RADYOMİK ÖZELLİKLER VE MAKİNE ÖĞRENMESİ TEKNİKLERİYLE MEME TÜMÖRLERİNİN SINIFLANDIRILMASI

Asuman Kaplan; Esra Kavadar; Mehmet Ali Altuncu

doi:10.17780/ksujes.1512476

TR EN

RADYOMİK ÖZELLİKLER VE MAKİNE ÖĞRENMESİ TEKNİKLERİYLE MEME TÜMÖRLERİNİN SINIFLANDIRILMASI

Öz

Meme kanseri, dünya genelinde kadınlar arasında en sık görülen kanser türüdür ve erken teşhis, tedavi başarısını önemli ölçüde artırmaktadır. Bu çalışmada, meme ultrason görüntülerinden iyi huylu ve kötü huylu tümörleri sınıflandırmak amacıyla radyomik özellikler ve makine öğrenmesi teknikleri kullanılmıştır. Çalışmada, halka açık BUSI veri seti kullanılmıştır. Sadece iyi huylu ve kötü huylu olarak etiketlenmiş görüntüler sınıflandırmada kullanılmış olup, normal etiketli görüntüler çalışmaya dahil edilmemiştir. Bu yaklaşım, modelin iki sınıf arasındaki ayrımı en yüksek doğrulukla yapmasına odaklanmıştır. Veri setindeki dengesizlik, kötü huylu tümörlerin görüntülerinin y ekseninde aynalanarak artırılmasıyla giderilmiştir. PyRadiomics kütüphanesi ile çıkarılan 123 radyomik özellik arasından, özellik önem skoru ve korelasyon matrisi kullanılarak en önemli 40 özellik seçilmiştir. Sınıflandırma aşamasında XGBoost, Gradient Boosting, AdaBoost, SVM, Random Forest ve Decision Tree algoritmaları uygulanmış, en yüksek doğruluk oranı (%98.13) Gradient Boosting algoritması ile elde edilmiştir.

Anahtar Kelimeler

CLASSIFICATION OF BREAST TUMORS USING RADIOMIC FEATURES AND MACHINE LEARNING TECHNIQUES

Abstract

Breast cancer is the most common type of cancer among women worldwide, and early diagnosis significantly increases the success of treatment. In this study, radiomic features and machine learning techniques were used to classify benign and malignant tumors from breast ultrasound images. The publicly available BUSI dataset was used in the study. Only images labeled as benign and malignant were used in the classification, and normal labeled images were not included in the study. This approach focused on the model distinguishing between the two classes with the highest accuracy. The imbalance in the dataset was eliminated by mirroring and augmenting the images of malignant tumors in the y-axis. Among the 123 radiomic features extracted with the PyRadiomics library, the most important 40 features were selected using feature importance scores and correlation matrix. XGBoost, Gradient Boosting, AdaBoost, SVM, Random Forest and Decision Tree algorithms were applied in the classification phase, and the highest accuracy rate (98.13%) was obtained with the Gradient Boosting algorithm.

Keywords

Kaynakça

Adnan, M., Alarood, A. a. S., Uddin, M. I., & Rehman, I. U. (2022). Utilizing grid search cross-validation with adaptive boosting for augmenting performance of machine learning models. PeerJ. Computer Science, 8, e803. https://doi.org/10.7717/peerj-cs.803
Al-Dhabyani, W., Gomaa, M., Khaled, H., & Fahmy, A. (2020). Dataset of breast ultrasound images. Data in Brief, 28, 104863. https://doi.org/10.1016/j.dib.2019.104863
Ali, J., Khan, R., Ahmad, N., & Maqsood, I. (2012). Random forests and decision trees. International Journal of Computer Science Issues, 9(5), 272–278. http://ijcsi.org/papers/IJCSI-9-5-3-272-278.pdf
Ara, S., Das, A., & Dey, A. (2021, April). Malignant and benign breast cancer classification using machine learning algorithms. In 2021 International Conference on Artificial Intelligence (ICAI) (pp. 97-101). IEEE.
Ardakani, A. A., Bureau, N. J., Ciaccio, E. J., & Acharya, U. R. (2022). Interpretation of radiomics features–A pictorial review. Computer Methods and Programs in Biomedicine, 215, 106609. https://doi.org/10.1016/j.cmpb.2021.106609
Aristokli, N., Polycarpou, I., Themistocleous, S. C., Sophocleous, D., & Mamais, I. (2022). Comparison of the diagnostic performance of Magnetic Resonance Imaging (MRI), ultrasound and mammography for detection of breast cancer based on tumor type, breast density and patient's history: A review. Radiography, 28(3), 848–856. https://doi.org/10.1016/j.radi.2022.01.006
Assiri, A. S., Nazir, S., & Velastin, S. A. (2020). Breast tumor classification using an ensemble machine learning method. Journal of Imaging, 6(6), 39. https://doi.org/10.3390/jimaging6060039
Badawy, S. M., Mohamed, A. E. N. A., Hefnawy, A. A., Zidan, H. E., GadAllah, M. T., & El-Banby, G. M. (2021, July). Classification of Breast Ultrasound Images Based on Convolutional Neural Networks-A Comparative Study. In 2021 International Telecommunications Conference (ITC-Egypt) (pp. 1-8). IEEE.

