COVİD-19 HASTALIĞININ TEŞHİSİNDE DERİN ÖĞRENME VE VERİ MAHREMİYETİ

Year 2021, Volume: 9 Issue: 2, 701 - 715, 20.06.2021

Yavuz Canbay , Abdullah İsmetoğlu , Pelin Canbay

https://doi.org/10.21923/jesd.870263

Cited By: 1

Abstract

Covid-19 hastalığı, ortaya çıktığı günden bugüne birçok can kaybına yol açmıştır. Pandemi olarak ilan edilen bu hastalığa yakalanan kişilerde ciddi akciğer tahribatları oluşabilmektedir. Hekimlerin bu hastalığın teşhisinde akciğer özelinde çekilen bilgisayarlı tomografi (Computed Tomography - CT) ve X-Ray (Chest X-Ray - CXR) görüntülerini inceleyerek teşhis koydukları bilinmektedir. Bu CXR görüntülerinin çekildiği anda enfekte olduğu değerlendirilen kişilere hekim kontrolü öncesi yapılacak bir erken teşhis ile koruyucu önlemler hızlıca alınabilir ve hekimlerin hastalığı teşhis süreçleri kısaltılabilir. Diğer birçok hastalığın teşhisinde başarılı sonuçlar üreten yapay zekâ yöntemlerinin, Covid-19 hastalığında da başarılı sonuçlar ürettiği güncel çalışmalarda görülebilmektedir. Elde edilen başarılı sonuçların yanında, kullanılan sağlık verileri kişisel veri sınıfına girdiği için bu verilerin işlenmesinde ve analiz edilmesinde mahremiyet koruyucu önlemlere ihtiyaç olduğu açıktır. Gerek Kişisel Verileri Koruma Kanunu (KVKK) gerekse de Genel Veri Koruma Tüzüğü (General Data Protection Rule - GDPR), bu tür verilerin işlenmesinde mahremiyetin korunmasına özen gösterilmesi gerekliliğini ortaya koymaktadır. Bu çalışmada, Covid-19 hastalığını tespit eden yapay zekâ odaklı çalışmalar incelenmiş, kullanılan açık veri kümeleri sunulmuş, Covid-19 hastalığının tespitinde mahremiyeti dikkate alan çalışmalar gözden geçirilerek genel değerlendirmelerde bulunulmuştur.

Keywords

Yapay Zekâ, Derin Öğrenme, Veri Mahremiyeti, Covid-19, Araştırma

Supporting Institution

Kahramanmaraş Sütçü İmam Üniversitesi Bilimsel Araştırma Projeleri Koordinasyon Birimi

Project Number

2020/7-22 M

Thanks

Bu çalışma Kahramanmaraş Sütçü İmam Üniversitesi Bilimsel Araştırma Projeleri Koordinasyon Birimince desteklenmiştir. Proje Numarası: 2020/7-22 M. Bu çalışmaya verdikleri destekten dolayı Kahramanmaraş Sütçü İmam Üniversitesi Data Vision Laboratuvarına (datavision.ksu.edu.tr) teşekkür ederiz.

DEEP LEARNING AND DATA PRIVACY IN DIAGNOSIS OF COVID-19

Abstract

Covid-19 disease has caused many mortalities since the day it emerged. People who suffer from this disease are more likely to have serious lung damages. It is known that physicians diagnose this disease by examining computed tomography (CT) and X-Ray (Chest X-Ray - CXR) images of the lung. At the moment these CXR images are taken, preventive measures can be taken quickly with an early diagnosis before physician control the people who are considered to be infected, and in addition, physicians' diagnosis processes can be shortened. It can be seen from the literature that artificial intelligence methods have produced successful results in the diagnosis of Covid-19 disease. Besides the successful results, it is a fact that since the health data is classified as personal data, privacy preserving measures are required in the processing and analysis of these data. Both Personal Data Protection Law and General Data Protection Rule (GDPR) reveal the need to focus on preserving privacy in the processing of these data. In this study, studies focusing on artificial intelligence to detect Covid-19 disease were examined, the open data sets used in the literature were presented, studies considering privacy in the detection of Covid-19 were investigated and general evaluations were presented.

