A Cloud-based Framework to Secure Medical Image Processing
Keywords:
Cloud computing, medical image processing, security, segmentation, genetic algorithmsAbstract
In the last few years, advanced software for processing medical images has gained a great interest in modern medicine. In fact, it provides valuable clinical information, and hence, can significantly improve diagnosis and treatment. Nevertheless, implementing these imaging tools often requires an important capital budget in both IT applications and hardware. This solution can unfortunately cause a dramatic increase in operational expenses and medical costs. To mitigate this problem, medical providers are shifting their interest onto using cloud computing, particularly the Software-as-a-Service (SaaS) model, instead of in-house data centres. In this case, healthcare professionals rely on remote applications delivered by an external provider to process patients’ digital records. Interestingly, in this paradigm, consumers are billed based on software utilization. Besides, cloud computing promises to offer a better Quality of Service (QoS), including availability, elasticity, trust, response time, security assurance, etc. Regardless of its significant financial benefits, the transition to the cloud environment gives rise to security and privacy problems, especially in the healthcare domain. Recently, various security measures and mechanisms have been suggested to overcome these challenges and accelerate the adoption of cloud computing services. In this regard, numerous cryptographic techniques are used to safely process digital medical images, techniques that make use of homomorphic cryptosystems, Secret Sharing Schemes (SSS), Service-Oriented Architecture (SOA) and Secure Multi-party Computation (SMC). Although these methods are deemed very promising, they can negatively impact the performance of cloud services. Most precisely, they are not yet mature enough to satisfy Service Level Agreement (SLA) constraints. The main contribution of this study consists of presenting a novel approach to secure cloud-based medical image processing. This proposed solution combines segmentation techniques and genetic algorithms together in one model. Based on this method, we rely on pixel intensity and entropy measurements to split an image into a number of regions to maintain data privacy. The principal reason for using genetic algorithms is to optimize the number of generated regions. Furthermore, we opt for an architecture based on multi-cloud systems and CloudSec module to enable distributed data processing and prevent accidental disclosure of medical information. As shown in the simulation results, the proposal is an appropriate framework for fuelling the integration of cloud applications in the healthcare sector. In particular, it enables clients to securely use remote image processing tools.
Downloads
References
Liu, F., Tong, J., Mao, J., Bohn, R., Messina, J., Badger, L., and Leaf,
D. (2011). NIST cloud computing reference architecture. NIST Special
Publication, 500(2011), 1–28.
Birje, M. N., Challagidad, P. S., Goudar, R. H., and Tapale, M. T. (2017).
Cloud computing review: concepts, technology, challenges and security.
International Journal of Cloud Computing, 6(1), 32–57.
Kumar, P. R., Raj, P. H., and Jelciana, P. (2017). Exploring Security Issues
and Solutions in Cloud Computing Services–A Survey. Cybernetics and
Information Technologies, 17(4), 3–31.
Noman, A., and Adams, C. (2013). Providing a data location assurance
service for cloud storage environments. Journal of Mobile Multimedia,
(4), 265–286.
Singh, A., and Chatterjee, K. (2017). Cloud security issues and challenges:
A survey. Journal of Network and Computer Applications, 79,
–115.
Radwan, T., Azer, M. A. and Abdelbaki, N. (2017). Cloud Computing
Security: challenges and future trends. International Journal of Computer
Applications in Technology, 55(2), 158 –172.
Kaur, K., Sharma, D. R., and Kahlon, D. R. (2017). Interoperability
and Portability Approaches in Inter-Connected Clouds: A Review. ACM
Computing Surveys (CSUR), 50(4), 49.
Tran, H. M., Ha, S. V. U., Dang, H. T., and Huynh, K. V. (2014).
Fault resolution system for inter-cloud environment. Journal of Mobile
Multimedia, 10(1&2), 16–29.
Shirazi, F., Seddighi, A., and Iqbal, A. (2017). Cloud Computing Security
and Privacy:AnEmpirical Study. In International Conference on Human-
Computer Interaction (pp. 534–549). Springer, Cham.
Kumar, P. R., Raj, P. H., and Jelciana, P. (2018). Exploring data security
issues and solutions in cloud computing. Procedia Computer Science,
, 691–697.
Yüksel, B., Küpçü, A., and Özkasap, Ö. (2017). Research issues for
privacy and security of electronic health services. Future Generation
Computer Systems, 68, 1–13.
Anjum, A., Malik, S. R, Choo, K. R., Khan, A., Haroon, A., Khan,
S., Khan, S. U., Ahmed, N. and Raza, B. (2018). An efficient privacy
mechanism for electronic health records. Computers & Security, 72,
–211.
Marwan, M., Kartit, A., and Ouahmane, H. (2018). A Framework
to Secure Medical Image Storage in Cloud Computing Environment.
Journal of Electronic Commerce in Organizations (JECO), 16(1), 1–16.
Shamir, A. (1979). How to share a secret. Communications of the ACM,
(11), 612–613.
