AKUT LENFOBLASTİK LÖSEMİ HÜCRELERİNİN YAPAY ZEKA İLE SINIFLANDIRILMASI

Öz

Olgunlaşmamış lenfoblastların (kanserli hücreler) lenfositlere (kanserli olmayan hücreler) morfolojik benzerliği Akut Lenfoblastik Lösemi kanserinin tespitinde patologlar için zorlu bir problemdir. Benzer bir desene sahip olan bu hücreler, hastalığın teşhisi sırasında çeşitli hatalara neden olabilmektedir. Bu sebepten çalışma kapsamında kanserli ve kanserli olmayan hücreler 3 farklı yapay zeka yaklaşımı kullanılarak tespit edilmiştir. İlk yaklaşımda Evrişimsel Sinir Ağları 4 farklı mimaride eğitilerek sınıflandırma işlemi gerçekleştirilmiştir. İkinci yaklaşımda, özellik çıkarıcı olarak CNN modelinin evrişim katmanı, sınıflandırıcı olarak ise Destek Vektör Makinesi, Naive Bayes ve Rastgele Orman algoritmaları birleştirilerek hibrit bir yaklaşım sunulmuştur. Önerilen ikinci yaklaşım eğitilerek sınıflandırma işlemleri gerçekleştirilmiştir. Üçüncü yaklaşımda ise transfer öğrenme süreci ile ResNet50 ve VGG16 ağları kullanılarak sınıflandırma işlemi gerçekleştirilmiştir. Tüm deneylerde modellerdeki hiperparametre ve veri setleri değişikliklerinin performans üzerindeki etkileri incelenmiştir. Bu üç yaklaşımla elde edilen sonuçlar Doğruluk, Kesinlik, Geri Çağırma, F-skor ve AUC performans ölçüleri kullanılarak karşılaştırılmış ve en başarılı sonuçların Dataset3 kullanılarak Yaklaşım1 ile elde edildiği tespit edilmiştir.

Anahtar Kelimeler

• Yapay Zeka
• Makine Öğrenimi
• Kanser Tespiti

CLASSIFICATION OF ACUTE LYMPHOBLASTIC LEUKEMIA CELLS USING ARTIFICIAL INTELLIGENCE

Öz

Due to the morphological similarity between immature lymphoblasts (cancerous cells) to lymphocytes (non-cancerous cells), detecting Acute Lymphoblastic Leukemia poses a significant challenge for pathologists. These cells, which exhibit a similar pattern, can lead to various errors during the diagnosis of the disease. In this study, the cancerous and non-cancerous cells were classified using 3 different artificial intelligence approaches. In the first approach, the classification process was carried out by training Convolutional Neural Networks in 4 different architectures. In the second approach, a hybrid approach was proposed by combining the convolution layer of the CNN model as the feature extractor with the Support Vector Machine, Naive Bayes and Random Forest algorithms as the classifier. The classification processes were carried out by training the proposed second approach. In the third approach, the classification process was performed using transfer learning process and ResNet50 and VGG16 networks. In all experiments, the effects of hyper-parameter and dataset changes on model performance were also examined. The results obtained by these three approaches were compared using the Accuracy, Precision, Recall, F-score, and AUC performance measures. It was determined that the most successful results were obtained with the 1st approach using the Dataset3.

Anahtar Kelimeler

• Artificial Intelligence
• Machine Learning
• Cancer Detection

Kaynakça

1. Anonymous. (2023, Nov. 10). Diagram showing the cell that ALL starts [Online]. Available:https://en.wikipedia.org/wiki/Acute_lymphoblastic_leukemia
2. Banik, P. P., Saha, R. and Kim, K. D., 2019. Fused Convolutional Neural Network for White Blood Cell Image Classification, In 2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pp. 238-240 , Okinawa, Japan.
3. Bhuiyan, M. N. Q., Rahut, S. K., Tanvir, R. A. and Ripon, S., 2019. Automatic Acute Lymphoblastic Leukemia Detection and Comparative Analysis from Images In 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 1144-1149, Paris, France, 2019.
4. Clark, K. , Vendt, B. , Smith, K., Freymann, J., Kirby, J., Koppel, P., Moore, S., Phillips, S., Maffitt, D., Pringle, M., Tarbox, L. and Prior, F., 2013. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. Journal of Digital Imaging, vol. 26, no. 6, pp. 1045-1057.
5. Duggal, R., Gupta, A. & Gupta, R., 2016b. Segmentation of overlapping/touching white blood cell nuclei using artificial neural networks, CME Series on Hemato - Oncopathology, All India Institute of Medical Sciences (AIIMS), New Delhi, India.
6. Duggal, R., Gupta, A., Gupta, R. and Mallick, P., 2017. SD-layer: stain deconvolutional layer for CNNs in medical microscopic imaging, In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 435-443, QC, Canada.
7. Duggal, R., Gupta, A., Gupta, R., Wadhwa, M. & Ahuja, C., 2016a. Overlapping cell nuclei segmentation in microscopic images using deep belief networks, In Proceedings of the Tenth Indian Conference on Computer Vision, Graphics and Image Processing, Guwahati, India.
8. Global Cancer Observation. (2024, Jan. 29). International Agency for Research on Cancer [Online]. Available:https://gco.iarc.fr/today/en/dataviz/pie?mode=cancer&group_populations=1&age_end=2

