scholarly journals Hybrid Inception v3 XGBoost Model for Acute Lymphoblastic Leukemia Classification

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
S. Ramaneswaran ◽  
Kathiravan Srinivasan ◽  
P. M. Durai Raj Vincent ◽  
Chuan-Yu Chang
Keyword(s):  
Acute Lymphoblastic Leukemia ◽  
Lymphoblastic Leukemia ◽  
Classification Performance ◽  
Image Feature ◽  
Pediatric Malignancy ◽  
Proposed Model ◽  
Feature Extractor ◽  
Life Threatening ◽  
Better Than

Acute lymphoblastic leukemia (ALL) is the most common type of pediatric malignancy which accounts for 25% of all pediatric cancers. It is a life-threatening disease which if left untreated can cause death within a few weeks. Many computerized methods have been proposed for the detection of ALL from microscopic cell images. In this paper, we propose a hybrid Inception v3 XGBoost model for the classification of acute lymphoblastic leukemia (ALL) from microscopic white blood cell images. In the proposed model, Inception v3 acts as the image feature extractor and the XGBoost model acts as the classification head. Experiments indicate that the proposed model performs better than the other methods identified in literature. The proposed hybrid model achieves a weighted F1 score of 0.986. Through experiments, we demonstrate that using an XGBoost classification head instead of a softmax classification head improves classification performance for this dataset for several different CNN backbones (feature extractors). We also visualize the attention map of the features extracted by Inception v3 to interpret the features learnt by the proposed model.

scholarly journals An Efficient Approach for Segmentation and Classification of Acute Lymphoblastic Leukemia via Optimized Spike-based Network

2021 ◽  
Author(s):  
Ali Noshad ◽  
saeed fallahi
Keyword(s):  
Acute Lymphoblastic Leukemia ◽  
Blood Cells ◽  
Lymphoblastic Leukemia ◽  
Gaussian Function ◽  
Principal Component ◽  
Complex Issue ◽  
Morphological Variations ◽  
Learning Techniques ◽  
Proposed Model

Abstract Identification of uncontrolled accumulation of abnormal blood cells ( lymphoblasts ) considered to be a challenging task. Despite a wide variety of image processing and deep learning techniques, the task of extracting the features from Acute Lymphoblastic Leukemia (ALL) images and detection of ALL cells is still challenging and complex issue due to morphological variations in cells. In order to overcome these drawbacks, in this study, we proposed a new framework with a combination of spiking and residual network for the detection and classification of lymphoblasts cells from healthy ones in blood sample images. According to this, features are extracted using a novel First-Spike-based approach, and then the Gaussian function is applied to remove the low-intensity edges. To reduce dimensionality, Principal Component Analysis ( PCA ) is used and finally, a developed deep residual architecture is employed to diagnose the ALL blood cells from the reconstructed images. To show the effectiveness of the proposed model, it is evaluated on microscopic images of blood samples from ALL Images (ALL- IDB ) and ISBI -2019 C- NMC dataset. The results show the superiority of the model to be an appropriate choice for future biomedical imaging tasks.

scholarly journals Space Precession Target Classification Based on Radar High-Resolution Range Profiles

2019 ◽  
Vol 2019 ◽  
pp. 1-9
Author(s):  
Yizhe Wang ◽  
Cunqian Feng ◽  
Yongshun Zhang ◽  
Sisan He
Keyword(s):  
Parameter Extraction ◽  
Classification Performance ◽  
Support Vector ◽  
Electromagnetic Data ◽  
Feature Extractor ◽  
Different Types ◽  
Radar Echo ◽  
High Level ◽  
Cone Target

Precession is a common micromotion form of space targets, introducing additional micro-Doppler (m-D) modulation into the radar echo. Effective classification of space targets is of great significance for further micromotion parameter extraction and identification. Feature extraction is a key step during the classification process, largely influencing the final classification performance. This paper presents two methods for classifying different types of space precession targets from the HRRPs. We first establish the precession model of space targets and analyze the scattering characteristics and then compute electromagnetic data of the cone target, cone-cylinder target, and cone-cylinder-flare target. Experimental results demonstrate that the support vector machine (SVM) using histograms of oriented gradient (HOG) features achieves a good result, whereas the deep convolutional neural network (DCNN) obtains a higher classification accuracy. DCNN combines the feature extractor and the classifier itself to automatically mine the high-level signatures of HRRPs through a training process. Besides, the efficiency of the two classification processes are compared using the same dataset.

scholarly journals Single-Cell Developmental Classification of B-Cell Precursor Acute Lymphoblastic Leukemia at Diagnosis Reveals Predictors of Relapse

2018 ◽  
Vol 64 ◽  
pp. S33-S34 ◽  
Author(s):  
Kara Davis ◽  
Zinaida Good ◽  
Jolanda Sarno ◽  
Astraea Jager ◽  
Nikolay Samusik ◽  
...  
Keyword(s):  
Acute Lymphoblastic Leukemia ◽  
B Cell ◽  
Single Cell ◽  
Lymphoblastic Leukemia ◽  
Cell Precursor

scholarly journals Acute Lymphoblastic Leukemia, Version 2.2021, NCCN Clinical Practice Guidelines in Oncology

