A Machine Learning Tool Using Digital Microscopy (Morphogo) for the Identification of Abnormal Lymphocytes in the Bone Marrow

2021 ◽  
pp. 1-4
Author(s):  
Gusheng Tang ◽  
Xinyan Fu ◽  
Zhen Wang ◽  
Mingyi Chen
Keyword(s):  
Machine Learning ◽  
Bone Marrow ◽  
Cell Lymphoma ◽  
Digital Pathology ◽  
B Cell Lymphoma ◽  
Lymphoid Cells ◽  
Learning System ◽  
Training Data ◽  
Digital Microscopy ◽  
Data Set

Morphological analysis of the bone marrow is an essential step in the diagnosis of hematological disease. The conventional analysis of bone marrow smears is performed under a manual microscope, which is labor-intensive and subject to interobserver variability. The morphological differential diagnosis of abnormal lymphocytes from normal lymphocytes is still challenging. The digital pathology methods integrated with advances in machine learning enable new diagnostic features/algorithms from digital bone marrow cell images in order to optimize classification, thus providing a robust and faster screening diagnostic tool. We have developed a machine learning system, Morphogo, based on algorithms to discriminate abnormal lymphocytes from normal lymphocytes using digital imaging analysis. We retrospectively reviewed 347 cases of bone marrow digital images. Among them, 53 cases had a clinical history and the diagnosis of marrow involvement with lymphoma was confirmed either by morphology or flow cytometry. We split the 53 cases into two groups for training and testing with 43 and 10 cases, respectively. The selected 15,353 cell images were reviewed by pathologists, based on morphological visual appearance, from 43 patients whose diagnosis was confirmed by complementary tests. To expand the range and the precision of recognizing the lymphoid cells in the marrow by automated digital microscopy systems, we developed an algorithm that incorporated color and texture in addition to geometrical cytological features of the variable lymphocyte images which were applied as the training data set. The selected images from the 10 patients were analyzed by the trained artificial intelligence-based recognition system and compared with the final diagnosis rendered by pathologists. The positive predictive value for the identification of the categories of reactive/normal lymphocytes and abnormal lymphoid cells was 99.04%. It seems likely that further training and improvement of the algorithms will facilitate further subclassification of specific lineage subset pathology, e.g., diffuse large B-cell lymphoma from chronic lymphocytic leukemia/small lymphocytic lymphoma, follicular lymphoma, mantle cell lymphoma or even hairy cell leukemia in cases of abnormal malignant lymphocyte classes in the future. This research demonstrated the feasibility of digital pathology and emerging machine learning approaches to automatically diagnose lymphoma cells in the bone marrow based on cytological-histological analyses.

Efficacy of Intrathecal Rituximab In the Management of CNS Relapse of Aggressive HIV Related Lymphoma

Blood ◽  
2010 ◽  
Vol 116 (21) ◽  
pp. 4929-4929
Author(s):  
Suthanthira Kannan Ramamoorthy ◽  
Vishnu Kumar ◽  
R Scientist
Keyword(s):  
Bone Marrow ◽  
Flow Cytometry ◽  
B Cell ◽  
Cranial Nerve ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Lymphoid Cells ◽  
Whole Body ◽  
Cns Involvement ◽  
Cranial Nerve Palsies