Cheraghi, A. (2014). Sharing several secrets based on Lagrange’s interpolation
formula and Cipher feedback mode. International Journal of
Nonlinear Analysis and Applications, 5(2), 60–66.
Deepthi, S., Lakshmi,V. S., and Deepthi, P. P. (2017). Image processing in
encrypted domain for distributed storage in cloud. In International Conference
onWireless Communications, Signal Processing and Networking
(WiSPNET), (pp. 1478–1482). IEEE.
Lathey, A., and Atrey, P. K. (2015). Image enhancement in encrypted
domain over cloud. ACM Transactions on Multimedia Computing,
Communications, and Applications (TOMM), 11(3), 38.
Paillier, P. (1999). Public-key cryptosystems based on composite degree
residuosity classes. In International Conference on the Theory and Applications
of Cryptographic Techniques (pp. 223–238). Springer, Berlin,
Heidelberg.
Ziad, M. T. I., Alanwar, A., Alzantot, M., and Srivastava, M. (2016).
Cryptoimg: Privacy preserving processing over encrypted images. In
IEEE Conference on Communications and Network Security (CNS),
(pp. 570–575). IEEE.
Hu, X., Zhang, W., Li, K., Hu, H., and Yu, N. (2016). Secure nonlocal
denoising in outsourced images. ACM Transactions on Multimedia
Computing, Communications, and Applications (TOMM), 12(3), 40.
Vaida, M. F., Todica, V., and Cremene, M. (2008). Service oriented
architecture for medical image processing. International Journal of
Computer Assisted Radiology and Surgery, 3(3–4), 363–369.
Shen, C., Zhao, Y., and Chen, L. (2013). Galaxie: a P2P based EDSOA
platform for cloud services. In Proceedings Demo & Poster Track of
ACM/IFIP/USENIX International Middleware Conference (p. 9). ACM.
Sadeghi, A. R., Schneider, T., and Wehrenberg, I. (2009). Efficient
privacy-preserving face recognition. In International Conference on
Information Security and Cryptology (pp. 229–244). Springer, Berlin,
Heidelberg.
Avidan, S. and Butman, M. (2006). Efficient Methods for Privacy Preserving
Face Detection, in NIPS’06: the 19th International Conference
on Neural Information Processing Systems, (Canada, 2006), 57–64.
You, G., Hwang, S. and Jain, N. (2011). Scalable Load Balancing in
Cluster Storage Systems. in Kon F., Kermarrec AM. eds. Middleware
Lecture Notes in Computer Science, vol. 7049. Springer, Berlin,
Heidelberg, 101–122.
Wong, K.W. (2009). Image Encryption Using Chaotic Maps. in Kocarev
L., Galias Z., Lian S. eds. Intelligent Computing Based on Chaos. Studies
in Computational Intelligence, vol. 184. Springer, Berlin, Heidelberg,
–354.
Andre, P. (1999). Selectionist Relaxation: Genetic Algorithm Applied to
Image Segmentation. Image and Vision Computing, vol. 17, 175–187.
Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization and
Machine Learning. Addison-Wesley, Massachusetts, USA.
Yoshimura, M. and Oe, S. (1999). Evolutionary Segmentation of Texture
using Genetic Algorithms Towards Automatic Decision of Optimum
Number of Segmentation Areas. Pattern Recognition, 2041–2054.
Wu, Y., Noonan, J. P. and Agaian, S. (2011). NPCR and UACI Randomness
Tests for Image Encryption. Cyber Journals: Multidisciplinary
Journals in Science and Technology, Journal of Selected Areas in
Telecommunications (JSAT), 31–38.
Marwan, M., Kartit, A. and Ouahmane, H., Security in Cloud-Based
Medical Image Processing: requirements and approaches. in BDCA’17:
the 2nd International Conference on Big Data, Cloud and Applications
(BDCA’17). ACM, New York, NY, USA, Article 6, 6 pages.
Marwan, M., A. Kartit and Ouahmane, H. (2016). A Secure Framework
for Medical Image Storage Based on Multi-cloud. in Proceeding of
the International Conference on Cloud Computing Technologies and
Applications, CloudTech, 88–94.
Guo, S. and Zou, C. (2017). An Improved Image Retrieval Method
Based on Spark. in ICCSN: 9th IEEE International Conference on
Communication Software and Networks, (Guangzhou, China, 2017),
–1296.
Vemula, S. and Crick, C. (2015). Hadoop Image Processing Framework.
in Big Data Congress 2015, IEEE International Congress on Big Data,
(New York, NY, USA), 506–513.
Xia, Q., Sifah, E. B., Smahi, A.,Amofa, S., and Zhang, X. (2017). BBDS:
Blockchain-based data sharing for electronic medical records in cloud
environments. Information, 8(2), 44–59.
Zyskind, G., and Nathan, O. (2015). Decentralizing privacy: Using
blockchain to protect personal data. In IEEE Security and Privacy
Workshops (SPW), (pp. 180–184). IEEE.
