A Review About Radiomics with Artificial Intelligence Methods in Breast Cancer Diagnosis and Prognosis

Abstract

According to the 2020 World Health Organization report on cancer disease, breast cancer is one of the most frequent cancer types. Early diagnosis and treatment are important for higher survival rates and better quality of life. In the diagnosis of breast cancer, radiomics is a new and popular research topic. Radiomics works on the numerical features of images obtained by radiographic imaging modalities such as magnetic resonance imaging (MRI), mammography, ultrasound (US) or positron emission tomography / computed tomography (PET / CT). Radiogenomics tries to associate the radiomics data with genomics data which may improve diagnosis, prognosis and prediction of cancer. Multidimensional large datasets are obtained by extracting large amount of candidative features from the radiographic images. Feature selection is an important task to remove non-valuable features to improve classification accuracy. Using feature selection methods, most valuable features are obtained and classified by using machine learning or deep learning methods to diagnose and prognose cancer. Recently many researchers have studied to develop radiomics models using quantitative “-omics” data with the rapid development of the use of artificial intelligence methods in the field of medicine. This review aims to provide a literature survey of radiomics and radiogenomics models with machine learning and deep learning methods in breast cancer diagnosis and prognosis. We review research papers published between 2012 and 2020 and represent the radiographic imaging modalities, radiomic feature extraction methods, radiomic feature selection methods and classification methods using machine learning and deep learning algortihms. Finally, we discuss the challenges and propose some future research directions of breast cancer radiomics models. 

Keywords

• Breast Cancer
• Deep Learning
• Machine Learning
• Radiogenomics
• Radiomics

Meme Kanseri Teşhis ve Prognozunda Radiomics ile Yapay Zeka Yöntemleri Kullanımı Hakkında Bir İnceleme

Öz

Dünya Sağlık Örgütünün 2020 kanser hastalığı raporuna göre meme kanseri en sık görülen kanser türlerinden biridir. Erken teşhis ve tedavi daha yüksek yaşam şansı ve daha iyi bir yaşam kalitesi için önemlidir. Radiomics, meme kanseri tanısında ve prognozunda yeni ve popüler bir araştırma alanıdır. Manyetik rezonans görüntüleme (MR), mamografi, ultrason (US) ve pozitron emüsyon tomografi / bilgisayarlı tomografi (PET / CT) gibi radyografik görüntüleme yöntemleri ile elde edilen görüntülerin sayısal özellikleri üzerinde çalışır. Radiogenomics ise radiomics veriyi kanserin teşhisi, prognozu ve tahmini destekleyecek çok sayıda genomics veri ile ilişkilendirmeye çalışır. Elde edilen radyografik görüntülerden büyük miktarda kandidatif veri çıkarılarak çok boyutlu büyük veri setleri elde edilir. Nitelik seçimi sınıflandırma doğruluğunu artırmak için değersiz nitelikleri veri setinden çıkaran önemli bir işlevdir. Nitelik seçim yöntemleri ile ayrılan değerli nitelikler makine öğrenme ya da derin öğrenme yöntemleri ile kanserin yakalanması, teşhisi, prognozun değerlendirilmesi amacıyla sınıflandırılır. Son yıllarda birçok araştırmacı yapay zeka yöntemlerinin tıp alanında kullanımının hızla gelişmesiyle bu kantitatif -omics verileri ile radiomics modeller geliştirmek amacıyla çok sayıda çalışma yapmışlardır. Bu inceleme, meme kanseri tanı ve prognozunda makine öğrenme ve derin öğrenme yöntemleri ile kullanılan radiomics ve radiogenomics modelleri hakkında literatür taraması yapmayı amaçlamaktadır. 2012 ile 2020 arasındaki araştırma makaleleri incelenmiş ve radyografik görüntüleme yöntemleri, radiomic nitelik çıkarma yöntemleri, nitelik seçme yöntemleri ve makine öğrenme ve derin öğrenme algoritmalarını kullanarak sınıflandırma yöntemleri sunulmuştur. Son olarak, meme kanseri radiomics modellerinin zorluklarını tartışıyor ve geleceteki bazı araştırma konularını öneriyoruz.

