Peripheral Blood Smears Examination by Artificial Intelligence: Comparison
View Latest Version
Please note this is a comparison between Version 2 by Lindsay Dong and Version 1 by Mohamad Abou Ali.

Artificial intelligence (AI) has emerged as a cutting-edge tool, simultaneously accelerating, securing, and enhancing the diagnosis and treatment of patients. An exemplification of this capability is evident in the analysis of peripheral blood smears (PBS). In university medical centers, hematologists routinely examine hundreds of PBS slides daily to validate or correct outcomes produced by advanced hematology analyzers assessing samples from potentially problematic patients. This process may logically lead to erroneous PBC readings, posing risks to patient health. AI functions as a transformative tool, significantly improving the accuracy and precision of readings and diagnoses.

  • deep learning (DP)
  • blood cell classification
  • “Naturalize” technique
  • %MCEPASTEBIN%

1. Introduction

Hematopoiesis, the remarkable process responsible for blood cell formation, is orchestrated by a hierarchy of specialized cells. At its core are hematopoietic stem cells, the ultimate architects of this symphony. These versatile cells possess the unique ability to self-renew and differentiate into various lineages. From them, progenitor cells emerge, committed to specific blood cell types like red blood cells, white blood cells, and platelets. Progenitor cells then give rise to precursor cells, which exhibit more specialized traits and characteristics. Finally, precursor cells mature into fully functional blood cells, capable of carrying out their vital roles in oxygen transport, immune defense, and clotting. The presence of precursor cells in the bloodstream is essential to maintain a dynamic reservoir, ready to respond to the body’s ever-changing demands for blood cells, ensuring a constant supply to sustain life and preserve health [1].
The transition from promyelocyte to the differentiated granulocytes—neutrophils, eosinophils, and basophils—constitutes a pivotal and intricately regulated process in hematopoiesis. This maturation journey encompasses distinct phases, each characterized by unique morphological and functional features. Following the promyelocyte stage, myelocytes emerge as granule-containing precursors, evolving into metamyelocytes, which display a progressive transformation in nuclear morphology. Subsequently, the cells progress to the band cell stage, marked by a characteristic U-shaped or horseshoe-shaped nucleus. Finally, the culmination of this finely orchestrated process results in the development of fully mature neutrophils, eosinophils, and basophils, each armed with specialized functions crucial for immune surveillance and response. This sequential progression underscores the intricacy of granulopoiesis [1], contributing to the generation of a diverse and highly specialized cellular arsenal essential for the maintenance of immune homeostasis.
Granulopoiesis [1] refers to the process of formation and maturation of granulocytes, which are a type of white blood cell characterized by the presence of granules in their cytoplasm. Granulocytes include neutrophils, eosinophils, and basophils, each playing a distinct role in the immune system. Granulopoiesis takes place in the bone marrow, where hematopoietic stem cells differentiate and undergo a series of stages to give rise to mature granulocytes. The process involves the development and specialization of cells through various stages, such as myeloblasts, promyelocytes, myelocytes, metamyelocytes, and finally, the release of mature granulocytes into the bloodstream. Granulocytes play a crucial role in the body’s defense against infections, allergic reactions, and other immune responses.
Figure 1 offers a visually compelling depiction of granulopoiesis, showcasing the remarkable progression from promyelocyte to the ultimate maturation of neutrophils, eosinophils, and basophils. This visual narrative not only illuminates the intricacies of their development in the bone marrow but also underscores their subsequent presence in the peripheral blood and various tissues. The orchestrated journey depicted underscores the dynamic nature of these immune sentinels as they transition from the confines of the bone marrow into the bloodstream and tissues, where they play pivotal roles in safeguarding the body against infections and maintaining immune homeostasis.
Algorithms 16 00562 g001
Figure 1.
Enchanting glimpse into granulopoiesis.
A peripheral blood smear is a microscopic window into hematopoiesis, offering a quick and insightful view of blood cell types and any abnormalities, crucial for diagnosing and monitoring hematological conditions [2].
In the realm of hematology, the meticulous examination of peripheral blood smears is vital for diagnosing blood disorders and guiding treatment Hematologists shoulder the burden of this labor-intensive manual process, scrutinizing countless blood cells with unwavering attention amidst a high workload and constant distractions. Their dedication is essential for precise diagnostics and patient care, given the criticality of the results they deliver [2].
However, the field of hematology has witnessed a transformative evolution through deep learning, a subset of artificial intelligence. This advancement automates peripheral blood smear analysis, alleviating the challenges faced by hematologists. Deep learning algorithms swiftly process blood cells, identifying subtle abnormalities and providing rapid, consistent results. This automation eases the workload, reduces human error, and empowers healthcare experts to focus on intricate cases [3].
As technology continues to advance, the fusion of deep learning and peripheral blood smear analysis promises to revolutionize blood disorder diagnosis and management, enhancing patient care outcomes [3].

