Akut Lenfositik Löseminin Makine Öğrenimi Yöntemleriyle Otomatik Tespitine İlişkin Karşılaştırmalı Bir Çalışma

Year 2022, Volume: 24 Issue: 72, 1021 - 1032, 19.09.2022

Canan Kocatürk Cemre Candemir , İlker Kocabaş

https://doi.org/10.21205/deufmd.2022247229

Abstract

Akut Lenfositik Lösemi (ALL) en sık görülen lösemi tiplerinden biridir ve çocukların ölüm riski yetişkinlere göre nispeten daha yüksektir. Bu hastalığın erken teşhisi çok kritik olup, kan hücrelerinin morfolojik değişiklikleri incelenerek tespit edilebilir. Bu çalışmada, ALL'nin makine öğrenmesi metodolojileri ile otomatik olarak sınıflandırılması ve tanımlanması üzerine karşılaştırmalı bir çalışma sunuyoruz. Çalışmada, 118 deneğe ait 6500 dijital mikroskobik patoloji görüntüsünden oluşan Kanser Görüntüleme Arşivi tarafından sunulan Akut Lenfoblastik Görüntü Veritabanı (ALL-CDB) kullanılmaktadır. İlk adım olarak geometrik öznitelikler çıkarılmıştır ve ardından Temel Bileşen Analizi (PCA) ile öznitelik seçimi yapılmıştır. Son olarak Naive Bayes, k-En Yakın Komşu (k-NN), Lineer Diskriminant Analizi (LDA), Karar Ağacı (DT), Rastgele Orman (RF), Destek Vektör Makinesi (SVM) ve Çok Katmanlı Algılayıcı (MLP) yöntemleri kullanılarak seçilen öznitelikler üzerinde sınıflandırma işlemi gerçekleştirilmiştir. Metodolojiler arasındaki sonuçlar, doğruluk, kesinlik, hatırlama ve F1-skor metrikleri açısından analiz edilmiştir. Sonuçlara göre MLP, ALL hücrelerini sınıflandırmak için %97 ile hem en yüksek doğruluk hem de F1-skorunu vermektedir.

Keywords

Akut Lenfositik Lösemi, makine öğrenmesi, sınıflandırma, karar ağacı, çok katmanlı algılayıcı, destek vektör makinesi, lineer diskriminant analizi, Akut Lenfositik Lösemi, makine öğrenmesi, sınıflandırma, karar ağacı, çok katmanlı algılayıcı, destek vektör makinesi, lineer diskriminant analizi

A Comparative Study of Automatic Detection of Acute Lymphocytic Leukemia with Machine Learning Methods

Abstract

Acute Lymphocytic Leukemia (ALL) is one of the most prevalent types of leukemia which has the risk of death of children is relatively higher than adults. The early diagnosis of this disease is crucial and it can be detected by examining the morphological changes of the blood cells. In this study, we exhibit a comparative study on the automatic classification and identification of the ALL with machine learning methodologies. Acute Lymphoblastic Challange Database (ALL-CDB) served by the Cancer Imaging Archive, which consists of 6500 digital microscopic pathology images from 118 subjects, is used. As the first step, the geometric features are extracted and after, the feature selection was performed with Principal Component Analysis (PCA). Finally, the classification process on the selected features was carried out by using Naive Bayes, k-Nearest Neighbor (k-NN), Linear Discriminant Analysis (LDA), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and Multilayer Perceptron (MLP) neural network methods. The results between the methodologies have been analyzed in terms of accuracy, precision, recall, and F1-score metrics. According to the results, MLP gives the both highest accuracy and F1-score with 97% to classify the ALL cells for leukemia.

Keywords

Acute Lymphocytic Leukemia, machine learning, classification, multilayer perceptron, support vector machine, decision tree, linear discriminant analysis

