Mezotelyoma Hastalığı için Makine Öğrenmesi tabanlı Erken Tanı Sistemi

Year 2020, , 1604 - 1611, 30.04.2020

Zehra Karapınar Şentürk , Nagihan Çekiç

https://doi.org/10.29130/dubited.659106

Cited By: 5

Abstract

Mezotelyoma, tanısından yaklaşık bir yıl sonra hastanın ölümüne sebep olan bir akciğer zarı kanseridir. Hastalık ağrıya ve nefes darlığına sebep olur. Hastalar geleneksel olarak CT (Bilgisayarlı Tomografi) taraması ve akciğer röntgenine tabi tutulurlar, fakat kesin tanı yöntemi biyopsidir. Tanı için farklı biyopsi yöntemleri de vardır. Hastalığın yaygınlığı dünyada milyonda 1 veya 2 iken Türkiye’de rakamlar korkunçtur. Türkiye’de her yıl beş yüz kişiye mezotelyoma tanısı konmaktadır. Bu ciddi rakamlar mezotelyoma hastalığı için bir erken tanı sistemini çok önemli kılmaktadır. Bu çalışmada, bahsedilen ölümcül hastalık için makine öğrenmesine dayalı bir erken tanı sistemi önerilmiştir. Deneylerde açık kaynaklı bir veri seti kullanılmış ve probleme farklı yöntemler uygulanmıştır. Yöntemlerin değerlendirilmesinde doğruluk ve hassasiyet performans ölçütleri kullanılmıştır. Sonuçlar, kullanılan farklı makine öğrenmesi yöntemlerinin mezotelyoma tanısı üzerindeki performansını göstermekte ve başarılı bir erken tanı sistemi sunmaktadır.

Keywords

Erken tanı, mezotelyoma hastalığı, makine öğrenmesi

A Machine Learning Based Early Diagnosis System for Mesothelioma Disease

Abstract

Mesothelioma is pleura cancer that cause death in about one year after diagnosis. The disease causes pain and shortness of breath. Patients have a CT (Computed Tomography)-scan and lung x-ray traditionally, but the exact method is biopsy. There are also different biopsy methods for its diagnosis. Its prevalence is one or two in a million around the world, but for Turkey it is disastrous. Five hundred people are diagnosed as mesothelioma every year in Turkey. This serious rate makes early diagnosis systems crucial for mesothelioma. In this paper, a machine learning based early detection system has been proposed for this fatal disease. An open database is used for the experiments and different methods have been applied to the problem of diagnosing mesothelioma disease. Accuracy and sensitivity performance metrics were used for the evaluation of the methods. The results show the diagnostic performance of different machine learning methods and present a successful early diagnosis system.

