Securing X-Ray Images Into Cover Images Using Hybrid EBS Steganography With Five-Layer Cryptography

被引:0
作者
Sharma, Divya [1 ]
Prabha, Chander [1 ]
Hassan, Md Mehedi [2 ]
Abdulla, Shahab [3 ]
Bairagi, Anupam Kumar [2 ]
Alshathri, Samah [4 ]
El-Shafai, Walid [5 ,6 ]
机构
[1] Chitkara Univ, Inst Engn & Technol, Rajpura 140401, Punjab, India
[2] Khulna Univ, Comp Sci & Engn Discipline, Khulna 9208, Bangladesh
[3] Univ Southern Queensland, UniSQ Coll, Toowoomba, Qld 4305, Australia
[4] Princess Nourah Bint AbdulRahman Univ, Coll Comp & Informat Sci, Dept Informat Technol, POB 84428, Riyadh, Saudi Arabia
[5] Prince Sultan Univ, Comp Sci Dept, Secur Engn Lab, Riyadh 11586, Saudi Arabia
[6] Menoufia Univ, Fac Elect Engn, Dept Elect & Elect Commun Engn, Menoufia 32952, Egypt
关键词
Electromagnetic interference; X-ray imaging; Security; MATLAB; Steganography; Image edge detection; Encryption; Medical diagnostic imaging; Computed tomography; Electronic medical records; Cryptography; Electronic medical images (EMI); security; privacy; cryptography; steganography;
D O I
10.1109/ACCESS.2024.3489452
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Electronic Medical Images (EMI) have grown with the increase in population. EMI are used for medical diagnosis for medical emergencies hence, they should be correct and clear for accurate diagnosis. In general, EMI are of varying sizes and dimensions. The aim is to enhance the security and privacy of EMI with reduced computational time while dealing with a larger and varying-sized data set. Reducing computational time will make the method suitable for real-time applications (RTA). Hence, a data set of 5856 secret X-ray images all varying in dimensions, total sized up to 1.16 GB, are applied with a hybrid of steganography and cryptography. Here, one X-Ray image is taken at a time then hidden into a single cover image using Edge-based steganography and then encrypted using five layers of cryptography. Various performance evaluation tests such as Structural Similarity Index Metrics (SSIM) achieved a value close to 1 which is the preferred value, Peak Signal-to-Noise Ratio (PSNR) is 82.51967 dB which is good, Mean Square Error (MSE) is 5.6E-09 which is close to zero indicating no addition of noise in the retrieved X-ray images, the Correlation (R) is 1. Therefore, the extracted image is the same as the original X-ray images, while remaining tests such as RMSE, Entropy, KLD, BER, SNR, CV, MAPE, PRD, etc. achieved good results. The computational time is measured by the Encryption Time (ET) is 0.37 seconds while the Decryption Time (DT) is 3.9275 sec. Thus, it can be concluded that a hybrid method (HM) could be implemented for RTA.
引用
收藏
页码:165050 / 165067
页数:18
相关论文
共 50 条
[21]   Knot Detection in X-ray Images of Wood Planks using Dictionary Learning [J].
Hansson, Mattias ;
Enescu, Alexandru ;
Brandt, Sami S. .
2015 14TH IAPR INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS (MVA), 2015, :497-500
[22]   Generalizable disease detection using model ensemble on chest X-ray images [J].
Abad, Maider ;
Casas-Roma, Jordi ;
Prados, Ferran .
SCIENTIFIC REPORTS, 2024, 14 (01)
[23]   Evaluation of digital flash X-ray images produced using computed radiography [J].
Carlsson, TE ;
Örnhed, H .
26th International Congress on High Speed Photography and Photonics, 2005, 5580 :842-850
[24]   Predicting the noise in hybrid (phase and attenuation) x-ray images acquired with the edge illumination technique [J].
Hagen, Charlotte Klara ;
Morgo, Oriol ;
Olivo, Alessandro .
MEDICAL PHYSICS, 2020, 47 (09) :4439-4449
[25]   An Improved Densenet Deep Neural Network Model for Tuberculosis Detection Using Chest X-Ray Images [J].
Huy, Vo Trong Quang ;
Lin, Chih-Min .
IEEE ACCESS, 2023, 11 :42839-42849
[26]   Securing the Classification of COVID-19 in Chest X-ray Images: A Privacy-Preserving Deep Learning Approach [J].
Boulila, Wadii ;
Ammar, Adel ;
Benjdira, Bilel ;
Koubaa, Anis .
2022 2ND INTERNATIONAL CONFERENCE OF SMART SYSTEMS AND EMERGING TECHNOLOGIES (SMARTTECH 2022), 2022, :220-225
[27]   Estimating Lung Volume Capacity from X-ray Images Using Deep Learning [J].
Ghimire, Samip ;
Subedi, Santosh .
QUANTUM BEAM SCIENCE, 2024, 8 (02)
[28]   An evaluation of utilizing geometric features for wheat grain classification using X-ray images [J].
Charytanowicz, Malgorzata ;
Kulczycki, Piotr ;
Kowalski, Piotr A. ;
Lukasik, Szymon ;
Czabak-Garbacz, Roza .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2018, 144 :260-268
[29]   Reduction of metal artifacts in x-ray CT images using a convolutional neural network [J].
Zhang, Yanbo ;
Chu, Ying ;
Yu, Hengyong .
DEVELOPMENTS IN X-RAY TOMOGRAPHY XI, 2017, 10391
[30]   A Hybrid Deep Learning-Based Framework for Chip Packaging Fault Diagnostics in X-Ray Images [J].
Wang, Jie ;
Li, Gaomin ;
Bai, Haoyu ;
Yuan, Guixin ;
Li, Xuan ;
Lin, Bin ;
Zhong, Lijun ;
Zhang, Xiaohu .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2024, 20 (09) :11181-11191