A Decision Support System For Detecting Stage In Hodgkin Lymphoma Patients Using Artificial Neural Network and Optimization Algorithms

Abstract

Hodgkin-type lymphoma is a disease with unique histological, immunophenotypic, and clinical features. This disease occurs in nearly 30% of all lymphomas. Its treatable is high. However, the treatment plan is specified after the stage and risk status are determined. For this reason, it is an important process for doctors to decide on the stage of the disease correctly. Some of the data used for this decision are the patient's history, detailed physical examination, laboratory findings, imaging methods and bone marrow biopsy results. Hybrid FDG-PET is the other method used in the medical world. This method is used in diagnosis, evaluation of response given to treatment, staging and restaging process. However, it is radiation-based. Therefore it has the possibility of producing undesirable results in the future. In this study, an artificial intelligence-based computer-assisted decision support system is done to reduce the number of used medical methods and radiation exposure. Data were obtained from the NCBI-GEO dataset. The evaluation of these data, which contains missing values, is handled in two ways. Firstly, samples with missing values in the initial evaluation are deleted from the dataset. Then, these data are trained with “trainlm” function in artificial neural network architecture. However, reducing the error value of the estimates is important. For this, the artificial neural network architecture is retrained with the artificial bee colony algorithm, particle swarm optimization algorithm and invasive weed algorithm, respectively. Secondly, the same operations are performed again on the dataset containing missing values. As a result of the training, the maximum performance was obtained for invasive weed and particle swarm optimization algorithms with 1,45547E+14 and 1,23103E+14 average error rates, respectively.

Keywords

• staging in hodgkin lymphoma
• artificial neural networks
• particle swarm optimization algorithm
• invasive weed optimization algorithm
• constructing hybrid structure for decision support system

References

1. [1] A. W. MD, A. Q. MD, A. Dasgupta ‘Hodgkin lymphoma - Chapter 14’, Hematology and Coagulation (Second Edition), pp. 217–225, 2020.
2. [2] Z. Abbasov, ‘Hodgkin Hastalığı Tanılı Hastaların Klinik, Laboratuar Bulguları ve Tedavi Sonuçlarının Değerlendirilmesi’, Uzmanlık Tezi, İstanbul Üniversitesi, 2017.
3. [3] T. Şahmaran and M. Bayburt, ‘Pozitron Emisyon Tomografi-Bilgisayar Tomografi (PET-BT) Uygulamalarında Hastanın Aldığı Radyasyon Dozunun Belirlenmesi’, Kafkas Univ. Inst. Nat. Appl. Sci. J., vol. 13, no. 1, pp. 58–63, 2020.
4. [4] S. Y. Aksoy and M. Halac, ‘Pediatrik Hodgkin lenfomalarda FDG PET/BT’, Turk Onkol. Derg., vol. 30, no. 4, pp. 240–251, 2015, doi: 10.5505/tjoncol.2015.1218.
5. [5] Ç. Soydal et al., ‘F-18 FDG PET/CT Practice Guideline in Oncology’, Nucl. Med. Semin., vol. 6, pp. 339–357, 2020, doi: 10.4274/nts.galenos.2020.0028.
6. [6] P. Ö. Kara, ‘Pediatrik Lenfomalarda PET_BT Görüntüleme’, Turkiye Klin. J Nucl Med-Special Top., vol. 3, no. 1, pp. 93–99, 2017.
7. [7] T. P. De Faria, M. Z. Do Nascimento, and L. G. A. Martins, ‘Understanding the multiclass classification of lymphomas from simple descriptors’, Proc. - 2021 Int. Conf. Comput. Sci. Comput. Intell. CSCI 2021, pp. 1202–1208, 2021, doi: 10.1109/CSCI54926.2021.00250.
8. [8] C. Lartizien, M. Rogez, E. Niaf, and F. Ricard, ‘Computer-aided staging of lymphoma patients with FDG PET/CT imaging based on textural information’, IEEE J. Biomed. Heal. Informatics, vol. 18, no. 3, pp. 946–955, 2014, doi: 10.1109/JBHI.2013.2283658.

