Lam Görüntülerinde Görü Dönüştürücü Tabanlı Kan Grubu Sınıflandırması

Abstract

Özet: Kan, insan vücudunda oksijen ve besin taşınmasını sağlayan temel bir sıvıdır. Kazalar, kalıcı hematolojik hastalıklar veya cerrahi prosedürler durumunda, kaybedilen kan hacminin geri kazanılması için kan transfüzyonları zorunludur. Bu nedenle, herhangi bir kan transfüzyonundan önce hastanın kan grubunun belirlenmesi zorunludur. Kan grubu tespitinin güncel uygulamalarında, kan dolaşımındaki antijenlerin çökelmesini kolaylaştıran test serumlarının (Anti-A, Anti-B, Anti-D) kullanımı yaygın bir uygulama haline gelmiştir. Kan grupları, antijenlerin çökelmesine göre antijenlerin varlığının tespit edilmesiyle belirlenir. Slaytlardaki çökelmenin gözlemlenmesi laboratuvar uzmanı tarafından gerçekleştirilir. Ancak, bu gözlem süreci zorlu ve zaman alıcı olabilir ve uzun süreler boyunca sürekli dikkat gerektirebilir. Özetle, makine görüsü güncel otomatikleştirilmiş yaklaşımlarda yaygın bir araç olarak ortaya çıkmış ve bu süreçler için uzman yükünü azaltmıştır. Makine görüsü sürekli gelişen bir alan olmakla birlikte kullanılan en güncel yöntemlerden biri de görü dönüştürücülerinin kullanımıdır. Sunulan çalışmanın amacı, kan gruplarının ayrımı amacıyla görü dönüştürücülerini kullanarak kan gruplarının yüksek doğrulukta sınıflandırılmasını elde etmektir. Deneysel çalışmaların bulguları, görü dönüştürücülerinin kan gruplarının sınıflandırılmasında dikkate değer bir başarıya sahip olduğunu göstermiştir. Öte yandan, deneysel bulgular, Uyarlamalı Moment Tahmini optimizatörünün görü dönüştürücüleriyle birlikte kullanıldığında daha iyi sınıflandırma performansı elde ettiğini göstermiştir.

Keywords

• Kan Grubu
• Görüntü İşleme
• Sınıflandırma
• Görü Dönüştürücü

Vision Transformer-Based Blood Group Classification on Slide Images

Abstract

Blood is an essential fluid in the human body, enabling the transport of oxygen and nutrients. In cases of accidents, persistent hematological illnesses, or surgical procedures, blood transfusions are imperative for the restoration of lost blood volume. Therefore, it is imperative to ascertain the patient's blood type prior to any blood transfusion. In contemporary applications of blood group determination, the utilization of test serums (Anti-A, Anti-B, Anti-D) that facilitates the precipitation of antigens within the bloodstream has become a prevailing practice. Blood groups are determined by detecting the presence of antigens according to the precipitation of antigens. The observation of precipitation on slides is conducted by the laboratory specialist. However, this observation process can be arduous and time-consuming, requiring sustained attention for extended periods. Consequently, machine vision has emerged as a prevalent tool in contemporary automated approaches, mitigating the expert load required for these processes. Machine vision is a field that is constantly evolving, and one of the most current methods employed is the use of vision transformers. The objective of the present study was to achieve high-accuracy classification of blood groups by employing vision transformers for the purpose of discrimination. The findings of experimental studies have indicated the notable efficacy of vision transformers in the classification of blood groups. Furthermore, experimental findings have indicated that the Adaptive Moment Estimation optimizer when employed in conjunction with vision transformers attains better classification performance.