Keywords

Artificial Intelligence, Deep Learning, Data Privacy, Covid-19, Review

Project Number

2020/7-22 M

References

• Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016). Deep Learning With Differential Privacy. Paper presented at the Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security.
• Akkuş, M. S. (2020). Koranavirüs ve Covid-19. Aksaray Üniversitesi Tıp Bilimleri Dergisi, 1(2), 15-20.
• Alafi, B. (2019). Artifıcial Intelligence And Deep Learning Methodologies. The Journal of Cognitive Systems, 4(2), 57-61.
• Alamo, T., Reina, D. G., Mammarella, M., & Abella, A. (2020). Covid-19: Open-data resources for monitoring, modeling, and forecasting the epidemic. Electronics, 9(5), 827.
• Albert Sun, N. (2020, Erişim Tarihi: 05.10.2020). NY-Times Covid-19 USA Dataset. İnternet Sayfası: https://github.com/nytimes/covid-19-data
• Aydoğan, M., & Karci, A. (2020). Spelling Correction with the Dictionary Method for the Turkish Language Using Word Embeddings. Avrupa Bilim ve Teknoloji Dergisi, 57-63.
• Badr, H. S. (2020, Erişim Tarihi: 04.10.2020). Covid-19 Unified-Dataset. İnternet Sayfası: https://github.com/CSSEGISandData/COVID-19_Unified-Dataset
• Beimel, A., Nissim, K., & Stemmer, U. (2013). Private Learning And Sanitization: Pure vs. Approximate Differential Privacy. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (pp. 363-378): Springer.
• Britz, D. (2015, Erişim Tarihi: 28.11.2020). Recurrent Neural Networks Tutorial, Part 1 – Introduction To RNNs. İnternet Sayfası: http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/
• Canbay, P. (2020). Sağlıkta Yapay Zekâ: Derin Öğrenme Teknikleri ve Uygulamaları. In K. D. Ahmet Rıza Şahin, Süleyman Sivri (Ed.), Sağlık Bilimlerinde Yapay Zekâ (pp. 25-39): Akademisyen Kitabevi.
• Canbay, Y. (2019). Aykırı Veri Yönelimli Fayda Temelli Büyük Veri Anonimleştirme Modeli. (Doktora Tezi), Gazi Üniversitesi,
• Canbay, Y., & Sağıroğlu, Ş. (2020). Derin Öğrenmede Diferansiyel Mahremiyet. Uluslararası Bilgi Güvenliği Mühendisliği Dergisi, 6(1), 1-16.
• Canbay, Y., Vural, Y., & Sağıroğlu, Ş. (2020). Mahremiyet Korumalı Büyük Veri Yayınlama İçin Kavramsal Model Önerileri. Politeknik Dergisi, 23(3), 785-798.
• Chung, A. G. (2020, Erişim Tarihi: 20.10.2020). Figure1-Covid-Chestxray-Dataset. İnternet Sayfası: https://github.com/agchung/Figure1-COVID-chestxray-dataset
• Coşkun, M., Yıldırım, Ö., Uçar, A., & Demir, Y. (2017). An Overview Of Popular Deep Learning Methods. European Journal of Technic (EJT), 165-176.
• De Campos, L. M. L. (2017). Time Series Prediction With Direct And Recurrent Neural Networks. Turkish Journal of Forecasting, 1(1), 7-15.
• Di Pietro, G., Biagi, F., Costa, P., Karpiński, Z., & Mazza, J. (2020). The likely impact of COVID-19 on education: Reflections based on the existing literature and recent international datasets (Vol. 30275): Publications Office of the European Union.
• Dokuz, Y., & Tüfekci, Z. (2020). Investigation Of The Effect Of LSTM Hyperparameters On Speech Recognition Performance. Avrupa Bilim ve Teknoloji Dergisi, 161-168.
• Dülger, M. V. (2015). Sağlık Hukukunda Kişisel Verilerin Korunması Ve Hasta Mahremiyeti. İstanbul Medipol Üniversitesi Hukuk Fakültesi Dergisi, 1(2), 43-80.
• Dwork, C. (2006). Differential Privacy. Paper presented at the International Colloquium on Automata, Languages and Programming, Berlin, Heidelberg.
• Erçin, Ö. (2018, Erişim Tarihi: 23.11.2020). Differential Privacy (Diferansiyel Gizlilik ve Mahremiyet). İnternet Sayfası: http://ozdenercin.com/2018/09/19/differential-privacy-diferansiyel-gizlilik-ve-mahremiyet/