Bota, M. A., Gota, D. I., Bota, P., Stan, O. P., Pop, A., Fanca, A., ... & Miclea, L. (2024, February). Utilizing Transfer Learning-Based Algorithms for Breast Ultrasound Data in Multi-Instance Classification. In 2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) (pp. 1-6). IEEE.
CERR. (n.d.). CERR: Computational Environment for Radiotherapy Research. Retrieved September 4, 2024, from https://cerr.github.io/CERR/
Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
Çapkan, H., Dönmez, B., Kalkan, G. M., Kaya, M. Z., Gürel, S., Akdağlı, E., ... & Uçar, M. K. (2022). Diagnosis of Breast Cancer with Hybrid Artificial Intelligence Method. Avrupa Bilim ve Teknoloji Dergisi, (42), 14-19.
Eroğlu, Y., Yildirim, M., & Çinar, A. (2021). Convolutional Neural Networks based classification of breast ultrasonography images by hybrid method with respect to benign, malignant, and normal using mRMR. Computers in Biology and Medicine, 133, 104407. https://doi.org/10.1016/j.compbiomed.2021.104407
Fornacon-Wood, I., Mistry, H., Ackermann, C. J., Blackhall, F., McPartlin, A., Faivre-Finn, C., ... & O’Connor, J. P. (2020). Reliability and prognostic value of radiomic features are highly dependent on choice of feature extraction platform. European Radiology, 30(12), 6241-6250. https://doi.org/10.1007/s00330-020-06957-9
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5). https://doi.org/10.1214/aos/1013203451
Ghabrim, H., Essid, C., & Sakli, H. (2023, February). A diagnostic system for classifying and segmenting breast cancer based on ultrasound images. In 2023 20th International Multi-Conference on Systems, Signals & Devices (SSD) (pp. 919-924). IEEE.
Gupta, S., Panwar, A., Yadav, R., Aeri, M., & Manwal, M. (2022, February). Employing Deep Learning Feature Extraction Models with Learning Classifiers to Diagnose Breast Cancer in Medical Images. In 2022 IEEE Delhi Section Conference (DELCON) (pp. 1-6). IEEE.
Hussain, Z., Gimenez, F., Yi, D., & Rubin, D. (2017). Differential data augmentation techniques for medical imaging classification tasks. AMIA annual symposium proceedings, 2017, 979-984.
Jabeen, K., Khan, M. A., Alhaisoni, M., Tariq, U., Zhang, Y. D., Hamza, A., Khalid, A., Kumar, S., Awais, M., Ali, M., & Damaševičius, R. (2022). Breast cancer classification from ultrasound images using probability-based optimal deep learning feature fusion. Sensors, 22(3), 807. https://doi.org/10.3390/s22030807
Khanna, P., Sahu, M., & Singh, B. K. (2021, December). Improving the classification performance of breast ultrasound image using deep learning and optimization algorithm. In 2021 IEEE International Conference on Technology, Research, and Innovation for Betterment of Society (TRIBES) (pp. 1-6). IEEE.
Kumar, V., Gu, Y., Basu, S., Berglund, A., Eschrich, S. A., Schabath, M. B., Patil, D. C., Little, R. B., Tsien, C. I., & Gillies, R. J. (2012). Radiomics: The process and the challenges. Magnetic Resonance Imaging, 30(9), 1234-1248. https://doi.org/10.1016/j.mri.2012.06.010
Lanjewar, M. G., Panchbhai, K. G., & Patle, L. B. (2024). Fusion of transfer learning models with LSTM for detection of breast cancer using ultrasound images. Computers in Biology and Medicine, 169, 107914. https://doi.org/10.1016/j.compbiomed.2023.107914
LIFEx. (n.d.). LIFEx: Lesion imaging feature extraction. Retrieved September 4, 2024, from https://www.lifexsoft.org/
Liu, H., Cui, G., Luo, Y., Guo, Y., Zhao, L., Wang, Y., . . . Tuncer, T. (2022). Artificial Intelligence-Based breast cancer diagnosis using ultrasound images and Grid-Based Deep Feature Generator. International Journal of General Medicine, Volume 15, 2271–2282. https://doi.org/10.2147/ijgm.s347491
Luo, J., Quan, Y., & Xu, S. (2024). Robust-GBDT: GBDT with nonconvex loss for tabular classification in the presence of label noise and class imbalance. arXiv. https://arxiv.org/abs/2310.05067
Medical Imaging Interaction Toolkit. (n.d.). The Medical Imaging Interaction Toolkit (MITK). Retrieved September 4, 2024, from https://www.mitk.org/wiki/The_Medical_Imaging_Interaction_Toolkit_(MITK)
Mishra, A. K., Roy, P., Bandyopadhyay, S., & Das, S. K. (2021). Breast ultrasound tumour classification: A Machine Learning—Radiomics based approach. Expert Systems, 38(7). https://doi.org/10.1111/exsy.12713