Abstract Abstract 4929 Intrathecal rituximab is not routinely used in the treatment of CNS involvement of Leukemia and Lymphomas. However, we had to use it in a patient who presented with aggressive relapse of HIV related lymphoma. He had multiple adverse prognostic factors such as HIV related lymphoma, relapse within few months of primary treatment, old age, extensive CNS disease (multiple cranial nerve involvement) with bone marrow involvement. This patient Mr X was admitted with complaints of swelling in the left side of face slowly growing on 4 months duration. He had no h/o of fever or weight loss. No deviation of angle of mouth or drooling of saliva. He has been a known diabetic on oral antihypoglycemic drugs for the past 10 years. He was found to have HIV positivity 5 years back and had been on anti retroviral therapy since then. On examination the swelling was 7×4cm in size in the left parotid extending 3 cm in front of ear to 5cm below the angle of mandible, well defined with surface appearing smooth. Biopsy confirmed it as Diffuse Large B cell lymphoma. Immunohistochemistry showed the cells to be positive for CD 20, CD79a, LCA with lamda restriction and negative for CD 3 and CD10. Ki 67 was positive in 20% of cells only. LDH was 461 U/L (230-460). Other biochemical parameters and blood counts were normal. Bone marrow was not involved. He has been staged as Stage IE with IPI score of 1/5. He had slightly low CD4 count at diagnosis. His anti retroviral medications include Lamividine 300mg, Tenofovir 300 mg combination od, Ritonavir 50mg, Iopinavir 200mg combination od. His HIV viral load remained undetectable. CD 4 counts regained normal levels at the end of chemotherapy cycles (see Table 1). He was started on continuous infusion CDE regimen (Cyclophosphamide, Doxorubicin and Etoposide) and tolerated the chemotherapy well. He was admitted with neutropenic sepsis every time after 3rd cycle and severe nuetropenia (ANC <500) never persisted for more than 4 days. He had a PET scan (whole body) after 3 cycles which was negative. He did not receive intra-thecal chemotherapy as LDH was not elevated. He presented a month later of completing chemotherapy with severe body pain and headache and within 3 days developed cranial nerve palsies (bilateral VI, right X11 and extra pyramidal signs in right leg.) His CT and MRI brain were normal. CSF showed 620 lymphocytes/cu mm. Flow cytometry on the CSF cells showed positivity for CD19, CD20 and monoclonal for lamda. This confirmed CNS involvement with lymphoma. Meanwhile the platelet count had dropped immediately to 80 × 10 9/L. Bone marrow showed infiltration with blasts (~ 35% showing deep blue cytoplasm with intense vacuolation). Cytogenetics and FISH could not be done. LDH was 1600 U/L (Normal up to 460 U/L). Flow cytometry showed CD 20, CD19, CD10, CD45 positivity with lamda restriction. Hence it is probable that the patient had Diffuse Large Cell Lymphoma- Burkitts like. He was planned and started on R Hyper CVAD regimen. In view of florid CNS manifestation with marrow involvement it was decided to give intrathecal rituximab in addition to triple IT. After informed consent, he was given 10 mg of rituximab in 5ml normal saline followed by triple Intrathecal with methotrexate, cytosine and hydrocortisone and given twice during each cycle as per the protocol. Intrathecal rituximb was given one dose at each cycle. He received a total of 12 cycles of triple IT. The abnormal lymphoid cells in CSF disappeared after the first intra-thecal chemotherapy He was started on R hyper CVAD with 75 % of dose reduction. His neutropenic period was not unduly prolonged and was manageable. He went into remission after the first cycle and the CNS status improved slowly and at the end of second cycle there was no residual neurological deficit. After 4 cycles, the dose had to be halved in view of prolonged neutropenia and hence it was decided to stop with 6 cycles. He received cranio-spinal RT after 6 cycles and has remained in continuous remission for more than 6 months so far.Table 1:CD4/CD8 Ratios at various time points of treatment:CD3 (716-2130)CD4 (354-1100)CD8 (192-980)Ratio (0.57-2.03)At diagnosis123921510010.22At CNS relapse14108804901.79Post 4 cycles of hyper CVAD126024010200.23End of therapy14257506751.11 Conclusion: Eventhough this observation was made in one patient, the dramatic response in this patient who otherwise would have had very poor prognosis, may warrant its use in patients with florid CNS manifestations. Disclosures: Off Label Use: Rituximab has been used extensively in B cell lymphomas. However its use as an intrathecal medicine is still in trials and is not generally recommended in all patients.

Combination of NVP-BEZ235 and Enzastaurin on B-Cell Lymphoma Cell Lines: An Effective Therapeutic Strategy

Blood ◽  
2011 ◽  
Vol 118 (21) ◽  
pp. 2719-2719 ◽  
Author(s):  
Monica Civallero ◽  
Maria Cosenza ◽  
Samantha Pozzi ◽  
Stefano Sacchi
Keyword(s):  
Bone Marrow ◽  
B Cell ◽  
Cell Lines ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Lymphoid Cells ◽  
Lymphoma Cell ◽  
Lymphoma Cells ◽  
Apoptosis Pathways ◽  
Extrinsic Apoptosis