Keywords

• Blood Group
• Image Processing
• Classification
• Vision Transformer

References

1. [1] Skull, A. 2022. Circulation - anatomy, physiology and pathophysiology. ss 1-86. McGloin, S., Skull, A. ed. 2022. Principles of Acute Care Nursing, SAGE Publications, UK, 280s.
2. [2] Roback, J. D., Grossman, B. J., Harris, T., Hillyer C. D. 2011. Technical Manual. 17th edition. American Association of Blood Banks (AABB). U.S.A., 1078s.
3. [3] Harmening, D. M. 2012. Modern Blood Banking & Transfusion Practices. 6th edition. F.A. Davis Company. U.S.A., 672s.
4. [4] Malomgre, W., Neumeister, B. 2009. Recent and future trends in blood group typing. Analytical and Bioanalytical Chemistry, 393, 1443-1451.
5. [5] Okroi, M., McCarthy, L. 2010. The original blood group pioneers: the Hirszfelds. Transfusion Medicine Reviews, 24(3), 244-246.
6. [6] Landsteiner, K., Wiener, A. S. 1940. An Agglutinable Factor in Human Blood Recognized by Immune Sera for Rhesus Blood. Experimental Biology and Medicine, 43(1), 223-223.
7. [7] Şentuna, C. 1982. Rh Gen Frekansları Yönünden Türkiye'nin Yeri. Ankara Üniversitesi Dil ve Tarih-Coğrafya Fakültesi Dergisi, 30, 153-179.
8. [8] Ferraz, A., Carvalho, V., Machado, J. 2017. Determination of human blood type using image processing techniques. Measurement, 97, 165-173.