Keywords

Early diagnosis, mesothelioma disease, machine learning

References

• [1] M. Ergin, “Mesothelioma (Pleura Cancer) in 3 Questions-Turkish Society of Thoracic Surgery,” 2019. [Online]. Available: http://www.tgcd.org.tr/3-soruda-mezotelyoma-akciger-zari-kanseri/. Accessed: 22-Nov-2019
• [2] M. A. Kurt and Ü. Yildirim, “Türkiye’de asbest yasağı ve bazı ithal ürünlerde asbest minerallerinin araştırılması,” NGU J. Eng. Sci. Niğde Üniversitesi Mühendislik Bilim. Derg., vol. 5, no. 2, pp. 90–96, 2016.
• [3] Y. Orgun Tutay, “İstanbul Asbest Raporu,” 2018.
• [4] M. Abdar, W. Książek, U. R. Acharya, R. S. Tan, V. Makarenkov, and P. Pławiak, “A new machine learning technique for an accurate diagnosis of coronary artery disease,” Comput. Methods Programs Biomed., vol. 179, 2019.
• [5] S.-H. Wang, P. Phillips, Y. Sui, B. Liu, M. Yang, and H. Cheng, “Classification of Alzheimer’s Disease Based on Eight-Layer Convolutional Neural Network with Leaky Rectified Linear Unit and Max Pooling,” J. Med. Syst., vol. 42, no. 5, pp. 85, 2018.
• [6] F. Zhang, S. Tian, S. Chen, Y. Ma, X. Li, and X. Guo, “Voxel-Based Morphometry: Improving the Diagnosis of Alzheimer’s Disease Based on an Extreme Learning Machine Method from the ADNI cohort,” Neuroscience, vol. 414, pp. 273–279, 2019.
• [7] C. Kotsavasiloglou, N. Kostikis, D. Hristu-Varsakelis, and M. Arnaoutoglou, “Machine learning-based classification of simple drawing movements in Parkinson’s disease,” Biomed. Signal Process. Control, vol. 31, pp. 174–180, 2017.
• [8] L. Parisi, N. RaviChandran, and M. L. Manaog, “Feature-driven machine learning to improve early diagnosis of parKinson’s disease,” Expert Syst. Appl., vol. 110, pp. 182–190, 2018.
• [9] F. Meriaudeau, “Machine Learning and Deep Learning approaches for Retinal Disease Diagnosis,” Procedia Comput. Sci., vol. 135, pp. 2, 2018.
• [10] “Cardiovascular diseases.” [Online]. Available: http://www.euro.who.int/en/health-topics/noncommunicable-diseases/cardiovascular-diseases/cardiovascular-diseases2. Accessed: 23-Jan-2019.
• [11] C. C. Wu et al., “Prediction of fatty liver disease using machine learning algorithms,” Comput. Methods Programs Biomed., vol. 170, pp. 23–29, 2019.
• [12] M. Nilashi, O. bin Ibrahim, H. Ahmadi, and L. Shahmoradi, “An analytical method for diseases prediction using machine learning techniques,” Comput. Chem. Eng., vol. 106, pp. 212–223, 2017.
• [13] O. Er, A. C. Tanrikulu, A. Abakay, and F. Temurtas, “An approach based on probabilistic neural network for diagnosis of Mesothelioma’s disease,” in Computers and Electrical Engineering, 2012, vol. 38, no. 1, pp. 75–81.
• [14] M. L. Huang and Y. C. Chou, “Combining a gravitational search algorithm, particle swarm optimization, and fuzzy rules to improve the classification performance of a feed-forward neural network,” Comput. Methods Programs Biomed., vol. 180, 2019.
• [15] M. Albayrak and A. Albayrak, “Feature Selection with Genetic Algorithm in Classification of Mesothelioma Disease Data,” in Tıp Teknolojileri Kongresi (TIPTEKNO’16), 2016, pp. 138–141.
• [16] W. Brahim, M. Mestiri, N. Betrouni, and K. Hamrouni, “Semi-Automated rib cage segmentation in CT images for mesothelioma detection,” in IPAS 2016 - 2nd International Image Processing, Applications and Systems Conference, 2017, pp. 1–6.
• [17] H. O. Ilhan and E. Celik, “The mesothelioma disease diagnosis with artificial intelligence methods,” in Application of Information and Communication Technologies, AICT 2016 - Conference Proceedings, 2017.
• [18] K. Y. Win, N. Maneerat, S. Choomchuay, S. Sreng, and K. Hamamoto, “Suitable Supervised Machine Learning Techniques For Malignant Mesothelioma Diagnosis,” 2018.
• [19] “UCI Machine Learning Repository.” [Online]. Available: https://archive.ics.uci.edu/ml/datasets.php. Accessed: 06-Mar-2020.
• [20] “Gradient Boosted Trees - RapidMiner Documentation.” [Online]. Available: https://docs.rapidminer.com/latest/studio/operators/modeling/predictive/trees/gradient_boosted_trees.html. Accessed: 12-Mar-2020.
• [21] “Welcome to H2O 3 — H2O 3.28.1.1 documentation.” [Online]. Available: http://docs.h2o.ai/h2o/latest-stable/h2o-docs/welcome.html. Accessed: 12-Mar-2020.
• [22] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.
• [23] D. A. Pisner and D. M. Schnyer, “Support vector machine,” in Machine Learning, Academic Press, 2020, pp. 101–121.
• [24] W. J. Chen, Y. H. Shao, C. N. Li, Y. Q. Wang, M. Z. Liu, and Z. Wang, “NPrSVM: Nonparallel sparse projection support vector machine with efficient algorithm,” Appl. Soft Comput. J., vol. 90, p. 106142, 2020.
• [25] “k-NN - RapidMiner Documentation.” [Online]. Available: https://docs.rapidminer.com/latest/studio/operators/modeling/predictive/lazy/k_nn.html. Accessed: 11-Mar-2020.
• [26] Ç. Elmas, Artificial Neural Networks, 1st ed. Ankara: Seçkin Yayıncılık, 2003.
• [27] E. Öztemel, Yapay Sinir Ağları, 3rd ed. İstanbul: Papatya Yayıncılık, 2012.
• [28] “RapidMiner©.” [Online]. Available: https://rapidminer.com/. Accessed: 04-Mar-2019.