• Farooq, M., & Hafeez, A. (2020). Covid-Resnet: A deep Learning Framework For Screening Of Covid19 From Radiographs. arXiv preprint arXiv:2003.14395.
• Fukushima, K. (1980). Neocognitron: A Self-organizing Neural Network Model for a Mechanism. Biol. Cybernetics 36, 193-202.
• Geambasu, R., Kohno, T., Levy, A. A., & Levy, H. M. (2009). Vanish: Increasing Data Privacy with Self-Destructing Data. Paper presented at the 18th USENIX Security Symposium, Washington.
• Gianfrancesco, M. A., Hyrich, K. L., Gossec, L., Strangfeld, A., Carmona, L., Mateus, E. F., . . . Bhana, S. (2020). Rheumatic disease and COVID-19: initial data from the COVID-19 global rheumatology alliance provider registries. The Lancet Rheumatology, 2(5), e250-e253.
• Goldbloom, A. (2020, Erişim Tarihi: 10.12.2020). Covid-19 Data From John Hopkins University Dataset. İnternet Sayfası: https://www.kaggle.com/antgoldbloom/covid19-data-from-john-hopkins-university
• Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y. (2016). Deep learning (Vol. 1): MIT press Cambridge.
• Hall, L. O., Paul, R., Goldgof, D. B., & Goldgof, G. M. (2020). Finding Covid-19 from Chest X-rays using Deep Learning on a Small Dataset. arxiv:2004.02060.
• Hemdan, E. E.-D., Shouman, M. A., & Karar, M. E. (2020). Covidx-Net: A Framework Of Deep Learning Classifiers To Diagnose Covid-19 In X-Ray Images. arXiv preprint arXiv:2003.11055.
• Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural computation, 9(8), 1735-1780.
• Hu, S., Gao, Y., Niu, Z., Jiang, Y., Li, L., Xiao, X., . . . Xia, J. (2020). Weakly Supervised Deep Learning For Covid-19 Infection Detection And Classification From CT Images. IEEE Access, 8, 118869-118883.
• IEEE. (2020, Erişim Tarihi: 05.12.2020). IEEE8023 Covid-19 Chest X-ray. İnternet Sayfası: https://github.com/ieee8023/covid-chestxray-dataset
• Institute, A. (2020, Erişim Tarihi: 05.12.2020). Covid-19 Open Research Dataset Challenge (CORD-19). İnternet Sayfası: https://www.kaggle.com/allen-institute-for-ai/CORD-19-research-challenge?select=metadata.csv
• Jain, P., Gyanchandani, M., & Khare, N. (2016). Big Data Privacy: A Technological Perspective And Review. Journal of Big Data, 3(1), 25.
• Karaküçük, Y., & Eker, S. (2020). Sağlık Bilimlerinde Yapay Zekâ. In Oftalmolojide Yapay Zeka ve Derin Öğrenme Uygulamaları (pp. 123-143): Akademisyen Kitabevi.
• Kerr, G. H., Badr, H. S., Gardner, L. M., Perez-Saez, J., & Zaitchik, B. F. (2021). Associations between meteorology and COVID-19 in early studies: Inconsistencies, uncertainties, and recommendations. One Health, 12, 100225.
• Kimanuka, U. A., & Büyük, O. (2018). Turkish Speech Recognition Based On Deep Neural Networks. Journal of Natural & Applied Sciences.
• Kişisel Verileri Koruma Kurumu. (2020, Erişim Tarihi: 23.10.2020). Kamuoyu Duyurusu (Covid-19 İle Mücadelede Konum Verisinin İşlenmesi ve Kişilerin Hareketliliklerinin İzlenmesi Hakkında Bilinmesi Gerekenler). İnternet Sayfası: https://www.kvkk.gov.tr/Icerik/6726/COVID-19-ILE-MUCADELEDE-KONUM-VERISININ-ISLENMESI-VE-KISILERIN-HAREKETLILIKLERININ-IZLENMESI-HAKKINDA-BILINMESI-GEREKENLER-2-
• Ko, H., Chung, H., Kang, W. S., Kim, K. W., Shin, Y., Kang, S. J., . . . Jung, H. (2020). Covid-19 pneumonia Diagnosis Using A Simple 2D Deep Learning Framework With A Single Chest CT Image: Model Development And Validation. Journal of Medical Internet Research, 22(6), e19569.
• Kobayashi, G., Sugasawa, S., Tamae, H., & Ozu, T. (2020). Predicting intervention effect for COVID-19 in Japan: state space modeling approach. BioScience Trends.