Abstract Abstract 2719 Non-Hodgkin's lymphoma is the most common hematologic neoplasm in adults. Chemotherapy combined with CD-20 monoclonal antibodies has improved survival in both indolent and aggressive B-NHL. However, a substantial subset of patients does not achieve a cure or long disease remission. This has promoted the identification of new targeted treatments and new agents that have shown promising efficacy for future B-NHL therapies. The phosphatidylinositol 3-kinase (PI3K) mammalian target of rapamicin (mTOR) pathway mediates proliferation, survival and drug resistance in lymphoma cells. NVP-BEZ235 (BEZ235) is a new, orally bio available inhibitor of PI3K and mTOR and a representative of a new class of anti-tumour agents. In the current study, the efficacy of the combination of two orally available inhibitor to PI3K/mTOR (BEZ235) and PKCbeta/AKT (enzastaurin) was evaluated in B-cell lymphoma cell lines (RL, WSH-NHL, Jeko and Granta). First, we tested the anti-lymphoma activity of BEZ235 alone and in combination with enzastaurin, everolimus and perifosine. Results using MTT assay were expressed as fraction of cells killed by the individual drug or the combination in the drug-treated versus untreated cells. The interaction between drugs was analyzed by isobologram analysis using the STACorp8.2 software program based upon the Chou-Talalay method to determine if the combination were additive or synergistic. We found that enzastaurin, everolimus and perifosine enhanced the cytotoxicity triggered by BEZ235; a clear synergistic interaction (CI<1) appeared after 48 hours using low concentrations of the all compounds. We examined the functional effects of BEZ235 alone and in combination on apoptosis in lymphoma cells. We demonstrated that BEZ235 (20nM) alone after 24 hours induces an increase of 8–10% of apoptotic cells versus untreated, instead BEZ235 (20nM) in combination with enzastaurin (5microM) after 24 hours induces an increase of 25%. We next defined mechanisms whereby BEZ235 alone and in combination induce apoptosis in lymphoid cells. In particular, BEZ235 combined with enzastaurin induces both intrinsic and extrinsic apoptosis pathways with caspase 3, caspase 9, caspase 8 cleavage. We also showed that the combination of BEZ235 and enzastaurin decreases viability and induce apoptosis in B-cell lymphoma cell lines and peripheral blood mononuclear cells (PBMCs) from lymphoma patients. The combination has no effect on normal PBMCs and suppresses cell prolipheration of B-cell lymphoma cell lines (RL and Jeko) when co-cultured with bone marrow stromal cells in a system that mimics the bone marrow microenvironment. BEZ235, enzastaurin, everolimus and perifosine are inhibitors of intracellular pathways, thought we investigated effects of BEZ235 alone and in combinations with the other compounds in targeting p-AKT, p-mTOR, p-GSK3beta, p-p70, p-p90, p-MAPK, p-4EBP1 and cyclin D1 pathways by Western Blot. In addition, we demonstrated that BEZ235 plus enzastaurin resulted in increased expression of pro-apoptotic Bim, and in decrease expression of anti-apoptotic Bcl-2, which could not be abrogated by BEZ235 alone. In conclusion, our data suggest that in B cell lymphoma cell lines, BEZ235 in combination with enzastaurin elicits its antitumor effect better that combinated with perifosine and everolimus. Our data reveals that the drug combination targets phosphorilation of PI3K/Akt/mTOR pathways and induces both intrinsic and extrinsic apoptosis pathways. Furthermore, inhibition of Bcl-2 anti-apoptosis family members may, in part, explain the efficacy of signalling blockade in lymphoma cells and suggests an additional therapeutic targeting strategy. Therefore, these preclinical data support the potential use of BEZ235 in patients with NHL, and in particular provide rationale for combination with enzastaurin. Disclosures: No relevant conflicts of interest to declare.

scholarly journals DESIGN OF BIOMETRIC PROTECTION AUTHENTIFICATION SYSTEM BASED ON K-AVERAGE METHOD

2021 ◽  
Vol 12 (4) ◽  
pp. 85-95
Author(s):  
Yaroslav Voznyi ◽  
Mariia Nazarkevych ◽  
Volodymyr Hrytsyk ◽  
Nataliia Lotoshynska ◽  
Bohdana Havrysh
Keyword(s):  
Machine Learning ◽  
Learning Outcomes ◽  
Learning System ◽  
Training Data ◽  
Biometric Identification ◽  
Security Systems ◽  
Traditional Media ◽  
Data Set ◽  
Fingerprint Data

The method of biometric identification, designed to ensure the protection of confidential information, is considered. The method of classification of biometric prints by means of machine learning is offered. One of the variants of the solution of the problem of identification of biometric images on the basis of the k-means algorithm is given. Marked data samples were created for learning and testing processes. Biometric fingerprint data were used to establish identity. A new fingerprint scan that belongs to a particular person is compared to the data stored for that person. If the measurements match, the statement that the person has been identified is true. Experimental results indicate that the k-means method is a promising approach to the classification of fingerprints. The development of biometrics leads to the creation of security systems with a better degree of recognition and with fewer errors than the security system on traditional media. Machine learning was performed using a number of samples from a known biometric database, and verification / testing was performed with samples from the same database that were not included in the training data set. Biometric fingerprint data based on the freely available NIST Special Database 302 were used to establish identity, and the learning outcomes were shown. A new fingerprint scan that belongs to a particular person is compared to the data stored for that person. If the measurements match, the statement that the person has been identified is true. The machine learning system is built on a modular basis, by forming combinations of individual modules scikit-learn library in a python environment.

