Are There Different Types Of Leukemia – HD-OCT study may be useful in investigating markers of the preclinical stage of diabetic retinopathy in patients with type 1 diabetes

Diagnostic performance of a support vector device in dermofluoroscopic melanoma detection: results of a retrospective clinical study on 214 pigmented skin lesions

Are There Different Types Of Leukemia

Open Access Policy Institutional Open Access Program Special Topics Guides Research Publication Process and Publication Ethics Article Processing Fee Awards References

Leukemia In Children And Teens

All articles published by me are available for direct use worldwide under an open access license. No special permission is required for re-use in whole or in part of the article published by me, including figures and tables. In articles published under the Creative Commons CC BY open access license, any part of the article may be reused without permission, provided the original article is clearly cited. Please see https:///openaccess for more information.

Feature articles represent interesting research with the potential to greatly impact the field. A feature article should be an important original paper that covers a variety of techniques or approaches, provides insight into future research directions, and describes possible research applications.

Feature articles are submitted by personal order or on the recommendation of scientific editors and must receive positive feedback from reviewers.

Editors’ Choice articles are based on recommendations from scientific editors of journals around the world. The editors select a small number of articles recently published in the journal that they believe will be of particular interest to readers or are important in the relevant research field. The goal is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.

Frequency Of Different Types Of Leukemia In Arica, Chile Between 2011…

Written by Nizar AhmedNizar Ahmed Scilit Preprints.org Google Scholar, Altuğ Yiğit Altuğ Yiğit Scilit Preprints.org Google Scholar View publications, Zerrin Işık Zerrin Işık Scilit Preprints.org Google Scholar View publications and publications by Adil Alpkocak Scili Alpko. *

Application receipt date: June 2, 2019 / Publication date: August 22, 2019 / Acceptance date: August 23, 2019 / Publication date: August 25, 2019

Leukemia is a deadly cancer and has two main types: acute and chronic. Each type has two additional subtypes: lymphoid and myeloid. So there are a total of four subtypes of leukemia. This study proposes a new approach to diagnose all subtypes of leukemia from microscopic images of blood cells using convolutional neural networks (CNN), which requires a large training set. Therefore, we synthetically investigated the effects of data augmentation for an increasing number of training examples. We used two publicly available leukemia data sources: ALL-IDB and ASH Image Bank. We then applied seven different image transformation techniques as well as data augmentation. We designed a CNN architecture that can detect all leukemia subtypes. We also tested other well-known machine learning algorithms such as Naive Bayes, Support Vector Machine, k-nearest neighbor and decision tree. To evaluate our approach, we set up a set of experiments and used 5-fold cross-validation. Our results from the experiments showed that the performance of our CNN model had an accuracy of 88.25% and 81.74% in healthy versus leukemia classification and multi-class classification of all subtypes, respectively. Finally, we also showed that the CNN model outperforms other known machine learning algorithms.

Diagnosis of leukemia; recognition of leukemia subtypes; multiclass classification; microscopic images of blood cells; data augmentation; deep learning; A convolutional neural network

Leukemia Rash: Pictures, Types, Symptoms, And More

Leukemia is an aggressive disease related to white blood cells (WBC) and affects the bones and blood in the human body. This disease can lead to the destruction of the human body’s immune system. There are two main types of leukemia, acute and chronic leukemia, depending on how quickly it progresses. In acute leukemia, an infected WBC does not function or behave like a normal WBC; May behave like normal WBC in chronic leukemia. Therefore, chronic leukemia can be severe because it is indistinguishable from normal white blood cells. Additionally, depending on the size and shape of the WBC, each type of leukemia has two subtypes: lymphoid and myeloid. In general, there are four subtypes of leukemia as shown in Figure 1; acute lymphocytic leukemia (ALL), acute myeloid leukemia (AML), chronic lymphocytic leukemia (CLL) and chronic myeloid leukemia (CML) [ 1 , 2 ]. Determining the presence and specific types of leukemia is important for hematologists to avoid medical risks and determine the correct treatment. Thus, using smart diagnostic methods will facilitate and speed up the discovery of leukemia subtypes with the help of images of blood cells (i.e. blood smears).

