Automatic white blood cell classification using pre-trained deep learning models: ResNet and Inception

Habibzadeh, Mehdi; Jannesari, Mahboobeh; Rezaei, Zahra; Baharvand, Hossein; Totonchi, Mehdi

doi:10.1117/12.2311282

Cited by 155 publications

(81 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…c) Comparison results: Compared with previous research in the literature that manually extracts features, our study shares a similar range of results as studies such as [9], but has higher results than [15]. However, when comparing our results with deep learning models, our results are higher than [17], but lower than [19]. However, these variations in performance could be due to using different datasets and preprocessing steps.…”

Section: Resultssupporting

confidence: 74%

“…The researchers conclude that the best result was 95.7% accuracy using ResNet-50. Mehdi et al [19] classify WBCs into four primary types -neutrophils, eosinophils, lymphocytes and monocytes -by consecutive deep learning framework. Using ResNet V1 50, their framework detects, on average, 100%, whereas alternative ResNet V1 152 and ResNet got promising results with 99.84% and 99.46% accuracy rate, respectively.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Improved White Blood Cells Classification based on Pre-trained Deep Learning Models

Mohamed

El-Behaidy

Khoriba

et al. 2020

J. commun. softw. syst. (Online)

View full text Add to dashboard Cite

Leukocytes, or white blood cells (WBCs), are microscopic organisms that fight against infectious disease, bacteria, viruses and others. The manual method to classify and count WBCs is tedious, time-consuming and may have inaccurate results, whereas the automated methods are costly. This research aims to automatically identify and classify WBCs in a microscopic image into four types with higher accuracy. BCCD is the used dataset in this study, which is a scaled-down blood cell detection dataset. BCCD is firstly preprocessed by passing through various processes such as segmentation and augmentation; then, it is passed to the proposed model. Our model combines the advantage of deep models in automatically extracting features with the higher classification accuracy of traditional machine learning classifiers. The proposed model consists of two main stages: a shallow tuning pre-trained model and a traditional machine learning classifier on top of it. In this study, ten different pretrained models with six types of machine learning are used. Moreover, the fully connected network (FCN) of pre-trained models is used as a baseline classifier for comparison. The evaluation process shows that the hybrid of MobileNet-224 as a feature extractor and logistic regression as classifier has a higher rank-1 accuracy of 97.03%. Besides, the proposed hybrid model outperformed the baseline FCN by 25.78% on average.

show abstract

Section: Resultssupporting

confidence: 74%

Section: Related Workmentioning

confidence: 99%

Improved White Blood Cells Classification based on Pre-trained Deep Learning Models

Mohamed

El-Behaidy

Khoriba

et al. 2020

J. commun. softw. syst. (Online)

View full text Add to dashboard Cite

show abstract

“…We demonstrate fair performance (~60% balanced accuracy) of a 2D architecture. We also demonstrate poor performance (~30% balanced accuracy), worse than our 2D approach, of a pretrained network, Resnet-31 39 . Thus, our 2D network could be a better starting point for additional refinement of a 2D approach.…”

Section: Discussionmentioning

confidence: 81%

In situclassification of cell types in human kidney tissue using 3D nuclear staining