2021 ◽  
Vol 19 (9) ◽  
pp. 1079-1109
Author(s):  
Patrick A. Brown ◽  
Bijal Shah ◽  
Anjali Advani ◽  
Patricia Aoun ◽  
Michael W. Boyer ◽  
...  
Keyword(s):  
Acute Lymphoblastic Leukemia ◽  
Supportive Care ◽  
Lymphoblastic Leukemia ◽  
Philadelphia Chromosome ◽  
Treatment Strategies ◽  
Adolescent And Young Adult ◽  
Cancer Center ◽  
Nccn Guidelines ◽  
Treatment Regimens

The NCCN Guidelines for Acute Lymphoblastic Leukemia (ALL) focus on the classification of ALL subtypes based on immunophenotype and cytogenetic/molecular markers; risk assessment and stratification for risk-adapted therapy; treatment strategies for Philadelphia chromosome (Ph)-positive and Ph-negative ALL for both adolescent and young adult and adult patients; and supportive care considerations. Given the complexity of ALL treatment regimens and the required supportive care measures, the NCCN ALL Panel recommends that patients be treated at a specialized cancer center with expertise in the management of ALL This portion of the Guidelines focuses on the management of Ph-positive and Ph-negative ALL in adolescents and young adults, and management in relapsed settings.

Acute Leukemia

2016 ◽  
Author(s):  
Richard A. Larson ◽  
Roland B Walter
Keyword(s):  
Acute Myeloid Leukemia ◽  
Acute Lymphoblastic Leukemia ◽  
Acute Leukemia ◽  
Myeloid Leukemia ◽  
Who Classification ◽  
Lymphoblastic Leukemia ◽  
World Health ◽  
Acute Leukemias ◽  
Acute Myeloid

The acute leukemias are malignant clonal disorders characterized by aberrant differentiation and proliferation of transformed hematopoietic progenitor cells. These cells accumulate within the bone marrow and lead to suppression of the production of normal blood cells, with resulting symptoms from varying degrees of anemia, neutropenia, and thrombocytopenia or from infiltration into tissues. They are currently classified by their presumed cell of origin, although the field is moving rapidly to genetic subclassification. This review covers epidemiology; etiology; classification of leukemia by morphology, immunophenotyping, and cytogenetic/molecular abnormalities; cytogenetics of acute leukemia; general principles of therapy; acute myeloid leukemia; acute lymphoblastic leukemia; and future possibilities. The figure shows the incidence of acute leukemias in the United States. Tables list World Health Organization (WHO) classification of acute myeloid leukemia and related neoplasms, expression of cell surface and cytoplasmic markers for the diagnosis of acute myeloid leukemia and mixed-phenotype acute leukemia, WHO classification of acute lymphoblastic leukemia, WHO classification of acute leukemias of ambiguous lineage, WHO classification of myelodysplastic syndromes, European LeukemiaNet cytogenetic and molecular genetic subsets in acute myeloid leukemia with prognostic importance, cytogenetic and molecular subtypes of acute lymphoblastic leukemia, terminology used in leukemia treatment, and treatment outcome for adults with acute leukemia. This review contains 1 highly rendered figure, 9 tables, and 117 references.

Life-threatening Hypercalcemia as the First Manifestation of Acute Lymphoblastic Leukemia

2019 ◽  
Vol 56 (11) ◽  
pp. 972-974 ◽  
Author(s):  
Kakali Roy ◽  
Rajni Sharma ◽  
Manisha Jana ◽  
Vandana Jain
Keyword(s):  
Acute Lymphoblastic Leukemia ◽  
Lymphoblastic Leukemia ◽  
Life Threatening

scholarly journals BCR-ABL1–like B-Acute Lymphoblastic Leukemia/Lymphoma: A Comprehensive Review

2019 ◽  
Vol 144 (2) ◽  
pp. 150-155 ◽  
Author(s):  
Sarika Jain ◽  
Anu Abraham
Keyword(s):  
Acute Lymphoblastic Leukemia ◽  
World Health Organization ◽  
Kinase Inhibitors ◽  
Lymphoblastic Leukemia ◽  
World Health ◽  
Comprehensive Review ◽  
The World ◽  
Health Organization ◽  
Stimulating Factor

Context.— In the 2016 update of the World Health Organization (WHO) classification of hematopoietic neoplasms, BCR-ABL1–like B-acute lymphoblastic leukemia/lymphoma (B-ALL) is added as a new provisional entity that lacks the BCR-ABL1 translocation but shows a pattern of gene expression very similar to that seen in B-ALL with BCR-ABL1. Objective.— To review the kinase-activating alterations and the diagnostic approach for BCR-ABL1–like B-ALL. Data Sources.— We provide a comprehensive review of BCR-ABL1–like B-ALL based on recent literature and the 2016 update of the World Health Organization classification of hematopoietic neoplasms. Conclusions.— Several types of kinase-activating alterations (fusions or mutations) are identified in BCR-ABL1–like B-ALL. The main categories are alterations in the ABL class family of genes, encompassing ABL1, ABL2, PDGFRB, PDGFRA (rare), and colony-stimulating factor 1 receptor (CSF1R) fusions, or the JAK2 class family of genes, encompassing alterations in JAK2, CRLF2, EPOR, and other genes in this pathway. These alterations determine the sensitivity to tyrosine kinase inhibitors. As a wide variety of genomic alterations are included in this category, the diagnosis of BCR-ABL1–like B-ALL is extremely complex. Stepwise algorithms and comprehensive unbiased testing are the 2 ways to approach the diagnosis of BCR-ABL1–like B-ALL.

Sign in / Sign up

Export Citation Format

Share Document