Acute Leukemia Classification Using Convolution Neural Network in Clinical Decision Support System

Ttp, Thanh; Pham, Giao N.; Park, Jinhyeok; Moon, Kwang-Seok; Lee, Suk-Hwan; Kwon, Ki-Ryong

doi:10.5121/csit.2017.71305

Cited by 14 publications

(9 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our experiments were conducted on Matlab with 1188 images, 70% (831 images) of them for training and the remaining 30% (357 images) for testing our model. The slightly narrow architecture used in [9] dramatically failed to reach an appropriate accuracy when applied to this augmented dataset. Therefore, we have presented here a deeper CNN architecture and changed the size of the input volume in order to improve the accuracy rate of the recognition of leukemia (our proposed CNN model achieved 96.6%).…”

Section: Resultsmentioning

confidence: 97%

“…In [9], the original ALL-IDB1 image database which consists of 108 cell image (59 normal and 49 abnormal cell images) was used. In this paper, to increase the accuracy of our proposed method, we have augmented the original dataset to 1188 pictures by applying transformations such as blurring, histogram equalization, reflection, translation, rotation, shearing.…”

Section: Resultsmentioning

confidence: 99%

“…ReLu is used as the activation function. In the preliminary version of this work that has been published in the 6th International Conference on Advanced Information Technologies and Applications (ICAITA 2017) [9], the authors have also adopted the convolutional neural network but with a slightly shallow architecture compared to the one proposed here and a really small number of data. In the current research, we present a deeper architecture trained on a significantly augmented dataset.…”

Section: A Proposed Cnn Architecturementioning

confidence: 99%

See 2 more Smart Citations

Leukemia Blood Cell Image Classification Using Convolutional Neural Network

Thanh¹,

Vununu²,

Atoev³

et al. 2018

IJCTE

Self Cite

114

View full text Add to dashboard Cite

Acute myeloid leukemia is a type of malignant blood cell cancer that can affect both children and adults. There are 60,140 people were expected to be diagnosed with Leukemia in 2016, according to the Leukemia and Lymphoma Society. In order to get the most effective treatment, the patient needs early diagnosis. Therefore we need to have a support system of early diagnosis to guide treatment for patients with acute leukemia as soon as possible. In this paper, the authors propose a Convolutional Neural Network (CNN) based method to distinguish normal and abnormal blood cell images. The proposed method achieves an accuracy up to 96.6% with the dataset including 1188 blood cell images.

show abstract

Section: Resultsmentioning

confidence: 97%

Section: Resultsmentioning

confidence: 99%

Section: A Proposed Cnn Architecturementioning

confidence: 99%

See 1 more Smart Citation

Leukemia Blood Cell Image Classification Using Convolutional Neural Network

Thanh¹,

Vununu²,

Atoev³

et al. 2018

IJCTE

Self Cite

114

View full text Add to dashboard Cite

show abstract

“…Here, the output result is used to calculate the network error rate to adjust network parameters, for network training. To do this, it compares the network output with a loss function that gives the correct answer and the error rate is calculated (TTP et al, 2017). The next step starts with the back propagation phase based on the calculated error rate.…”

Section: Feature Extractionmentioning

confidence: 99%

Dorsal Hand Veins Based Biometric Identification System Using Deep Learning

Nayebi

Turgut

2021

Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi

View full text Add to dashboard Cite

Identification systems have become biometric based, especially with the increase in the performance rates of machine learning methods. Biometric identification systems offer a high level of security by using reliable, difficult-to-change parameters. In this study, a biometric identification system is proposed using dorsal hand vein patterns. The relevant system has been tested on the sample dataset in the literature. The number of data were increased by adding noisy data to the data set used. Classification was made on the preprocessed images using SVM, ANN, LDA + KNN, and CNN methods. It has been determined that the highest identification accuracy is achieved when CNN is used, and CNN method provides higher performance compared to other methods. With the proposed identification system, after multiple runs, an average accuracy of 99.64% is achieved with the CNN machine learning method.

show abstract

“…Karakteristik dari penyakit ini ditandai dengan perkembangan sel darah putih yang tidak normal di sumsum tulang belakang tanpa menghambat pertumbuhan sel. Terdapat dua jenis leukemia yang umum diketahui yaitu Leukemia Limfosit Akut (LLA) yang mempengaruhi perkembangan sel limfosit dan Leukemia Mieloid Akut (LMA) yang mempengaruhi perkembangan sel mileoid (basofil, eosinofil, dan neutrofil) [2].…”

unclassified

Klasifikasi Sel Darah Putih dan Sel Limfoblas Menggunakan Metode Multilayer Perceptron Backpropagation

Liyantoko

Candradewi

Harjoko

2019

Indonesian J. Electron. Instrum. Syst.

View full text Add to dashboard Cite

Leukemia is a type of cancer that is on white blood cell. This disease are characterized by abundance of abnormal white blood cell called lymphoblast in the bone marrow. Classification of blood cell types, calculation of the ratio of cell types and comparison with normal blood cells can be the subject of diagnosing this disease. The diagnostic process is carried out manually by hematologists through microscopic image. This method is likely to provide a subjective result and time-consuming.The application of digital image processing techniques and machine learning in the process of classifying white blood cells can provide more objective results. This research used thresholding method as segmentation and multilayer method of back propagation perceptron with variations in the extraction of textural features, geometry, and colors. The results of segmentation testing in this study amounted to 68.70%. Whereas the classification test shows that the combination of feature extraction of GLCM features, geometry features, and color features gives the best results. This test produces an accuration value 91.43%, precision value of 50.63%, sensitivity 56.67%, F1Score 51.95%, and specitifity 94.16%.

show abstract

Acute Leukemia Classification Using Convolution Neural Network in Clinical Decision Support System

Abstract: Leukemia induced death has been listed in the top

Cited by 14 publications

References 1 publication

Leukemia Blood Cell Image Classification Using Convolutional Neural Network

Leukemia Blood Cell Image Classification Using Convolutional Neural Network

Dorsal Hand Veins Based Biometric Identification System Using Deep Learning

Klasifikasi Sel Darah Putih dan Sel Limfoblas Menggunakan Metode Multilayer Perceptron Backpropagation

Contact Info

Product

Resources

About