References

• [1]https://www.cancer.org/acutelymphocytic-lukemia/about/key-statistics.html (access:10.12.2021).
• [2] “PS80 FactsBook_2020_2021_FINAL.pdf”. https://www.lls.org/sites/default/files/202108/PS80%20FactsBook_2020_2021_FINAL.pdf (access:10.12.2021).
• [3] F. Bray, J. Ferlay, I. Soerjomataram, R. L. Siegel, L. A. Torre, ve A. Jemal, “Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries”, CA: a cancer journal for clinicians, c. 68, v. 6, ss. 394-424, 2018.
• [4] Y. Dong vd., “Leukemia incidence trends at the global, regional, and national level between 1990 and 2017”, Exp Hematol Oncol, c. 9, sy 1, s. 14, Ara. 2020, doi: 10.1186/s40164-020-00170-6.
• [5] S. Mandal, V. Daivajna, ve R. V., “Machine Learning based System for Automatic Detection of Leukemia Cancer Cell”, içinde 2019 IEEE 16th India Council International Conference (INDICON), Rajkot, India, Ara. 2019, ss. 1-4. doi: 10.1109/INDICON47234.2019.9029034.
• [6] Ahmed, Yigit, Isik, ve Alpkocak, “Identification of Leukemia Subtypes from Microscopic Images Using Convolutional Neural Network”, Diagnostics, c. 9, sy 3, s. 104, Ağu. 2019, doi: 10.3390/diagnostics9030104.
• [7] Md. N. Q. Bhuiyan, S. K. Rahut, R. A. Tanvir, ve S. Ripon, “Automatic Acute Lymphoblastic Leukemia Detection and Comparative Analysis from Images”, içinde 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT), Paris, France, Nis. 2019, ss. 1144-1149. doi: 10.1109/CoDIT.2019.8820299.
• [8] M. A. Khosrosereshki ve M. B. Menhaj, “A fuzzy based classifier for diagnosis of acute lymphoblastic leukemia using blood smear image processing”, içinde 2017 5th Iranian Joint Congress on Fuzzy and Intelligent Systems (CFIS), Qazvin, Iran, Mar. 2017, ss. 13-18. doi: 10.1109/CFIS.2017.8003589.
• [9] MARIA, Italia Joseph; DEVI, T.; RAVI, D. Machine learning algorithms for diagnosis of leukemia. Int J Sci Technol Res, 2020, 9.1.
• [10] KUMAR, Sachin, et al. Automated detection of acute leukemia using k-mean clustering algorithm. In: Advances in computer and computational sciences. Springer, Singapore, 2018. p. 655-670.
• [11] H. Parvaresh, H. Sajedi, ve S. A. Rahimi, “Leukemia Diagnosis Using Image Processing and Computational Intelligence”, içinde 2018 IEEE 22nd International Conference on Intelligent Engineering Systems (INES), Las Palmas de Gran Canaria, Haz. 2018, ss. 000305-000310. doi: 10.1109/INES.2018.8523900.
• [12] D. Umamaheswari ve S. Geetha, “Segmentation and Classification of Acute Lymphoblastic Leukemia Cells Tooled with Digital Image Processing and ML Techniques”, içinde 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, Haz. 2018, ss. 1336-1341. doi: 10.1109/ICCONS.2018.8662950.
• [13] Wahhab, Hayan Tareq Abdul. Classification of acute leukemia using image processing and machine learning techniques. 2015. PhD Thesis. University of Malaya.
• [14] S. Rajpurohit, S. Patil, N. Choudhary, S. Gavasane, ve P. Kosamkar, “Identification of Acute Lymphoblastic Leukemia in Microscopic Blood Image Using Image Processing and Machine Learning Algorithms”, içinde 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Bangalore, Eyl. 2018, ss. 2359-2363. doi: 10.1109/ICACCI.2018.8554576.
• [15] A. M. Abdeldaim, A. T. Sahlol, M. Elhoseny, ve A. E. Hassanien, “Computer-Aided Acute Lymphoblastic Leukemia Diagnosis System Based on Image Analysis”, içinde Advances in Soft Computing and Machine Learning in Image Processing, c. 730, A. E. Hassanien ve D. A. Oliva, Ed. Cham: Springer International Publishing, 2018, ss. 131-147. doi: 10.1007/978-3-319-63754-9_7.
• [16] S. Shafique ve S. Tehsin, “Acute Lymphoblastic Leukemia Detection and Classification of Its Subtypes Using Pretrained Deep Convolutional Neural Networks”, Technol Cancer Res Treat, c. 17, s. 153303381880278, Oca. 2018, doi: 10.1177/1533033818802789.
• [17] S. Mourya, S. Kant, P. Kumar, A. Gupta, ve R. Gupta, “ALL Challenge dataset of ISBI 2019”. The Cancer Imaging Archive, 2019. doi: 10.7937/TCIA.2019.DC64I46R.
• [18] F.Çam,A.Güven, “Methods Used In The Classification of White Blood Cells from Blood Cell Images Taken under a Digital Microscope”, s.21, 2019.