• Latifoğlu, L., & Nuralan, K. B. (2020). Tekil Spektrum Analizi ve Uzun-Kısa Süreli Bellek Ağları ile Nehir Akım Tahmini. Avrupa Bilim ve Teknoloji Dergisi, 376-381.
• Lecun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.
• LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 2278 - 2324.
• Levitt, M., Scaiewicz, A., & Zonta, F. (2020). Predicting the trajectory of any COVID19 epidemic from the best straight line. medRxiv.
• Li, N., Li, T., & Venkatasubramanian, S. (2007). t-Closeness: Privacy Beyond k-Anonymity And l-Diversity. Paper presented at the 2007 IEEE 23rd International Conference on Data Engineering.
• Lira, C. (2020, Erişim Tarihi: 05.12.2020). Covid-19 Mexico Dataset. İnternet Sayfası: https://www.kaggle.com/carloslira/covid19-mexico
• Lisphilar. (2020, Erişim Tarihi: 10.12.2020). Covid-19 Dataset In Japan. İnternet Sayfası: https://www.kaggle.com/lisphilar/covid19-dataset-in-japan
• Machanavajjhala, A., Kifer, D., Gehrke, J., & Venkitasubramaniam, M. (2007). l-Diversity: Privacy Beyond k-Anonymity. ACM Transactions on Knowledge Discovery from Data (TKDD), 1(1), 3-es.
• Mavragani, A. (2020). Tracking COVID-19 in Europe: infodemiology approach. JMIR public health and surveillance, 6(2), e18941.
• Medel-Ramírez, C., & Medel-Lopez, H. (2020). Data Mining for the Study of the Epidemic (SARS-CoV-2) COVID-19: Algorithm for the Identification of Patients (SARS-CoV-2) COVID 19 in Mexico. Available at SSRN 3619549.
• Metin, İ. A., & Karasulu, B. (2015). İnsan Aktivitelerinin Sınıflandırılmasında Tekrarlayan Sinir Ağı Kullanan Derin Öğrenme Tabanlı Yaklaşım. Veri Bilimi, 2(2), 1-10.
• Minaee, S., Kafieh, R., Sonka, M., Yazdani, S., & Soufi, G. J. (2020). Deep-Covid: Predicting Covid-19 From Chest X-Ray Images Using Deep Transfer Learning. arXiv preprint arXiv:2004.09363.
• Mooney, P. (2020a, Erişim Tarihi: 08.12.2020). Kaggle, Pneumonia Sample X-Rays. İnternet Sayfası: https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
• Mooney, P. (2020b, Erişim Tarihi: 06.12.2020). San Francisco Covid-19 Data. İnternet Sayfası: https://www.kaggle.com/paultimothymooney/san-francisco-covid19-data
• Müftüoğlu, Z., Kizrak, M. A., & Yıldırım, T. (2020). Differential Privacy Practice On Diagnosis of Covid-19 Radiology Imaging Using EfficientNet. Paper presented at the 2020 International Conference on INnovations in Intelligent SysTems and Applications (INISTA).
• Nabiyev, V. V. (2012). Yapay Zekâ: Seçkin Yayıncılık.
• Narin, A., Kaya, C., & Pamuk, Z. (2020). Automatic Detection Of Coronavirus Disease (Covid-19) Using X-Ray Images And Deep Convolutional Neural Networks. arXiv preprint arXiv:2003.10849.
• Olah, C. (2015, Erişim Tarihi: 06.12.2020). Understanding LSTM Networks. İnternet Sayfası: http://colah.github.io/posts/2015-08-Understanding-LSTMs
• Onan, A. (2020). Evrişimli Sinir Ağı Mimarilerine Dayalı Türkçe Duygu Analizi. Avrupa Bilim ve Teknoloji Dergisi, 374-380.
• Pengtao Xie, J. S., Jinyu Zhao. (2020, Erişim Tarihi: 28.11.2020). GitHub UCSD-AI4H / Covid-CT. İnternet Sayfası: https://github.com/UCSD-AI4H/COVID-CT
• Prakash, K. B., Imambi, S. S., Ismail, M., Kumar, T. P., & Pawan, Y. (2020). Analysis, prediction and evaluation of covid-19 datasets using machine learning algorithms. International Journal, 8(5).
• Rabbah, J., Ridouani, M., & Hassouni, L. (2020). A New Classification Model Based on Stacknet and Deep Learning for Fast Detection of COVID 19 Through X Rays Images. Paper presented at the 2020 Fourth International Conference On Intelligent Computing in Data Sciences (ICDS).
• Rajkumar, S. (2020a, Erişim Tarihi: 20.12.2020). Covid-19 India Dataset. İnternet Sayfası: https://www.kaggle.com/sudalairajkumar/covid19-in-india