9. [9] T. A. A. Tosta, M. Z. Do Nascimento, P. R. De Faria, and L. A. Neves, ‘Application of Evolutionary Algorithms on Unsupervised Segmentation of Lymphoma Histological Images’, Proc. - IEEE Symp. Comput. Med. Syst., pp. 89–94, 2017, doi: 10.1109/CBMS.2017.69.
10. [10] E. Michail, K. Dimitropoulos, T. Koletsa, I. Kostopoulos, and N. Grammalidis, ‘Morphological and textural analysis of centroblasts in low-thickness sliced tissue biopsies of follicular lymphoma’, 2014 36th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBC 2014, pp. 3374–3377, 2014, doi: 10.1109/EMBC.2014.6944346.
11. [11] M. Goncalves Ribeiro, L. Alves Neves, G. Freire Roberto, T. A. A. Tosta, A. S. Martins, and M. Z. Do Nascimento, ‘Analysis of the Influence of Color Normalization in the Classification of Non-Hodgkin Lymphoma Images’, 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 369–376, 2018, doi: 10.1109/SIBGRAPI.2018.00054.
12. [12] A. E. Nugroho, W. D. Lukito, I. Anshori, W. Adiprawita, H. A. Usman, and O. Husain, ‘CLAHE Performance on Histogram-Based Features for Lymphoma Classification using KNN Algorithm’, Proceeding 15th Int. Conf. Telecommun. Syst. Serv. Appl. TSSA 2021, 2021, doi: 10.1109/TSSA52866.2021.9768221.
13. [13] N. Hatipoglu and G. Bilgin, ‘Classification of Malignant Lymphoma Types Using Convolutional Neural Network’, 2020 Med. Technol. Congr., 2020.
14. [14] A. Ganguly, R. Das, and S. K. Setua, ‘Histopathological Image and Lymphoma Image Classification using customized Deep Learning models and different optimization algorithms’, 2020 11th Int. Conf. Comput. Commun. Netw. Technol. ICCCNT 2020, 2020, doi: 10.1109/ICCCNT49239.2020.9225616.
15. [15] A. I. Kamel, T. F. Taha Ali, and M. A. Tawab, ‘Potential impact of PET/CT on the initial staging of lymphoma’, Egypt. J. Radiol. Nucl. Med., vol. 44, no. 2, pp. 331–338, 2013, doi: 10.1016/j.ejrnm.2012.12.008.
16. [16] N. H. E. D. Behairy, T. A. Rafaat, A. S. E. D. El Nayal, and M. I. Bassiouny, ‘PET/CT in initial staging and therapy response assessment of early mediastinal lymphoma’, Egypt. J. Radiol. Nucl. Med., vol. 45, no. 1, pp. 61–67, 2014, doi: 10.1016/j.ejrnm.2013.11.009.
17. [17] A. Elsammak, ‘Clinical usefulness of PET-CT in staging, evaluation of treatment response and restaging of thoracic lymphoma’, Egypt. J. Radiol. Nucl. Med., vol. 48, no. 4, pp. 1073–1081, 2017, doi: 10.1016/j.ejrnm.2017.04.005.
18. [18] R. A. Elshafey, N. Daabes, and S. Galal, ‘FDG-PET/CT in re-staging of patients with non Hodgkin lymphoma and monitory response to therapy in Egypt’, Egypt. J. Radiol. Nucl. Med., vol. 49, no. 4, pp. 1076–1082, 2018, doi: 10.1016/j.ejrnm.2018.06.003.
19. [19] M. Panebianco et al., ‘Comparison of 18F FDG PET-CT AND CECT in pretreatment staging of adults with Hodgkin’s lymphoma’, Leuk. Res., vol. 76, pp. 48–52, 2019, doi: 10.1016/j.leukres.2018.11.018.
20. [20] D. Albano et al., ‘Diagnostic and Clinical Impact of Staging 18F-FDG PET/CT in Mantle-Cell Lymphoma: A Two-Center Experience’, Clin. Lymphoma, Myeloma Leuk., vol. 19, no. 8, pp. e457–e464, 2019, doi: 10.1016/j.clml.2019.04.016.
21. [21] ‘NCBI Gene Expression Omnibus’. https://www.ncbi.nlm.nih.gov/geo.