Woloshuk

Khochare

Almulhim

et al. 2020

Preprint

View full text Add to dashboard Cite

To understand the physiology and pathology of disease, capturing the heterogeneity of cell types within their tissue environment is fundamental. In such an endeavor, the human kidney presents a formidable challenge because its complex organizational structure is tightly linked to key physiological functions. Advances in imaging-based cell classification may be limited by the need to incorporate specific markers that can link classification to function. Multiplex imaging can mitigate these limitations, but requires cumulative incorporation of markers, which may lead to tissue exhaustion. Furthermore, the application of such strategies in large scale 3dimensional (3D) imaging is challenging. Here, we propose that 3D nuclear signatures from a DNA stain, DAPI, which could be incorporated in most experimental imaging, can be used for classifying cells in intact human kidney tissue. We developed an unsupervised approach that uses 3D tissue cytometry to generate a large training dataset of nuclei images (NephNuc), where each nucleus is associated with a cell type label. We then devised various supervised machine learning approaches for kidney cell classification and demonstrated that a deep learning approach outperforms classical machine learning or shape-based classifiers.Specifically, a custom 3D convolutional neural network (NephNet3D) trained on nuclei image volumes achieved a balanced accuracy of 80.26%. Importantly, integrating NephNet3D classification with tissue cytometry allowed in situ visualization of cell type classifications in kidney tissue. In conclusion, we present a tissue cytometry and deep learning approach for in situ classification of cell types in human kidney tissue using only a DNA stain. This methodology is generalizable to other tissues and has potential advantages on tissue economy and non-exhaustive classification of different cell types.

show abstract

“…Habibzadeh et al [23] presented a classification model for WBCs based on both transfer learning and deep learning. The proposed method started with a pre-processing step, and then employed transfer learning for feature extraction.…”

Section: Deep-learning-based Methodsmentioning

confidence: 99%

“…Data augmentation consists of three operations: translation, reflection, and rotation. In translation, the images are shifted along the X-axes and Y-axes with selected values being randomly bounded by the interval [15][16][17][18][19][20][21][22][23][24][25]. In the reflection process, the images are mirrored along the vertical axis.…”

Section: First Classification Modelmentioning

confidence: 99%

Deep Transfer Learning in Diagnosing Leukemia in Blood Cells

2020

View full text Add to dashboard Cite

Leukemia is a fatal disease that threatens the lives of many patients. Early detection can effectively improve its rate of remission. This paper proposes two automated classification models based on blood microscopic images to detect leukemia by employing transfer learning, rather than traditional approaches that have several disadvantages. In the first model, blood microscopic images are pre-processed; then, features are extracted by a pre-trained deep convolutional neural network named AlexNet, which makes classifications according to numerous well-known classifiers. In the second model, after pre-processing the images, AlexNet is fine-tuned for both feature extraction and classification. Experiments were conducted on a dataset consisting of 2820 images confirming that the second model performs better than the first because of 100% classification accuracy.Computers 2020, 9, 29 2 of 12 and classification. However, the success of each step depends on the success of the preceding step. For example, the success of classification depends on the success of the preceding feature extraction, which itself depends on the success of the preceding segmentation. Hence, high classification accuracy requires the success of all steps, each of which is non-trivial and problem-dependent [1,7].Recently, deep learning achieved many breakthroughs in different fields such as computer vision, natural language processing, and object recognition. Deep neural networks, such as convolutional neural networks (CNNs), can be used effectively to build computer-aided diagnostic systems. However, the design and training of deep neural networks are non-trivial and time-consuming tasks. Hence, instead of building a deep neural network from scratch, we use the concept of transfer learning, in which a deep network that achieved success in solving a certain problem is tuned to solve another problem.This paper proposes two classification models that are based on transfer learning and can distinguish between healthy and unhealthy blood smear images with high accuracy. These models employ AlexNet, which is a deep CNN that achieved huge success in the image classification challenge, ImageNet 2012.The remaining sections of this paper are arranged as follows: Section 2 covers some of the traditional and end-to-end-based methods described in the literature. Section 3 presents our two proposed classification models. Section 4 discusses their implementation in our experiments. Section 5 discusses the results obtained. Finally, Section 6 concludes the paper.

show abstract

Automatic white blood cell classification using pre-trained deep learning models: ResNet and Inception

Cited by 155 publications

References 12 publications

Improved White Blood Cells Classification based on Pre-trained Deep Learning Models

Improved White Blood Cells Classification based on Pre-trained Deep Learning Models

In situclassification of cell types in human kidney tissue using 3D nuclear staining

Deep Transfer Learning in Diagnosing Leukemia in Blood Cells

Contact Info

Product

Resources

About