Comparative Analysis of Machine Learning Techniques Using Predictive Modeling

2020 ◽  
Vol 13 ◽  
Author(s):  
Ritu Khandelwal ◽  
Hemlata Goyal ◽  
Rajveer Singh Shekhawat
Keyword(s):  
Machine Learning ◽  
Comparative Analysis ◽  
Data Science ◽  
Training Data ◽  
Machine Learning Techniques ◽  
Future Trends ◽  
Data Set ◽  
Learning Stage ◽  
Learning Techniques ◽  
Different Types

Introduction: Machine learning is an intelligent technology that works as a bridge between businesses and data science. With the involvement of data science, the business goal focuses on findings to get valuable insights on available data. The large part of Indian Cinema is Bollywood which is a multi-million dollar industry. This paper attempts to predict whether the upcoming Bollywood Movie would be Blockbuster, Superhit, Hit, Average or Flop. For this Machine Learning techniques (classification and prediction) will be applied. To make classifier or prediction model first step is the learning stage in which we need to give the training data set to train the model by applying some technique or algorithm and after that different rules are generated which helps to make a model and predict future trends in different types of organizations. Methods: All the techniques related to classification and Prediction such as Support Vector Machine(SVM), Random Forest, Decision Tree, Naïve Bayes, Logistic Regression, Adaboost, and KNN will be applied and try to find out efficient and effective results. All these functionalities can be applied with GUI Based workflows available with various categories such as data, Visualize, Model, and Evaluate. Result: To make classifier or prediction model first step is learning stage in which we need to give the training data set to train the model by applying some technique or algorithm and after that different rules are generated which helps to make a model and predict future trends in different types of organizations Conclusion: This paper focuses on Comparative Analysis that would be performed based on different parameters such as Accuracy, Confusion Matrix to identify the best possible model for predicting the movie Success. By using Advertisement Propaganda, they can plan for the best time to release the movie according to the predicted success rate to gain higher benefits. Discussion: Data Mining is the process of discovering different patterns from large data sets and from that various relationships are also discovered to solve various problems that come in business and helps to predict the forthcoming trends. This Prediction can help Production Houses for Advertisement Propaganda and also they can plan their costs and by assuring these factors they can make the movie more profitable.

scholarly journals Building Damage Detection from Post-Event Aerial Imagery Using Single Shot Multibox Detector

2019 ◽  
Vol 9 (6) ◽  
pp. 1128 ◽  
Author(s):  
Yundong Li ◽  
Wei Hu ◽  
Han Dong ◽  
Xueyan Zhang
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Hurricane Sandy ◽  
Training Data ◽  
Aerial Images ◽  
Detection Methods ◽  
Single Shot ◽  
Data Set ◽  
Augmentation Strategies ◽  
Post Disaster

Using aerial cameras, satellite remote sensing or unmanned aerial vehicles (UAV) equipped with cameras can facilitate search and rescue tasks after disasters. The traditional manual interpretation of huge aerial images is inefficient and could be replaced by machine learning-based methods combined with image processing techniques. Given the development of machine learning, researchers find that convolutional neural networks can effectively extract features from images. Some target detection methods based on deep learning, such as the single-shot multibox detector (SSD) algorithm, can achieve better results than traditional methods. However, the impressive performance of machine learning-based methods results from the numerous labeled samples. Given the complexity of post-disaster scenarios, obtaining many samples in the aftermath of disasters is difficult. To address this issue, a damaged building assessment method using SSD with pretraining and data augmentation is proposed in the current study and highlights the following aspects. (1) Objects can be detected and classified into undamaged buildings, damaged buildings, and ruins. (2) A convolution auto-encoder (CAE) that consists of VGG16 is constructed and trained using unlabeled post-disaster images. As a transfer learning strategy, the weights of the SSD model are initialized using the weights of the CAE counterpart. (3) Data augmentation strategies, such as image mirroring, rotation, Gaussian blur, and Gaussian noise processing, are utilized to augment the training data set. As a case study, aerial images of Hurricane Sandy in 2012 were maximized to validate the proposed method’s effectiveness. Experiments show that the pretraining strategy can improve of 10% in terms of overall accuracy compared with the SSD trained from scratch. These experiments also demonstrate that using data augmentation strategies can improve mAP and mF1 by 72% and 20%, respectively. Finally, the experiment is further verified by another dataset of Hurricane Irma, and it is concluded that the paper method is feasible.

