WBCs-Net: type identification of white blood cells using convolutional neural network

Baghel, Neeraj; Verma, U. P.; Nagwanshi, Kapil Kumar

doi:10.1007/s11042-021-11449-z

Cited by 30 publications

(16 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our proposed model achieved higher performance than those reported by Abou et al [33], Baydilli [44], Banik et al [47], Huang et al [39], Jiang et al [37], Kutlu et al [49], Liang et al [50], Özyurt [42], Patil et al [43], Togacar et al [34], Wang et al [35], Yao et al [38], and Yu et al [51], who reported accuracy between 83% and 98%. However, it should be noted that the average performance of our proposal was lower than those reported by Baghel et al [45] and Basnet et al [36], where they have included image processing for feature extraction to enhance the prediction performance. Likewise, the works of Çınar et al [23], Hedge et al [48], and Khan et al [40] have reported accuracy values higher than 99%.…”

Section: Resultscontrasting

confidence: 65%

“…Research presenting a multi-level scheme in the WBC classification is scarce. Although Baghel et al [ 45 ] do not perform a plan, they propose a CNN classification model whose performance is evaluated in two phases: an initial step, binary discrimination between the mononuclear and polymorphonuclears, and a second phase that corresponds to the classification of subtypes. Tran et al [ 46 ] presented as an initial setup a DL semantic segmentation between WBC and RBC, as initial steps for classifying leukocytes.…”

Section: State Of the Artmentioning

confidence: 99%

“…Simpler models that maintain good performance with fewer trainable parameters in their architecture could be generated. However, these methods require image processing techniques for feature extraction, making them slower [ 45 , 47 ]. Therefore, to implement deep learning models in a CAD system, methods should have a reasonable trade-off between performance and complexity without affecting the processing speed.…”

Section: State Of the Artmentioning

confidence: 99%

See 2 more Smart Citations

An Efficient Multi-Level Convolutional Neural Network Approach for White Blood Cells Classification

et al. 2022

View full text Add to dashboard Cite

The evaluation of white blood cells is essential to assess the quality of the human immune system; however, the assessment of the blood smear depends on the pathologist’s expertise. Most machine learning tools make a one-level classification for white blood cell classification. This work presents a two-stage hybrid multi-level scheme that efficiently classifies four cell groups: lymphocytes and monocytes (mononuclear) and segmented neutrophils and eosinophils (polymorphonuclear). At the first level, a Faster R-CNN network is applied for the identification of the region of interest of white blood cells, together with the separation of mononuclear cells from polymorphonuclear cells. Once separated, two parallel convolutional neural networks with the MobileNet structure are used to recognize the subclasses in the second level. The results obtained using Monte Carlo cross-validation show that the proposed model has a performance metric of around 98.4% (accuracy, recall, precision, and F1-score). The proposed model represents a good alternative for computer-aided diagnosis (CAD) tools for supporting the pathologist in the clinical laboratory in assessing white blood cells from blood smear images.

show abstract

Section: Resultscontrasting

confidence: 65%

Section: State Of the Artmentioning

confidence: 99%

Section: State Of the Artmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Multi-Level Convolutional Neural Network Approach for White Blood Cells Classification

et al. 2022

View full text Add to dashboard Cite

show abstract

“…CNN performs a wide range of Computer Vision tasks. Over the years, CNN has enabled numerous researchers to contribute to the various domains [40,41] and continue to succeed. A CNN is made up of multiple layers, each of which has a task to do when extracting features from input data.…”

Section: Cnn and Its Layersmentioning

confidence: 99%

Unmanned Aerial Vehicle Assisted Forest Fire Detection Using Deep Convolutional Neural Network

Rahman¹,

Sakif²,

Sikder³

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Disasters may occur at any time and place without little to no presage in advance. With the development of surveillance and forecasting systems, it is now possible to forebode the most life-threatening and formidable disasters. However, forest fires are among the ones that are still hard to anticipate beforehand, and the technologies to detect and plot their possible courses are still in development. Unmanned Aerial Vehicle (UAV) image-based fire detection systems can be a viable solution to this problem. However, these automatic systems use advanced deep learning and image processing algorithms at their core and can be tuned to provide accurate outcomes. Therefore, this article proposed a forest fire detection method based on a Convolutional Neural Network (CNN) architecture using a new fire detection dataset. Notably, our method also uses separable convolution layers (requiring less computational resources) for immediate fire detection and typical convolution layers. Thus, making it suitable for real-time applications. Consequently, after being trained on the dataset, experimental results show that the method can identify forest fires within images with a 97.63% accuracy, 98.00% F1 Score, and 80% Kappa. Hence, if deployed in practical circumstances, this identification method can be used as an assistive tool to detect fire outbreaks, allowing the authorities to respond quickly and deploy preventive measures to minimize damage.

show abstract

“…Deep Learning has been applied in a variety of fields, especially in recognition [16] and detection [17]. Healthcare sector is a big gun of this technique recently such in medical imaging [18], sentiment analysis [19], disease detections [20] and classifications [21] and so on [22]. Image recognition tasks have gotten tremendous hype in the Deep Learning fields.…”

Section: Introductionmentioning

confidence: 99%

Detecting Deepfake Images Using Deep Learning Techniques and Explainable AI Methods

Abir¹,

Khanam²,

Alam³

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

WBCs-Net: type identification of white blood cells using convolutional neural network

Cited by 30 publications

References 26 publications

An Efficient Multi-Level Convolutional Neural Network Approach for White Blood Cells Classification

An Efficient Multi-Level Convolutional Neural Network Approach for White Blood Cells Classification

Unmanned Aerial Vehicle Assisted Forest Fire Detection Using Deep Convolutional Neural Network

Detecting Deepfake Images Using Deep Learning Techniques and Explainable AI Methods

Contact Info

Product

Resources

About