Myles, A. J., Feudale, R. N., Liu, Y., Woody, N. A., & Brown, S. D. (2004). An introduction to decision tree modeling. Journal of Chemometrics, 18(6), 275–285. https://doi.org/10.1002/cem.873
Natekin, A., & Knoll, A. (2013). Gradient boosting machines, a tutorial. Frontiers in neurorobotics, 7, 21. https://doi.org/10.3389/fnbot.2013.00021
Nielsen, D. (2016). Tree Boosting With XGBoost. Master's thesis. Norwegian University of Science and Technology, Trondheim 98s.
Oshiro, T. M., Perez, P. S., & Baranauskas, J. A. (2012). How many trees in a random forest?. In Machine Learning and Data Mining in Pattern Recognition: 8th International Conference, MLDM 2012, Berlin, Germany, July 13-20, 2012. Proceedings 8 (pp. 154-168). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-31537-4_13
Pesapane, F., De Marco, P., Rapino, A., Lombardo, E., Nicosia, L., Tantrige, P., Sardanelli, F., Manfredi, R., Bertelli, E., Castello, R., & Cassano, E. (2023). How radiomics can improve breast cancer diagnosis and treatment. Journal of Clinical Medicine, 12(4), 1372. https://doi.org/10.3390/jcm12041372
Pisner, D. A., & Schnyer, D. M. (2020). Support vector machine. In Machine learning (pp. 101-121). Academic Press. https://doi.org/10.1016/B978-0-12-815739-8.00006-7
Podda, A. S., Balia, R., Barra, S., Carta, S., Fenu, G., & Piano, L. (2022). Fully-automated deep learning pipeline for segmentation and classification of breast ultrasound images. Journal of Computational Science, 63, 101816. https://doi.org/10.1016/j.jocs.2022.101816
Pourasad, Y., Zarouri, E., Parizi, M. S., & Mohammed, A. S. (2021). Presentation of novel architecture for diagnosis and identifying breast cancer location based on ultrasound images using Machine learning. Diagnostics, 11(10), 1870. https://doi.org/10.3390/diagnostics11101870
Quinlan, J. R. (1996). Learning decision tree classifiers. ACM Computing Surveys (CSUR), 28(1), 71-72. Rashid, H. U., Ibrikci, T., Paydaş, S., Binokay, F., & Çevik, U. (2022). Analysis of breast cancer classification robustness with radiomics feature extraction and deep learning techniques. Expert Systems, 39(8), e13018. https://doi.org/10.1111/exsy.13018
Rizzo, S., Botta, F., Raimondi, S., Origgi, D., Fanciullo, C., Morganti, A. G., & Bellomi, M. (2018). Radiomics: the facts and the challenges of image analysis. European Radiology Experimental, 2(1). https://doi.org/10.1186/s41747-018-0068-z
Şenol, A., & Kaya, M. (2024). An investigation on the use of clustering algorithms for data preprocessing in breast cancer diagnosis. Türk Doğa ve Fen Dergisi, 13(1), 70-77. https://doi.org/10.46810/tdfd.1364397 Schapire, R. E. (2013). Explaining AdaBoost. In Springer eBooks (pp. 37–52). https://doi.org/10.1007/978-3-642-41136-6_5
Sun, H., Li, H., Si, S., Qi, S., Zhang, W., Ma, H., Chen, X., Liu, Y., Yang, J., Zhang, X., & Qian, W. (2018). Performance evaluation of breast cancer diagnosis with mammography, ultrasonography, and magnetic resonance imaging. Journal of X-ray Science and Technology, 26(5), 805-813. doi: https://doi.org/10.3233/xst-18388
Van Griethuysen, J. J., Fedorov, A., Parmar, C., Hosny, A., Aucoin, N., Narayan, V., . . . Aerts, H. J. (2017). Computational Radiomics system to decode the radiographic phenotype. Cancer Research, 77(21), e104–e107. https://doi.org/10.1158/0008-5472.can-17-0339
World Health Organization (WHO). (2024, Eylül 4). Breast cancer. https://www.who.int/news-room/fact-sheets/detail/breast-cancer
Zhang, G., Zhao, K., Hong, Y., Qiu, X., Zhang, K., & Wei, B. (2021). SHA-MTL: Soft and hard attention multi-task learning for automated breast cancer ultrasound image segmentation and classification. International Journal of Computer Assisted Radiology and Surgery, 16(12), 1719-1725. https://doi.org/10.1007/s11548-021-02445-7
Zhang, W., Guo, Y., & Jin, Q. (2023). Radiomics and its feature selection: A review. Symmetry, 15(10), 1834. https://doi.org/10.3390/sym15101834
Zhang, X., Zhang, Y., Zhang, G., Qiu, X., Tan, W., Yin, X., & Liao, L. (2022). Deep learning with radiomics for disease diagnosis and treatment: Challenges and potential. Frontiers in Oncology, 12, 773840. https://doi.org/10.3389/fonc.2022.773840