• Rajkumar, S. (2020b, Erişim Tarihi: 05.12.2020). Novel Coronavirus 2019 Dataset. İnternet Sayfası: https://www.kaggle.com/sudalairajkumar/novel-corona-virus-2019-dataset
• Rodrigues, P. (2020, Erişim Tarihi: 04.12.2020). Covid-19 – Kaggle: Chest X-Ray (normal). İnternet Sayfası: https://data.mendeley.com/datasets/rscbjbr9sj/2
• Sharma, S. (2020). Drawing insights from COVID-19-infected patients using CT scan images and machine learning techniques: a study on 200 patients. Environmental Science and Pollution Research, 27(29), 37155-37163.
• Sun, Z., Wang, Y., Shu, M., Liu, R., & Zhao, H. (2019). Differential Privacy for Data and Model Publishing of Medical Data. IEEE, 152103-152114.
• Sweeney, L. (2002). k-Anonymity: A Model For Protecting Privacy. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 10(05), 557-570.
• Tails, H. (2020, Erişim Tarihi: 06.12.2020). Covid-19 Tracking Germany Dataset. İnternet Sayfası: https://www.kaggle.com/headsortails/covid19-tracking-germany
• Tan, Z. (2019). Derin Öğrenme Yardımıyla Araç Sınıflandırma. (Yüksek Lisans Tezi), Fırat Üniversitesi,
• Toğaçar, M., Ergen, B., & Cömert, Z. (2020). Covid-19 Detection Using Deep Learning Models To Exploit Social Mimic Optimization And Structured Chest X-Ray Images Using Fuzzy Color And Stacking Approaches. Computers in Biology and Medicine, 103805.
• Union, E. (2020, Erişim Tarihi: 20.12.2020). European Union Open Covid-19 Coronavirus Dataset. İnternet Sayfası: https://data.europa.eu/euodp/en/data/dataset/covid-19-coronavirus-data
• Var, E., & İnan, A. (2018). Sınıflandırma İçin Diferansiyel Mahremiyete Dayalı Öznitelik Seçimi. Journal of the Faculty of Engineering & Architecture of Gazi University, 33(1).
• Vural, Y. (2018). Veri Mahremiyeti: Saldırılar, Korunma ve Yeni bir Çözüm Önerisi Uluslararası Bilgi Güvenliği Mühendisliği Dergisi, 4(2), 21-34.
• Wang, L., Lin, Z. Q., & Wong, A. (2020). Covid-Net: A Tailored deep Convolutional Neural Network Design For Detection Of Covid-19 Cases From Chest X-Ray Images. Scientific Reports, 10(1), 1-12.
• Wang, L. L., Lo, K., Chandrasekhar, Y., Reas, R., Yang, J., Eide, D., . . . Merrill, W. (2020). Cord-19: The covid-19 open research dataset. ArXiv.
• Wang, S., Kang, B., Ma, J., Zeng, X., Xiao, M., Guo, J., . . . Meng, X. (2020). A Deep Learning Algorithm Using CT Images To Screen For Corona Virus Disease (Covid-19). medRxiv.
• Wang, S., Zha, Y., Li, W., Wu, Q., Li, X., Niu, M., . . . Yu, H. (2020). A Fully Automatic Deep Learning System For Covid-19 Diagnostic And Prognostic Analysis. European Respiratory Journal.
• Wong, A., Qiu Lin, Z., Wang, L., Chung, A. G., Shen, B., Abbasi, A., . . . Duong, T. Q. (2020). COVIDNet-S: Towards computer-aided severity assessment via training and validation of deep neural networks for geographic extent and opacity extent scoring of chest X-rays for SARS-CoV-2 lung disease severity. arXiv e-prints, arXiv: 2005.12855.
• World Health Organization. (2021, Erişim Tarihi: 20.03.2021). WHO Coronavirus Disease (COVID-19) Dashboard. İnternet Sayfası: https://covid19.who.int/
• Xu, L., Jiang, C., Wang, J., Yuan, J., & Ren, Y. (2014). Information Security in Big Data: Privacy and Data Mining. IEEE Access, 1149 - 1176.
• Zarikas, V., Poulopoulos, S. G., Gareiou, Z., & Zervas, E. (2020). Clustering analysis of countries using the COVID-19 cases dataset. Data in brief, 31, 105787.
• Zhang, J., Xie, Y., Liao, Z., Pang, G., Verjans, J., Li, W., Shen, C. (2020). Viral Pneumonia Screening On Chest X-Ray Images Using Confidence-Aware Anomaly Detection. arXiv preprint arXiv:2003.12338.