9. Heffner, S., Colgan, O. and Doolan, C. Digital Patology, [Online]. Available: https://www.leicabiosystems.com/pathologyleaders/digital-pathology/, Accessed on: April 5, 2021
10. Hu, J., Shen, L. & Sun, G., 2018. Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7132-7141.
11. Inaba, H., Greaves M. & Mullighan, C. G., 2013. Acute lymphoblastic leukaemia. The Lancet, vol. 381, no. 9881, pp. 1943-1955.
12. Jiang, H., Li, Z., Li, S. and Zhou, F., 2018. An Effective Multi-Classification Method for NHL Pathological Images, In 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 763-768, Miyazaki, Japan.
13. Karlik, B., and Olgac, A. V., 2011. Performance analysis of various activation functions in generalized MLP architectures of neural networks. International Journal of Artificial Intelligence and Expert Systems, 1(4), 111-122.
14. Kingma, D. P. and Ba, J., 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980
15. Kumar, S., Mishra, S. & Asthana, P., 2018. Advances in Computer and Computational Sciences (second edition), Springer, Singapore, pp. 655-670.
16. Madabhushi, A. (2009) Digital pathology image analysis: opportunities and challenges. Imaging in medicine, vol. 1, no.1, pp. 7-10.
17. Mourya S., Kant S., Kumar P., Gupta A., Gupta R. (2023, May. 5). ALL Challenge dataset of ISBI 2019 [Data set]. The Cancer Imaging Archive. [Online]. Available: https://www.cancerimagingarchive.net/collection/c-nmc-2019/
18. Oliveira, J. E. M. & Dantas, D. O., 2021. Classification of Normal versus Leukemic Cells with Data Augmentation and Convolutional Neural Networks. In VISIGRAPP (4: VISAPP), pp. 685-692.
19. PDQ® Pediatric Treatment Editorial Board PDQ Childhood Acute Lymphoblastic Leukemia Treatment. Bethesda, MD: National Cancer Institute, [Online]. Available: https://www.cancer.gov/types/leukemia/patient/child-all-treatment-pdq. , Accessed on: April. 10, 2021
20. Prellberg, J. & Kramer, O., 2019. Acute lymphoblastic leukemia classification from microscopic images using convolutional neural networks. In ISBI 2019 C-NMC Challenge: Classification in Cancer Cell Imaging, pp. 53-61, Springer, Singapore.
21. Selçuk, O. and Özen, F., 2015. Acute lymphoblastic leukemia diagnosis using image processing techniques. In 2015 23rd Signal Processing and Communications Applications Conference (SIU), pp. 803-806, Malatya, Turkey.
22. Si, J., Harris, S. L. & Yfantis, E., 2018. A Dynamic ReLU on Neural Network. In 2018 IEEE 13th Dallas Circuits and Systems Conference (DCAS), pp. 1-6, IEEE.
23. Sibi, P., Jones, S. A. and Siddarth, P., 2013. Analysis of different activation functions using back propagation neural networks. Journal of Theoretical and Applied Information Technology, 47(3), 1264-1268.
24. Sipes, R. and Li, D., 2018. Using Convolutional Neural Networks for Automated Fine-Grained Image Classification of Acute Lymphoblastic Leukemia. In 2018 3rd International Conference on Computational Intelligence and Applications (ICCIA), pp. 157-161, Hong Kong, China.
25. Sipes, R. and Li, D., 2018. Using Convolutional Neural Networks for Automated Fine-Grained Image Classification of Acute Lymphoblastic Leukemia, In 2018 3rd International Conference on Computational Intelligence and Applications (ICCIA), pp. 157-161, Hong Kong, China.
26. Stursa D. and Dolezel, P., 2019. Comparison of ReLU and linear saturated activation functions in neural network for universal approximation. In 2019 22nd International Conference on Process Control (PC19), pp. 146-151, IEEE.
27. Uzunhan, T. A. and Karakaş, Z., 2012. Çocukluk Çağı Akut Lenfoblastik Lösemisi. Çocuk Dergisi, vol. 12, no. 1, pp. 6-15.
28. Yazan, E. and Talu, M. F., 2017. Comparison of the stochastic gradient descent-based optimization techniques. In 2017 International Artificial Intelligence and Data Processing Symposium (IDAP). 1-5. IEEE.
29. Yöntem, A. & Bayram, İ., 2018. Çocukluk Çağında Akut Lenfoblastik Lösemi. Arşiv Kaynak Tarama Dergisi, vol. 27, no. 4, pp. 483-499.
30. Zhao, J., Zhang, M., Zhou, Z., Chu, J. and Cao, F. (2017) Automatic Detection and Classification of Leukocytes Using Convolutional Neural Networks, Medical & Biological Engineering & Computing, vol. 55, no. 8, pp. 1287-1301