22. [22] M. D. Christian Steidl, et al., ‘Tumor-Associated Macrophages and Survival in Classic Hodgkin’s Lymphoma’, N. Engl. J. Med., vol. 362, no. 10, pp. 875–885, 2010.
23. [23] D. A. Hashimoto, T. M. Ward, and O. R. Meireles, ‘The Role of Artificial Intelligence in Surgery’, Adv. Surg., vol. 54, pp. 89–101, 2020, doi: 10.1016/j.yasu.2020.05.010.
24. [24] R. Dias and A. Torkamani, ‘Artificial intelligence in clinical and genomic diagnostics’, Genome Med., vol. 11, pp. 1–12, 2019, doi: 10.1186/s13073-019-0689-8.
25. [25] S. Hayou, A. Doucet, and J. Rousseau, ‘On the impact of the activation function on deep neural networks training’, Arxiv, 2019.
26. [26] ‘MathWorks-Help Center’. https://www.mathworks.com/help/.
27. [27] C. Doğan, ‘Balina Optimizasyon Algoritması ve Gri Kurt Optimizasyonu Algoritmaları Kullanılarak Yeni Hibrit Optimizasyon Algoritmalarının Geliştirilmesi’, 2019.
28. [28] E. G. Dada, S. B. Joseph, D. O. Oyewola, A. A. Fadele, H. Chiroma, and S. M. Abdulhamid, ‘Application of Grey Wolf Optimization Algorithm: Recent Trends, Issues, and Possible Horizons’, Gazi Univ. J. Sci., vol. 35, no. 2, pp. 485–504, 2022, doi: 10.35378/gujs.820885.
29. [29] F. Akalın and N. Yumuşak, ‘DNA genom dizilimi üzerinde dijital sinyal işleme teknikleri kullanılarak elde edilen ekson ve intron bölgelerinin EfficientNetB7 mimarisi ile sınıflandırılması’, Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Derg., vol. 37, no. 3, pp. 1355–1371, 2022, doi: 10.17341/gazimmfd.900987.
30. [30] O. Sertel, J. Kong, U. V. Catalyurek, G. Lozanski, J. H. Saltz, and M. N. Gurcan, ‘Histopathological image analysis using model-based intermediate representations and color texture: Follicular lymphoma grading’, J. Signal Process. Syst., vol. 55, pp. 169–183, 2009, doi: 10.1007/s11265-008-0201-y.
31. [31] M. Lippi et al., ‘Texture analysis and multiple-instance learning for the classification of malignant lymphomas’, Comput. Methods Programs Biomed., vol. 185, 2020, doi: 10.1016/j.cmpb.2019.105153.
32. [32] B. Ganeshan et al., ‘CT-based texture analysis potentially provides prognostic information complementary to interim fdg-pet for patients with hodgkin’s and aggressive non-hodgkin’s lymphomas’, Eur. Radiol., vol. 27, pp. 1012–1020, 2017, doi: 10.1007/s00330-016-4470-8.
33. [33] M. Z. Nascimento, L. Neves, S. C. Duarte, Y. A. S. Duarte, and V. R. Batista, ‘Classification of histological images based on the stationary wavelet transform’, J. Phys. Conf. Ser., vol. 574, 2015, doi: 10.1088/1742-6596/574/1/012133.
34. [34] E. S. Alférez, A. Merino, L. E. Mújica, M. Ruiz, L. Bigorra, and J. Rodellar, ‘Digital Blood Image Processing and Fuzzy Clustering for Detection and Classification of Atypical Lymphoid B cells’, Jornades Recer. Euetib 2013, pp. 1–12, 2013.
35. [35] O. Sertel, G. Lozanski, A. Shanáah, and M. N. Gurcan, ‘Computer-aided detection of centroblasts for follicular lymphoma grading using adaptive likelihood-based cell segmentation’, IEEE Trans. Biomed. Eng., vol. 57, no. 10, pp. 2613–2616, 2010, doi: 10.1109/TBME.2010.2055058.
36. [36] N. V. Orlov et al., ‘Automatic classification of lymphoma images with transform-based global features’, IEEE Trans. Inf. Technol. Biomed., vol. 14, no. 4, pp. 1003–1013, 2010, doi: 10.1109/TITB.2010.2050695.