Anahtar Kelimeler

• Derin Öğrenme
• Makine Öğrenme
• Meme kanseri
• Radiogenomics
• Radiomics

References

1. Chandrashekar, G., & Sahin, F. (2014). A survey on feature selection methods. Computers & Electrical Engineering, 40(1), 16–28. https://doi.org/10.1016/j.compeleceng.2013.11.024
2. Deniz, A., Kiziloz, H. E., Dokeroglu, T., & Cosar, A. (2017). Robust multiobjective evolutionary feature subset selection algorithm for binary classification using machine learning techniques. Neurocomputing, 241, 128–146. https://doi.org/10.1016/J.NEUCOM.2017.02.033
3. Ferlay, J., Colombet, M., Soerjomataram, I., Mathers, C., Parkin, D. M., Piñeros, M., … Bray, F. (2019, Nisan 15). Estimating the global cancer incidence and mortality in 2018: GLOBOCAN sources and methods. International Journal of Cancer. Wiley-Liss Inc. https://doi.org/10.1002/ijc.31937
4. Gierach, G. L., Li, H., Loud, J. T., Greene, M. H., Chow, C. K., Lan, L., … Giger, M. L. (2014). Relationships between computer-extracted mammographic texture pattern features and BRCA1/2 mutation status: A cross-sectional study. Breast Cancer Research, 16(4), 424. https://doi.org/10.1186/s13058-014-0424-8
5. Gillies, R. J., Kinahan, P. E., & Hricak, H. (2016). Radiomics: Images Are More than Pictures, They Are Data. Radiology, 278(2), 563–577. https://doi.org/10.1148/radiol.2015151169
6. Grimm, L. J., & Mazurowski, M. A. (2020, Ocak 1). Breast Cancer Radiogenomics: Current Status and Future Directions. Academic Radiology. Elsevier USA. https://doi.org/10.1016/j.acra.2019.09.012
7. Guo, Y., Hu, Y., Qiao, M., Wang, Y., Yu, J., Li, J., & Chang, C. (2018). Radiomics Analysis on Ultrasound for Prediction of Biologic Behavior in Breast Invasive Ductal Carcinoma. Clinical Breast Cancer, 18(3), e335–e344. https://doi.org/10.1016/j.clbc.2017.08.002
8. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Içinde Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (C. 2016-Decem, ss. 770–778). https://doi.org/10.1109/CVPR.2016.90