2. Peripheral Blood Smears Examination by Artificial Intelligence

Within the realm of machine learning, the conventional approach involved the manual extraction of image features followed by classification. The advent of deep learning revolutionized this process by automating image classification, particularly impactful in blood cell analysis. Previous studies primarily concentrated on five white blood cell (WBC) types: neutrophils, eosinophils, basophils, lymphocytes, and monocytes. Jung et al. [13][4] introduced W-Net, a CNN-based model for white blood cell (WBC) classification, achieving 97% accuracy with 10-fold cross-validation. Their work focused on classifying five WBC types: neutrophils, eosinophils, basophils, lymphocytes, and monocytes. Sahlol et al. [14][5] combined VGG-16 and a feature reduction algorithm (SESSA) to achieve 95.67% accuracy for WBC leukemia image classification. They categorized WBCs into five classes. Almezhghwi et al. [15][6] used ImageNet pre-trained architectures (VGG, ResNet, DenseNet) and data augmentation, with DenseNet-169 achieving 98.8% accuracy. Their study involved the classification of five WBC types. Tavakoli et al. [16][7] developed a segmentation algorithm and used SVM for WBC classification, achieving high accuracy in multiple datasets. They focused on five WBC types. Chen et al. [17][8] proposed a hybrid deep model combining ResNet and DenseNet with a spatial and channel attention module (SCAM), outperforming previous methods. They worked with datasets containing five WBC types. Katar et al. [18][9] applied transfer learning with ImageNet models, with MobileNet-V3-Small achieving 98.86% accuracy. They classified five WBC types. Nahzat et al. [19][10] designed a CNN-based model using the Kaggle BCCD dataset, achieving competitive results. They also focused on five WBC types. Heni et al. [20][11] introduced the EK-Means method for WBC image segmentation, achieving a validation accuracy of 96.24% with VGG-19. They categorized five WBC types. Ziquan Zhu [21,22][12][13] presented DLBCNet models that used ResNet-50 for feature extraction and achieved impressive accuracy. They worked with datasets containing five WBC types. Other groups of researchers [23,24,25,26,27,28][14][15][16][17][18][19] worked on the classification of 8 blood classes in the the PBC dataset [4][20]. Table 1 summarizes the work of those groups.
Table 1.
Previous works on the classification of 8 blood classes of the PBC dataset.
Paper Year Used Model Classes Accuracy (%) Precision (%) Recall (%) F1-Score (%)
[23][14] 2019 Fine-Tuned VGG-16 8 96.20 97.00 96.00 97.00
[24][15] 2020 ShuffleNet 8 97.94 97.94 97.94 97.94
[25][16] 2021 BloodCaps 8 99.30 99.17 99.16 99.88
[26][17] 2021 Ensemble ResNet-50-2 and VGG-19 8 99.51 99.47 99.58 99.93
[27][18] 2023 CNN 8 99.91 99.77 99.60 99.60
[28][19] 2023 Mask R-CNN 8 99.31 97.25 97.37 97.31

The “Naturalize” technique directly tackles two prominent challenges in deep learning: data insufficiency and class imbalance. In the realm of deep learning, the quality and balance of data significantly impact model performance. “Naturalize” effectively addresses these challenges by generating high-quality blood cell samples. This innovative approach substantially enhances the performance of blood cell classification, pushing the boundaries of deep learning in blood cell analysis. Not only does it improve accuracy, but it also ensures robustness and reliability when handling diverse and imbalanced blood cell classes.