• [19] Z. F. Mohammed ve A. A. Abdulla, “Thresholding-based White Blood Cells Segmentation from Microscopic Blood Images”, UHD J SCI TECH, c. 4, pp1,s.9,Şub.2020.doi: 10.21928/uhdjst.v4n1y2020.pp9-17.
• [20] M. MoradiAmin, A. Memari, N. Samadzadehaghdam, S. Kermani, ve A. Talebi, “Computer aided detection and classification of acute lymphoblastic leukemia cell subtypes based on microscopic image analysis”, Microscopy Research and Technique, c. 79, sy 10, ss. 908-916, 2016, doi: https://doi.org/10.1002/jemt.22718.
• [21] K. Yildiz, A. Çamurcu, ve B. Dogan, A Comperative Analize of Principal Component Analysis and Non-Negative Matrix Factorization Techniques in Data Mining. 2010.
• [22] A. Jamal, A. Handayani, A. Septiandri, E. Ripmiatin, ve Y. Effendi, “Dimensionality Reduction using PCA and K-Means Clustering for Breast Cancer Prediction”, Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, s. 192, Ara. 2018, doi: 10.24843/LKJITI.2018.v09.i03.p08.
• [23] A. B. Varol ve İ. İşeri, “Lenf Kanserine İlişkin Patoloji Görüntülerinin Makine Öğrenimi Yöntemleri ile Sınıflandırılması”, European Journal of Science and Technology, ss. 404-410, Eki. 2019, doi: 10.31590/ejosat.638372.
• [24] M. M. Saritas, “Performance Analysis of ANN and Naive Bayes Classification Algorithm for Data Classification”, ijisae, c. 7, sy 2, ss. 88-91, Oca. 2019, doi: 10.18201/ijisae.2019252786.
• [25] J. Gupta, “The Accuracy of Supervised Machine Learning Algorithms in Predicting Cardiovascular Disease”, içinde 2021 International Conference on Artificial Intelligence and Computer Science Technology (ICAICST), Yogyakarta, Indonesia, Haz. 2021, ss. 234-239. doi: 10.1109/ICAICST53116.2021.9497837.
• [26] S. Sharma, A. Aggarwal, ve T. Choudhury, “Breast Cancer Detection Using Machine Learning Algorithms”, içinde 2018 International Conference on Computational Techniques, Electronics and Mechanical Systems (CTEMS), Ara. 2018, ss. 114-118. doi: 10.1109/CTEMS.2018.8769187.
• [27] M. A. Pala, M. E. Çimen, Ö. F. Boyraz, M. Z. Yildiz, ve A. F. Boz, “Meme Kanserinin Teşhis Edilmesinde Karar Ağacı Ve KNN Algoritmalarının Karşılaştırmalı Başarım Analizi”, acperpro, c. 2, sy 3, ss. 544-552, Kas. 2019.
• [28] C. Oral, A. Aydın Yurdusev, ve E. Bergil, “Mamogramların Sınıflandırılmasında Dokusal Özelliklerin Etkileri”, DÜMF Mühendislik Dergisi, c. 10, sy 1, ss. 23-33, Mar. 2019, doi: 10.24012/dumf.403657.
• [29] ELSAYAD, Alaa M.; ELSALAMONY, H. A. Diagnosis of breast cancer using decision tree models and SVM. International Journal of Computer Applications, 2013, 83.5.
• [30] GÜLDAL, Hakan. Karar ağacı algoritmalarının eğitsel veriler üzerindeki performanslarının incelenmesi The analysing of desicion alghoritms’ performance on educational data. In: 13th International Balkan Education and Science Congress. 2018. p. 6.
• [31] J. Thongkam, G. Xu, ve Y. Zhang, “AdaBoost algorithm with random forests for predicting breast cancer survivability”, içinde 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China, Haz. 2008, ss. 3062-3069. doi: 10.1109/IJCNN.2008.4634231.
• [32] B. Özlüer Başer, M. Yangin, ve E. S. Saridaş, “Makine Öğrenmesi Teknikleriyle Diyabet Hastalığının Sınıflandırılması”, Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, Şub. 2021, doi: 10.19113/sdufenbed.842460.
• [33] S. Ghosh, S. Mondal, ve B. Ghosh, “A comparative study of breast cancer detection based on SVM and MLP BPN classifier”, içinde 2014 First International Conference on Automation, Control, Energy and Systems (ACES), India, Şub. 2014, ss. 1-4. doi: 10.1109/ACES.2014.6808002.
• [34] A. O. Ibrahim, S. M. Shamsuddin, A. Yahya Saleh, A. Abdelmaboud, ve A. Ali, “Intelligent multi-objective classifier for breast cancer diagnosis based on multilayer perceptron neural network and Differential Evolution”, içinde 2015 International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE), Khartoum, Sudan, Eyl. 2015, ss. 422-427. doi: 10.1109/ICCNEEE.2015.7381405.
• [35] D. Soria, J. M. Garibaldi, E. Biganzoli, ve I. O. Ellis, “A Comparison of Three Different Methods for Classification of Breast Cancer Data”, içinde 2008 Seventh International Conference on Machine Learning and Applications, San Diego, CA, USA, 2008, ss. 619-624. doi: 10.1109/ICMLA.2008.97.