9. Herent, P., Schmauch, B., Jehanno, P., Dehaene, O., Saillard, C., Balleyguier, C., … Jégou, S. (2019). Detection and characterization of MRI breast lesions using deep learning. Diagnostic and Interventional Imaging, 100(4), 219–225. https://doi.org/10.1016/j.diii.2019.02.008
10. Kira, K., & Rendell, L. A. (1992). A Practical Approach to Feature Selection. Içinde Machine Learning Proceedings 1992 (ss. 249–256). Elsevier. https://doi.org/10.1016/B978-1-55860-247-2.50037-1
11. Lambin, P., Rios-Velazquez, E., Leijenaar, R., Carvalho, S., Van Stiphout, R. G. P. M., Granton, P., … Aerts, H. J. W. L. (2012). Radiomics: Extracting more information from medical images using advanced feature analysis. European Journal of Cancer, 48(4), 441–446. https://doi.org/10.1016/j.ejca.2011.11.036
12. Li, H., Giger, M. L., Huynh, B. Q., & Antropova, N. O. (2017). Deep learning in breast cancer risk assessment: evaluation of convolutional neural networks on a clinical dataset of full-field digital mammograms. Journal of Medical Imaging, 4(04), 1. https://doi.org/10.1117/1.jmi.4.4.041304
13. Li, H., Giger, M. L., Lan, L., Janardanan, J., & Sennett, C. A. (2014). Comparative analysis of image-based phenotypes of mammographic density and parenchymal patterns in distinguishing between BRCA1/2 cases, unilateral cancer cases, and controls . Journal of Medical Imaging, 1(3), 031009. https://doi.org/10.1117/1.jmi.1.3.031009
14. M. Heath, K. Bowyer, D. Kopans, R. M. and P. K. J. (2001). The Digital Database for Screening Mammography. Içinde the Fifth International Workshop on Digital Mammography, M.J. Yaffe, ed., Medical Physics Publishing, 2001. (ss. 212–218). https://doi.org/ISBN 1-930524-00-5
15. Mazurowski, M. A., Zhang, J., Grimm, L. J., Yoon, S. C., & Silber, J. I. (2014). Radiogenomic analysis of breast cancer: Luminal B molecular subtype is associated with enhancement dynamics at MR imaging. Radiology, 273(2), 365–372. https://doi.org/10.1148/radiol.14132641
16. Moreira, I. C., Amaral, I., Domingues, I., Cardoso, A., Cardoso, M. J., & Cardoso, J. S. (2012). INbreast: Toward a Full-field Digital Mammographic Database. Academic Radiology, 19(2), 236–248. https://doi.org/10.1016/j.acra.2011.09.014
17. Parekh, V., & Jacobs, M. A. (2016). Radiomics: a new application from established techniques. Expert Review of Precision Medicine and Drug Development. https://doi.org/10.1080/23808993.2016.1164013
18. Parekh, V. S., & Jacobs, M. A. (2019, Mart 4). Deep learning and radiomics in precision medicine. Expert Review of Precision Medicine and Drug Development. Taylor and Francis Ltd. https://doi.org/10.1080/23808993.2019.1585805
19. Ribli, D., Horváth, A., Unger, Z., Pollner, P., & Csabai, I. (2018). Detecting and classifying lesions in mammograms with Deep Learning. Scientific Reports, 8(1), 1–7. https://doi.org/10.1038/s41598-018-22437-z
20. Rodriguez-Ruiz, A., Lång, K., Gubern-Merida, A., Broeders, M., Gennaro, G., Clauser, P., … Sechopoulos, I. (2019). Stand-Alone Artificial Intelligence for Breast Cancer Detection in Mammography: Comparison With 101 Radiologists. Journal of the National Cancer Institute, 111(9), 916–922. https://doi.org/10.1093/jnci/djy222
21. Saha, A., Harowicz, M. R., Grimm, L. J., Kim, C. E., Ghate, S. V., Walsh, R., & Mazurowski, M. A. (2018). A machine learning approach to radiogenomics of breast cancer: A study of 922 subjects and 529 dce-mri features. British Journal of Cancer, 119(4), 508–516. https://doi.org/10.1038/s41416-018-0185-8
22. Sun, Q., Lin, X., Zhao, Y., Li, L., Yan, K., Liang, D., … Li, Z. C. (2020). Deep Learning vs. Radiomics for Predicting Axillary Lymph Node Metastasis of Breast Cancer Using Ultrasound Images: Don’t Forget the Peritumoral Region. Frontiers in Oncology, 10. https://doi.org/10.3389/fonc.2020.00053
23. World Health Organization. (2020). WHO. Tarihinde adresinden erişildi https://www.who.int/cancer/country-profiles/Global_Cancer_Profile_2020.pdf
24. Xue, B., Zhang, M., Browne, W. N., & Yao, X. (2016). A Survey on Evolutionary Computation Approaches to Feature Selection. IEEE Transactions on Evolutionary Computation, 20(4), 606–626. https://doi.org/10.1109/TEVC.2015.2504420
25. Yamamoto, S., Maki, D. D., Korn, R. L., & Kuo, M. D. (2012). Radiogenomic analysis of breast cancer using MRI: A preliminary study to define the landscape. American Journal of Roentgenology, 199(3), 654–663. https://doi.org/10.2214/AJR.11.7824
26. Zhao, X., Li, D., Yang, B., Chen, H., Yang, X., Yu, C., & Liu, S. (2015). A two-stage feature selection method with its application. Computers & Electrical Engineering, 47, 114–125. https://doi.org/10.1016/J.COMPELECENG.2015.08.011