References

  1. McKenzie, S.B.; Williams, L. Clinical Laboratory Hematology, 3rd ed.; Pearson: Upper Saddle River, NJ, USA, 2014.
  2. Rodak, B.F.; Carr, J.H. Clinical Hematology Atlas, 4th ed.; Saunders: Maryland Heights, MO, USA, 2012.
  3. Al-qudah, R.; Suen, C.Y. Peripheral blood smear analysis using deep learning: Current challenges and future directions. In Computational Intelligence and Image Processing in Medical Applications; World Scientific: Singapore, 2022; pp. 105–118.
  4. Jung, C.; Abuhamad, M.; Alikhanov, J.; Mohaisen, A.; Han, K.; Nyang, D. W-Net: A CNN-based architecture for white blood cells image classification. arXiv 2019, arXiv:1910.01091.
  5. Sahlol, A.T.; Kollmannsberger, P.; Ewees, A.A. Efficient classification of white Blood Cell Leukemia with improved swarm optimization of deep features. Sci. Rep. 2020, 10, 2536.
  6. Almezhghwi, K.; Serte, S. Improved classification of white blood cells with the generative adversarial network and deep convolutional neural network. Comput. Intell. Neurosci. 2020, 2020, 6490479.
  7. Tavakoli, S.; Ghaffari, A.; Kouzehkanan, Z.M.; Hosseini, R. New segmentation and feature extraction algorithm for classification of white blood cells in peripheral smear images. Sci. Rep. 2021, 11, 19428.
  8. Chen, H.; Liu, J.; Hua, C.; Feng, J.; Pang, B.; Cao, D.; Li, C. Accurate classification of white blood cells by coupling pre-trained ResNet and DenseNet with SCAM mechanism. BMC Bioinform. 2022, 23, 282.
  9. Katar, O.; Kilinçer, İ.F. Automatic classification of white blood cells using pre-trained deep models. Sak. Univ. J. Comput. Inf. Sci. 2022, 5, 462–476.
  10. Nahzat, S. White Blood Cell Classification Using Convolutional Neural Network. Technol. Eng. Res. 2022, 3, 32–41.
  11. Heni, A. Blood Cells Classification Using Deep Learning with customized data augmentation and EK-means segmentation. J. Theor. Appl. Inf. Technol. 2023, 101, 1162–1173. Available online: https://www.jatit.org/volumes/Vol101No3/11Vol101No3.pdf (accessed on 10 November 2020).
  12. Zhu, Z.; Wang, S.-H.; Zhang, Y.-D. ReRNet: A deep learning network for classifying blood cells. Technol. Cancer Res. Treat. 2023, 22, 15330338231165856.
  13. Zhu, Z.; Ren, Z.; Lu, S.; Wang, S.; Zhang, Y. DLBCNet: A deep learning network for classifying blood cells. Big Data Cogn. Comput. 2023, 7, 75.
  14. Acevedo, A.; Alférez, S.; Merino, A.; Puigví, L.; Rodellar, J. Recognition of peripheral blood cell images using convolutional neural networks. Comput. Methods Progr. Biomed. 2019, 180, 1050209.
  15. Ucar, F. Deep learning approach to cell classificatio in human peripheral blood. In Proceedings of the 2020 5th International Conference on Computer Science and Engineering (UBMK), Diyarbakir, Turkey, 9–11 September 2020.
  16. Long, F.; Peng, J.-J.; Song, W.; Xia, X.; Sang, J. BloodCaps: A capsule network based model for the multiclassification of human peripheral blood cells. Comput. Methods Progr. Biomed. 2021, 202, 105972.
  17. Gavas, E.; Olpadkar, K. Deep CNNs for peripheral blood cell classification. arXiv 2021, arXiv:2110.095082.
  18. Asghar, R.; Kumar, S.; Hynds, P.; Mahfooz, A. Automatic classification of blood cell images using convolutional neural network. arXiv 2023, arXiv:2308.06300.
  19. Atici, H.; Kocer, H.E. Mask R-CNN based segmentation and classification of blood smear images. Gazi Muhendis. Bilim. Derg. 2023, 9, 128–1433.
  20. Acevedo, A.; Merino, A.; Alférez, S.; Molina, Á.; Boldú, L.; Rodellar, J. A dataset of microscopic peripheral blood cell images for development of automatic recognition systems. Data Brief 2020, 30, 105474.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/)
Video Production Service
Feedback