A Comparison Study Between Deep Learning and Conventional Machine Learning on White Blood Cells Classification

Wibawa, Made Satria

doi:10.1109/icot.2018.8705892

Cited by 14 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The WBC sample needs to remove the red blood cells (RBCs) in the background and then segmented each WBC into a single frame [ 14 ]. In another work, M. S. Wibawa [ 15 ] applied a simple 5-layer deep learning Convolutional Neural Network (CNN) to classify stained WBC images into four categories and compared them with machine learning methods, namely Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Multi-Layer Perceptron (MLP) classifiers, to classify the feature values of WBCs, such as average brightness, entropy, kurtosis, etc. Zhao et al extracted feature values through texture features then used the SVM classifier to divide stained WBCs into Basophil, Eosinophil, and others [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning Based Label-Free Classification of Activated and Inactivated Neutrophils for Rapid Immune State Monitoring

Huang

Jeon

Liu

et al. 2021

Sensors

View full text Add to dashboard Cite

The differential count of white blood cells (WBCs) is one widely used approach to assess the status of a patient’s immune system. Currently, the main methods of differential WBC counting are manual counting and automatic instrument analysis with labeling preprocessing. But these two methods are complicated to operate and may interfere with the physiological states of cells. Therefore, we propose a deep learning-based method to perform label-free classification of three types of WBCs based on their morphologies to judge the activated or inactivated neutrophils. Over 90% accuracy was finally achieved by a pre-trained fine-tuning Resnet-50 network. This deep learning-based method for label-free WBC classification can tackle the problem of complex instrumental operation and interference of fluorescent labeling to the physiological states of the cells, which is promising for future point-of-care applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep-Learning Based Label-Free Classification of Activated and Inactivated Neutrophils for Rapid Immune State Monitoring

Huang

Jeon

Liu

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Neste trabalho, foi utilizada a CNN ResNet18 para o pré-processamento da imagem, pelo motivo de apresentar alta acurácia e demandar processamento razoável, como demonstra a Figura 1, e em substituição às camadas densas -referentes à rede neural -foi escolhido o classificador Support Vector Machine (SVM), devido ao fato deste apresentar bons resultados em diversos trabalhos [Wibawa S. 2018] e [Yao et al 2021]. A Figura 2 representa a arquitetura do modelo.…”

Section: Metodologiaunclassified

“…Diversas pesquisas têm sido realizadas para avaliar a eficácia das RNA na classificação do diferencial de leucócitos do sangue periférico . Além das RNA, também pode-se utilizar outros algoritmos de ML, tais como Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree (DT) e Random Forest (RF), para classificação de células brancas sanguíneas, como no estudo conduzido por Wibawa S. (2018).…”

Section: Introductionunclassified

Algoritmos de Aprendizado de Máquina para Classificação de Células Nucleadas do Sangue Periférico - Uma Experiência do Projeto Hemovision

Santos

Bertemes²,

Souza³

et al. 2022

Anais Da X Escola Regional De Informática De Goiás (ERI-GO 2022)

View full text Add to dashboard Cite

Este trabalho trata do uso de algoritmos de aprendizado de máquina para classificação de células nucleadas do sangue periférico. Foi utilizada a rede neural convolucional ResNet18 para o pré-processamento das imagens e em substituição às camadas densas; e para a saída foi escolhido o classificador Support Vector Machine (SVM). Foram usadas imagens disponibilizadas por um estudo de classificação de imagem do Hospital das Clínicas de Barcelona, contendo oito classes. O modelo desenvolvido obteve uma acurácia média de 97.2%, e o F1-Score médio de 97%, sendo que algumas classes obtiveram médias próximas de 100%, enquanto outras, de 95%. Diante dos resultados encontrados, constatou-se que os algoritmos de aprendizado de máquina podem ser integrados de forma satisfatória aos processos educacionais e de apoio ao diagnóstico.

show abstract

“…By processing patient data and data from comprehensive studies around the world, deep learning has made significant developments in the medical field, such as X-ray [1], MRI [2], gastroscopy [3], and other medical projects related to imaging. It also has significant help in the diagnosis of medical imaging symptoms, for example, cell classification [4], tumor lesions [5], and vascular analysis [6]. In proteomic analysis, by integrating proteomic information and combining structural deep network embedding (SDNE) framework [7].…”

Section: Introductionmentioning

confidence: 99%

Missing Teeth and Restoration Detection Using Dental Panoramic Radiography Based on Transfer Learning With CNNs

Chen

Huang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Common dental diseases include caries, periodontitis, missing teeth and restorations. Dentists still use manual methods to judge and label lesions which is very time-consuming and highly repetitive. This research proposal uses artificial intelligence combined with image judgment technology for an improved efficiency on the process. In terms of cropping technology in images, the proposed study uses histogram equalization combined with flat-field correction for pixel value assignment. The details of the bone structure improves the resolution of the high-noise coverage. Thus, using the polynomial function connects all the interstitial strands by the strips to form a smooth curve. The curve solves the problem where the original cropping technology could not recognize a single tooth in some images. The accuracy has been improved by around 4% through the proposed cropping technique. For the convolutional neural network (CNN) technology, the lesion area analysis model is trained to judge the restoration and missing teeth of the clinical panorama (PANO) to achieve the purpose of developing an automatic diagnosis as a precision medical technology. In the current 3 commonly used neural networks namely AlexNet, GoogLeNet, and SqueezeNet, the experimental results show that the accuracy of the proposed GoogLeNet model for restoration and SqueezeNet model for missing teeth reached 97.10% and 99.90%, respectively. This research has passed the Research Institution Review Board (IRB) with application number 202002030B0.

show abstract

A Comparison Study Between Deep Learning and Conventional Machine Learning on White Blood Cells Classification

Cited by 14 publications

References 8 publications

Deep-Learning Based Label-Free Classification of Activated and Inactivated Neutrophils for Rapid Immune State Monitoring

Deep-Learning Based Label-Free Classification of Activated and Inactivated Neutrophils for Rapid Immune State Monitoring

Algoritmos de Aprendizado de Máquina para Classificação de Células Nucleadas do Sangue Periférico - Uma Experiência do Projeto Hemovision

Missing Teeth and Restoration Detection Using Dental Panoramic Radiography Based on Transfer Learning With CNNs

Contact Info

Product

Resources

About