A Challenging Case of A Myeloid Sarcoma Misdiagnosed as High Grade B-Cell Lymphoma

2020 ◽  
Vol 154 (Supplement_1) ◽  
pp. S97-S97
Author(s):  
A Herrmann ◽  
B Mai ◽  
S Elzamly ◽  
A Wahed ◽  
A Nguyen ◽  
...  
Keyword(s):  
Bone Marrow ◽  
B Cell ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Myeloid Sarcoma ◽  
Proliferation Index ◽  
High Grade ◽  
Cell Markers ◽  
Thoracolumbar Region ◽  
The Right

Abstract Introduction/Objective A 46-year-old female presented with severe back pain associated with progressive bilateral lower extremity weakness and paresthesia, urinary retention, and constipation. Computed tomography revealed a retroperitoneal mass encasing the right psoas muscle, obstructing the right kidney, and extending to the thoracolumbar region resulting in severe spinal compression. An epidural tumor resection was subsequently performed at an outside hospital. Methods Histological sections showed sheets of blastoid neoplastic cells with intermediate to large nuclei, irregular membranes, fine chromatin, and prominent nucleoli. Immunohistochemical stains showed that these cells were positive for CD43, CD79a (weak, focal), BCL2, C-MYC, and PAX5 (weak, focal) and negative for CD10, CD20, CD30, ALK1, BCL6, MUM1, and Tdt. The Ki-67 proliferation index was 75-80%. With this immunophenotype, this patient was diagnosed with a high grade B-cell lymphoma and transferred to our institution for further work-up. On review of the slides, further immunohistochemical testing was requested which revealed positivity for CD117 and myeloperoxidase (MPO). Results The overall morphological and immunophenotypical features are most compatible with myeloid sarcoma (MS) with aberrant expression of B-cell markers and this patient’s diagnosis was amended. Interestingly, the patient’s bone marrow examination only showed 2% myeloblasts with left shifted granulocytosis and concurrent fluorescence in situ hybridization (FISH) studies were negative. Conclusion A literature review showed that 40-50% of MS are misdiagnosed as lymphoma. MS can frequently stain with B-cell or T-cell markers, as seen in this case, which makes it challenging for an accurate diagnosis and sub- classification. In addition, our case is interesting in that there was only extramedullary presentation without bone marrow involvement. Typically, MS develops after the diagnosis of acute myeloid leukemia (AML) with an incidence of 3–5% after AML. It can also manifest de novo in healthy patients, who then go on to develop AML months to years later. Therefore, this patient will require close follow-up.

scholarly journals CT-based radiomics model with machine learning for predicting primary treatment failure in diffuse large B-cell Lymphoma

2021 ◽  
Vol 14 (10) ◽  
pp. 101188
Author(s):  
Raoul Santiago ◽  
Johanna Ortiz Jimenez ◽  
Reza Forghani ◽  
Nikesh Muthukrishnan ◽  
Olivier Del Corpo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Treatment Failure ◽  
B Cell ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Primary Treatment ◽  
Large B Cell Lymphoma ◽  
Large B Cell

scholarly journals Tumor staging in a Beagle dog with concomitant large B-cell lymphoma and T-cell acute lymphoblastic leukemia

2021 ◽  
pp. 104063872110110
Author(s):  
Alessandro Ferrari ◽  
Marzia Cozzi ◽  
Luca Aresu ◽  
Valeria Martini
Keyword(s):  
Bone Marrow ◽  
Lymph Node ◽  
T Cell ◽  
B Cell ◽  
Cell Lymphoma ◽  
Tumor Staging ◽  
Lymphoblastic Leukemia ◽  
B Cell Lymphoma ◽  
Large B Cell Lymphoma ◽  
Cell Acute Lymphoblastic Leukemia

An 8-y-old spayed female Beagle dog was presented with peripheral lymphadenomegaly. Lymph node cytology and flow cytometry led to the diagnosis of large B-cell lymphoma (LBCL). We detected minimal percentages of LBCL cells in peripheral blood and bone marrow samples. However, a monomorphic population of neoplastic cells different from those found in the lymph node was found in the bone marrow. T-cell acute lymphoblastic leukemia was suspected based on flow cytometric immunophenotyping. PCR for antigen receptor rearrangement (PARR) revealed clonal rearrangement of both B-cell and T-cell receptors, and the presence of both neoplastic clones in the lymph node, peripheral blood, and bone marrow. The dog was treated with multi-agent chemotherapy but died 46 d following diagnosis. Tumor staging and patient classification are needed to accurately establish a prognosis and select the most appropriate therapeutic protocol.

Sign in / Sign up

Export Citation Format

Share Document