9. [9] Shaban, S. A., Elsheweikh, D. L. 2022. Blood Group Classification System Based on Image Processing Techniques. Intelligent Automation & Soft Computing, 31(2), 817-834.
10. [10] Mankar, J., Neve, S., Parkhe, M., Kumawat, P., Kale, N. R. 2021. Automated Blood Group Detection System Using Image Processing. International Journal of Advance Research and Innovative Ideas in Education, 7(3), 3237-3244.
11. [11] Malhotra, A., Chethana, N., Nagapranitha, D. R., Anand, S., Shruthi, B. 2021. Automated Blood Group Determination Using Image Processing Techniques with Integration of Raspberry Pi. Journal of Emerging Technologies and Innovative Research, 8(6), 954-965.
12. [12] Jayakumar, P., Padmanabhan, S., Suthendran, K., Kumar, Y. N., Sujith, M. 2020. Identification and Analysis of Blood Group with Digital Microscope Using Image Processing. IOP Conference Series: Materials Science and Engineering, 923, 012013.
13. [13] Ferraz, A., Soares, F., Carvalho, V. 2013. A Prototype for Blood Typing Based on Image Processing. SENSORDEVICES 2013: The Fourth International Conference on Sensor Device Technologies and Applications, 25-31 August, Barcelona, 139-144.
14. [14] Ayan, E., Yıldırım, E. K. 2016. Real Time Blood Type Determination by Gel Test Method on an Embedded System. International Journal of Applied Mathematics, Electronics and Computers, 4, 412-415.
15. [15] Atıcı, H., Koçer, H. E., Kader, S. 2020. Dijital Görüntüler Kullanılarak Kan Grubunun Görüntü İşleme Tabanlı Tespiti. BŞEÜ Fen Bilimleri Dergisi, 7(2), 649-659.
16. [16] Dong, Y., Chen, N., Fu, W., Liu, M., Zhou, Z., Chen, S. 2017. ABO Blood Group Detection Based on Image Processing Technology. 2017 2nd International Conference on Image, Vision and Computing, 2-4 June, Chengdu, China, 655-659.
17. [17] Dhande, A., Bhoir, P., Gade, V. 2018. Identifying the blood group using Image Processing. International Research Journal of Engineering and Technology, 5(3), 2639-2642.
18. [18] Ravindran, G., Titus, T. J., Pravin, M., Pandiyan, P. 2017. Determination and Classification of Blood Types using Image Processing Techniques. International Journal of Computer Applications, 157(1), 12-16.
19. [19] Chandra, K. B. S., Madgula, V. B., Raghavaraju, D. 2023. Prototype for Blood Typing Based on Image Processing. Advanced Engineering Science, 55(4), 1-11.
20. [20] Rishitha, G. S., Jerusha, D. S., Shehanaz, S. 2022. Blood Detection Using Image Processing. International Journal of Creative Research Thoughts, 10(5), 365-369.
21. [21] Odeh, N., Toma, A., Mohammed, F., Dama, Y., Oshaibi, F., Shaar, M. 2021. An Efficient System for Automatic Blood Type Determination Based on Image Matching Techniques. Applied Sciences, 11, 5225-5252.
22. [22] Rosales, M. A., de Luna, R. G. 2022. Computer-Based Blood Type Identification Using Image Processing and Machine Learning Algorithm. Journal of Advanced Computational Intelligence and Intelligent Informatics, 26(5), 698-705.
23. [23] Dannana, S., Prasad, D. Y. V. 2022. Blood group detection using ML classifier. Journal of Health Sciences, 6(S1), 4395–4408.
24. [24] Mahmood, M. F. 2024. Recognition And Categorization of Blood Groups by Machine Learning and Image Processing Method. Innovative Biosystems and Bioengineering, 8(2), 53-68.
25. [25] Ferraz, A., Brito, J. H., Carvalho, V., Machado, J. 2017. Blood type classification using computer vision and machine learning. Neural Computing and Applications, 28, 2029-2040.
26. [26] Balaji, B., Jeyasakthi, R., Julius Fusic, S., Rishwana, M., Swathilakshmi, P. R. K., Reshma, K. K. 2021. A novel approach of classifying ABO blood group image dataset using deep learning algorithm. International Conference on Computational Performance Evaluation, 1-3 December, Meghalaya, India, 393-398.
27. [27] Titus, A., Devi, K. M., Divya, G., Nimmagadda, P., Shankar, S. V. 2023. A Systematic Procedure to Identify Human Blood Groups by using Image Processing Assisted Learning Principle. International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, 14-15 December, Chennai, India, 1-6.
28. [28] Aboubaker, C. D. 2023. Blood Group Prediction Using Deep Learning. Kasdi Mebah University, Computer Science Department, Master Thesis, 70s, Algeria.
29. [29] Shen, R., Wen, J., Zhu, P. 2023. Blood Group Interpretation Algorithm Based on Improved AlexNet. Electronics, 12, 2608-2622.
30. [30] Devlin, J., Chang, M., Lee, K., Toutanova, K. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. North American Chapter of the Association for Computational Linguistics, 1, 4171-4186.
31. [31] Vaswani, A., Ramachandran, P., Srinivas, A., Parmar, N., Hechtman, B., Shlens, J. 2021. Scaling local self-attention for parameter efficient visual backbones. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 20-25 June, Nashville, U.S.A., 12894-12904.
32. [32] Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. International Conference on Learning Representations. International Conference on Learning Representations, 26 April – 1 May, Virtual, 1-22.
33. [33] Minor Project 5th Semester. 2024. Blood Group Detection Dataset. http://universe.roboflow.com/minor-project-5th-semester/blood-group-detection-4yvdx (Erişim Tarihi: 01.03.2025).
34. [34] Shorten, A., Khoshgoftaar T. M. 2019. A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6(60), 1-48.
35. [35] Amballa, D. P. 2022. Automated Blood Group Identification using Machine Learning and Deep Learning: A Novel Approach for Laboratory Settings. International Journal of Science and Research, 11(10), 1390-1393.
36. [36] Wilson, A. C., Roelofs, R., Stern, M., Srebro, N., Recht, B. 2017. The marginal value of adaptive gradient methods in machine learning. 31st Conference on Neural Information Processing Systems, 4-9 December, U.S.A., 1-11.
37. [37] Choi, D., Shallue, C. J., Nado, Z., Lee, J., Maddison, C. J., Dahl, G. E. 2019. On empirical comparisons of optimizers for deep learning. arXiv, 1-27.
38. [38] Neyshabur, B. 2020. Towards Learning Convolutions from Scratch. 34th Conference on Neural Information Processing Systems, 6-12 December, 1-11.