Microscopic blood tests are considered the most important procedure in the diagnosis of leukemia [2]. Blood smear analysis is the most common way to detect leukemia, but it is not the only technique. Interventional radiology is an alternative technique for diagnosing leukemia. However, radiological techniques such as percutaneous aspiration, biopsy and catheter drainage have inherent limitations in sensitivity to imaging modality and resolution of radiographs [3]. Furthermore, other techniques such as molecular cytogenetics, long-distance inverse polymerase chain reaction (LDI-PCR), and array-based comparative genomic hybridization (aCGH) require extensive research and time to identify leukemia types [ 4 ]. Because these techniques require time and cost, microscopic blood and bone marrow tests are the most common methods for determining leukemia subtypes.

A machine learning (ML) algorithm will help identify cancerous blood cells from lung cells if a large training set is available. The ALL-IDB leukemia image database [ 5 ] is one of the datasets used as a benchmark by many medical researchers [ 1 , 6 , 7 ]. An additional leukemia dataset was obtained from the American Society of Hematology (ASH) and is available on their website [8]. Thanh et al. [7] used the ASH database to identify AML leukemia in their study. Google is another source of unannotated leukemia images, where images are randomly collected from websites. Karthikeyan et al. [9] used microscopic images collected from Google in their study to detect leukemia; Here, the authors themselves have added descriptions to the images. A successful application of machine learning-based leukemia diagnosis can be built on the use of an annotated image dataset.

Identification of leukemia subtypes from healthy samples is a very challenging problem. Many researchers in the literature have investigated binary classification between only one subtype versus healthy samples [1, 7, 9, 10, 11, 12]. They achieved very high performance, even more than 96% accuracy. In addition, Shafique et al. [6] Specimens are further classified with all subtypes based on the size of the cell and the nature of its nucleus. However, tackling the identification of all leukemia subtypes is a more challenging task than simple binary classification [13]. To the best of our knowledge, there is no automatic detection approach that addresses all leukemia subtypes.

Leukemic Stem Cells And Therapy Resistance In Acute Myeloid Leukemia

Several ML algorithms help to classify and identify leukemia disease from microscopic images. For example, Paswan et al. [10] using support vector machine (SVM) and k-nearest neighbors (k-NN) to classify AML leukemia subtype reached 83% accuracy. Patel et al. [1] applied SVM to classify ALL leukemia subtype and achieved an accuracy of 93%. Karthikeyan et al. [9] also used SVM and c-mean clustering technique to separate WBC from background and achieved 90% accuracy. Although using the deep learning (DL) approach appears to be more efficient, the performance is highly dependent on the quantity and quality of the data set used [6]. A convolutional neural network (CNN) is one of the common neural network architectures for dealing with image registration and classification problems. Shafik et al. [6] applied a convolutional neural network (CNN) to detect all leukemia subtypes. Their results recorded 99% for binary classification between ALL and HEALTHY samples and 96% for further classification of all subtypes alone. Thanh et al. [7] also built a CNN model consisting of five convolutional layers to perform binary classification of all leukemia subtypes and achieved an accuracy of 96.6%. Unfortunately, classification performance in this type of neural network required large training data to learn how to identify important objects from the entire image. However, developing a large training set is time consuming and labor intensive. To avoid this problem, we recommend expanding the limited number of samples by enlarging an image. Using an insufficient number of image samples in the training dataset may lead to overfitting problems [14]. Therefore, most researchers in the literature rely on applying some image modification techniques to synthetically increase the number of training set samples to avoid the overfitting problem. Patel et al. [1] Wiener median filters were applied to remove noise and blur. Many image modification techniques are used in the literature, such as image rotation and reflection, histogram comparison, image translation, grayscale conversion, image blurring, and image cropping [6, 9, 10]. The use of image augmentation makes it possible to use a DL approach that requires a large number of numbers in the training set.

In this study, we propose a new approach for diagnosing leukemia from microscopic blood images that identifies four subtypes of leukemia (i.e., ALL, AML, CLL, and CML) using the CNN deep learning architecture. To our knowledge, this is the first study.

Are there different kinds of leukemia, the different types of leukemia, how many types of leukemia cancer are there, different types of aml leukemia, what are the different types of leukemia, what different types of leukemia are there, different types of leukemia, what types of leukemia are there, are there stages of leukemia, how many different types of leukemia are there, different types of childhood leukemia, how many types of leukemia are there