Ayrıntılar

Birincil Dil

Türkçe

Konular

Takviyeli Öğrenme , Yapay Görme

Bölüm

Araştırma Makalesi

Yazarlar

Asuman Kaplan
0009-0004-9357-1773
Türkiye

Esra Kavadar
0009-0005-9548-7548
Türkiye

Mehmet Ali Altuncu ^*
0000-0002-2948-3937
Türkiye

Yayımlanma Tarihi

3 Mart 2025

Gönderilme Tarihi

8 Temmuz 2024

Kabul Tarihi

7 Kasım 2024

Yayımlandığı Sayı

Yıl 2025 Cilt: 28 Sayı: 1

DOI

https://doi.org/10.17780/ksujes.1512476

IZ

https://izlik.org/JA72UN59PA

Kaynak Göster

RIS / Bibtex

APA

Kaplan, A., Kavadar, E., & Altuncu, M. A. (2025). RADYOMİK ÖZELLİKLER VE MAKİNE ÖĞRENMESİ TEKNİKLERİYLE MEME TÜMÖRLERİNİN SINIFLANDIRILMASI. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(1), 38-50. https://doi.org/10.17780/ksujes.1512476

Cited By

MULTILAYER ANALYSIS OF NICOTINE-INDUCED GENE EXPRESSION ALTERATIONS IN BREAST CANCER CELLS USING CLUSTERING AND SUPERVISED LEARNING METHODS

Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi

https://doi.org/10.17780/ksujes.1730962