predicts the result based on the quality of the dataset used. Transfer learning is used to fine-tune the deep learning models to obtain higher training and validation accuracy. Partial data augmentation techniques are employed to increase the training dataset in a balanced way. The proposed weighted classifier is able to outperform all the individual models. Finally, the model is evaluated, not only in terms of test accuracy, but also in the AUC score. The final proposed weighted classifier model is able to achieve a test accuracy of 98.43% and an AUC score of 99.76 on the unseen data from the Guangzhou Women and Children’s Medical Center pneumonia dataset. Hence, the proposed model can be used for a quick diagnosis of pneumonia and can aid the radiologists in the diagnosis process.

Acute Lymphoblastic Leukemia in a Patient with Monomac Syndrome/GATA2 Haploinsufficiency

Blood ◽  
2015 ◽  
Vol 126 (23) ◽  
pp. 3729-3729
Author(s):  
Ashley Koegel ◽  
Venee N. Tubman ◽  
Inga Hofmann
Keyword(s):  
Bone Marrow ◽  
Acute Lymphoblastic Leukemia ◽  
Conflicts Of Interest ◽  
Bone Marrow Failure ◽  
Lymphoblastic Leukemia ◽  
Killer Cell ◽  
Cell Transplant ◽  
Hematopoietic Stem ◽  
Monosomy 7 ◽  
Definitive Therapy

Abstract Background: Heterozygous germline mutations in GATA2 have been described in three distinct conditions: 1) familial myelodysplastic syndrome (MDS)/ acute myeloid leukemia (AML), 2) Emberger syndrome which is characterized by lymphedema, warts and predisposition to MDS/AML, 3) MonoMac syndrome which is comprised of atypical nontuberculous mycobacterial infection, monocyte, and B and natural killer cell lymphoid deficiency. It is now recognized that these conditions represent a spectrum of hematopoietic, lymphatic and immune system disorders due to GATA2 haplosinsufficiency. MDS/AML due to GATA2 mutation shows a unique histopathology with characteristic dysplasia and is often associated with monosomy 7. Although many patients with GATA2 haploinsufficiency are initially asymptomatic the majority of patients will ultimately experience a significant complication such as severe infections due to immunodeficiency, pulmonary alveolar proteinosis (PAP), thrombotic events, bone marrow failure, MDS and progression to AML. Allogenic hematopoietic stem cell transplant (HSCT) is the only curative treatment for patients with GATA2 haploinsufficiency and those who develop MDS/AML. Here we report a unique patient who presented with with acute lymphoblastic leukemia (ALL) and was later found to have classical features of MonoMAC syndrome and GATA2 haploinsufficiency. Case Summary: A previously healthy 11 year-old girl presented with fever, cellulitis, and pancytopenia. Bone marrow biopsy and aspirate were diagnostic for B-precursor acute lymphoblastic leukemia (ALL) with associated monosomy 7 and the following karyotype: 45,XX,-7,del(9)(p13),del(10)(q24). She was treated on Dana Farber Cancer Institute (DFCI) Consortium ALL Protocol 05-001, achieving a morphological and cytogenetic remission. During induction, she developed necrotizing aspergillus pneumonia and molluscum contagiousum. Her planned course of therapy was abbreviated due to the development of restrictive lung disease associated with PAP and disseminated Mycobacterium kansasii infection. Serial off therapy bone marrow studies were obtained given poor count recovery and revealed significant morphologic dysplasia, most prominent in the megakaryocytes. These findings were reminiscent of those characteristically seen in patients with GATA2 haploinsufficiency. Her infectious complications, profound monocytopenia, PAP and bone marrow dysplasia raised concern for MonoMAC Syndrome. Sanger Sequencing of GATA2 revealed a point mutation in the regulatory enhancer region of intron 5 (c.1017+572C>T) confirming the diagnosis. More than 3 years following remission of ALL, she developed a bone marrow relapse with her initial clone. Given her diagnosis of GATA2 haploinsufficiency, HSCT was selected as consolidation therapy in second remission. She succumbed to complications of HSCT 4 months after transplantation. Conclusion: Patients with GATA2 haploinsufficiency show a heterogeneous clinical presentation and are at high risk for MDS/AML often associated with monosomy 7. The development of ALL in association with GATA2 haploinsufficiency has not been described in the literature. Hematologist and oncologists should be aware that ALL may be associated with GATA2 haploinsufficiency and should be attuned to the clinical, laboratory and histopathologic features of the MonoMAC syndrome that would prompt additional testing and potentially alter treatment regimens. As allogenic HSCT is the only definitive therapy for patients with GATA2 mutation, consideration of immediate HSCT following induction of remission should be considered in patients with ALL and GATA2 haploinsufficiency. Further, as patients with GATA2 mutations can be asymptomatic, it is imperative to screen family members for GATA2 mutations and offer genetic counselling prior to consideration as potential bone marrow donors. Disclosures No relevant conflicts of interest to declare.

scholarly journals Origin and fate of blood cells deficient in glycosylphosphatidylinositol-anchored protein among patients with bone marrow failure

2009 ◽  
Vol 147 (1) ◽  
pp. 102-112 ◽  
Author(s):  
Chiharu Sugimori ◽  
Kanako Mochizuki ◽  
Zhirong Qi ◽  
Naomi Sugimori ◽  
Ken Ishiyama ◽  
...  
Keyword(s):  
Bone Marrow ◽  
Blood Cells ◽  
Bone Marrow Failure

scholarly journals Improved RSSI-Based Data Augmentation Technique for Fingerprint Indoor Localisation

Electronics ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 851 ◽  
Author(s):  
Rashmi Sharan Sinha ◽  
Seung-Hoon Hwang
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Indoor Localization ◽  
Laboratory Simulation ◽  
Test Accuracy ◽  
Learning Approaches ◽  
Positioning Systems ◽  
Positioning Algorithm ◽  
Received Signal Strength Indication ◽  
Indoor Localisation

Recently, deep-learning-based indoor localisation systems have attracted attention owing to their higher performance compared with traditional indoor localization systems. However, to achieve satisfactory performance, the former systems require large amounts of data to train deep learning models. Since obtaining the data is usually a tedious task, this requirement deters the use of deep learning approaches. To address this problem, we propose an improved data augmentation technique based on received signal strength indication (RSSI) values for fingerprint indoor positioning systems. The technique is implemented using available RSSI values at one reference point, and unlike existing techniques, it mimics the constantly varying RSSI signals. With this technique, the proposed method achieves a test accuracy of 95.26% in the laboratory simulation and 94.59% in a real-time environment, and the average location error is as low as 1.45 and 1.60 m, respectively. The method exhibits higher performance compared with an existing augmentation method. In particular, the data augmentation technique can be applied irrespective of the positioning algorithm used.

Sign in / Sign up

Export Citation Format

Share Document