White Blood Cell Segmentation and Classification Using Deep Learning Coupled with Image Processing Technique

Huynh, Hieu Trung; Dat, Vo Vuong Thanh; Anh, Ha Bao

doi:10.1007/978-981-16-8062-5_27

Cited by 2 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Information could travel through the encoder portion without having to be transformed into features. This means that the CNN model could use the information in the features of the shallower regions as well as the knowledge it learned through being compelled to construct features in the deep part [46]. Figure 5 illustrates an example UNet structure.…”

Section: Methodsmentioning

confidence: 99%

Comprehensive data analysis of white blood cells with classification and segmentation by using deep learning approaches

Özcan,

Uyar,

Karayeğen

2024

Cytometry Pt A

View full text Add to dashboard Cite

Deep learning approaches have frequently been used in the classification and segmentation of human peripheral blood cells. The common feature of previous studies was that they used more than one dataset, but used them separately. No study has been found that combines more than two datasets to use together. In classification, five types of white blood cells were identified by using a mixture of four different datasets. In segmentation, four types of white blood cells were determined, and three different neural networks, including CNN (Convolutional Neural Network), UNet and SegNet, were applied. The classification results of the presented study were compared with those of related studies. The balanced accuracy was 98.03%, and the test accuracy of the train‐independent dataset was determined to be 97.27%. For segmentation, accuracy rates of 98.9% for train‐dependent dataset and 92.82% for train‐independent dataset for the proposed CNN were obtained in both nucleus and cytoplasm detection. In the presented study, the proposed method showed that it could detect white blood cells from a train‐independent dataset with high accuracy. Additionally, it is promising as a diagnostic tool that can be used in the clinical field, with successful results in classification and segmentation.

show abstract

Section: Methodsmentioning

confidence: 99%

Comprehensive data analysis of white blood cells with classification and segmentation by using deep learning approaches

Özcan,

Uyar,

Karayeğen

2024

Cytometry Pt A

View full text Add to dashboard Cite

show abstract

“…The highest sensitivity of 99.4 % [7] was obtained where the method of TissueQuant was used to manage color alterations for the nuclei detection. The highest mean accuracy of 99.4 % [8] was obtained, using Thresholding method and Watershed algorithm. Color-based segmentation with active contour model.…”

Section: Literature Reviewmentioning

confidence: 96%

“…The proposed WBC segmentation approach by Hieu Trung Huynh et al [8], was an aggregation of Watershed algorithm and thresholding method. The WBCs or leukocyte types were labelled by a deep neural network-based model where the considered viewpoint reached the accuracy of mean classification for 5-class WBCs nucleus is 99.40 %, the least achieved accuracy for Monocytes is 98.60 % while the highest accuracy achieved for eosinophil is 99.80 % and 99.4 %, 99.6 %, and 99.2 % respectively for neutrophil, basophil, and lymphocyte.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Cucun Very Angkoso et al [8], Previously, intended an automated WBC nucleus segmentation method based on color-based segmentation using active contour model where the effectiveness of RGB, HSV, YC B C R, CieLab, and grayscale was analyzed, and the accuracy and specificity was found to be 99.38 % and 97.92 % respectively. A computer-aided method for identifying and distinguishing myeloma cells in bone marrow blurs was proposed by Sumit Kumar Das et al [11], where for recognition Mask-Recurrent CNN was used, and for detection Efficient Net B3 was used.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation and Classification of White Blood SMEAR Images using Modified CNN Architecture

Kumar,

Rawat

2024

Preprint

View full text Add to dashboard Cite

The classification and recognition of leukocytes or WBCs in blood stain images present a key role in the corresponding diagnosis of specific diseases, such as leukemia, tumor, hematological disorders, etc. The segmentation & classification of WBCs nucleus sets a solid ground for automation in the calculation and recognition of WBCs related disorders. However, it is complicated by reason to causes such as background obscurity and alterations in occurrence generated by histological staining conditions. For improving the accuracy of segmentation of WBC images, we intend to consider a deep learning network using microscopic images of white blood cell. Furthermore, the functioning of the intended design will be compared with other modern methods. By the end of this study a successful model classifying various nucleus morphologies such as Basophil, Eosinophil, Lymphocyte, Monocyte and Neutrophil was obtained where overall test accuracy achieved was 97.0 % for VGGNet classifier and 94.0 % for MobileNet V2 classifier.

show abstract

White Blood Cell Segmentation and Classification Using Deep Learning Coupled with Image Processing Technique

Cited by 2 publications

References 24 publications

Comprehensive data analysis of white blood cells with classification and segmentation by using deep learning approaches

Comprehensive data analysis of white blood cells with classification and segmentation by using deep learning approaches

Segmentation and Classification of White Blood SMEAR Images using Modified CNN Architecture

Contact Info

Product

Resources

About