In therapeutic diagnostics, early diagnosis and monitoring of heart disease is dependent on fast time-series MRI data processing. Robust encryption techniques are necessary to guarantee patient confidentiality. While deep learning (DL) algorithm have improved medical imaging, privacy and performance are still hard to balance. In this study, a novel approach for analyzing homomorphivally-encrypted (HE) time-series MRI data is introduced: The Multi-Faceted Long Short-Term Memory (MF-LSTM). This method includes privacy protection. The MF-LSTM architecture protects patient's privacy while accurately categorizing and forecasting cardiac disease, with accuracy (97.5%), precision (96.5%), recall (98.3%), and F1-score (97.4%). While segmentation methods help to improve interpretability by identifying important region in encrypted MRI images, Generalized Histogram Equalization (GHE) improves image quality. Extensive testing on selected dataset if encrypted time-series MRI images proves the method's stability and efficacy, outperforming previous approaches. The finding shows that the suggested technique can decode medical image to expose visual representation as well as sequential movement while protecting privacy and providing accurate medical image evaluation.

Applied Science Research Center Applied Science Private University Amman Jordan

Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai 602 105 India

Department of Chemistry College of Science King Saud University P O Box 2455 Riyadh 11451 Kingdom of Saudi Arabia

Department of Computer Science and Engineering Faculty of Engineering and Technology Jain University Bengaluru Karnataka India

Department of Computer Science and Engineering Vivekananda Global University Jaipur India

Department of CSE Graphic Era Deemed To Be University Dehradun Uttarakhand 248002 India

Department of CSE Graphic Era Hill University Dehradun 248002 India

Department of Machining Assembly and Engineering Metrology Faculty of Mechanical Engineering VSB Technical University of Ostrava 70800 Ostrava Czech Republic

University Centre for Research and Development Chandigarh University Gharuan Mohali Punjab India

Zobrazit více v PubMed

Jeelani, H., Martin, J., Vasquez, F., Salerno, M. and Weller, D.S., 2018, April. Image quality affects deep learning reconstruction of MRI. In 2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018) (pp. 357–360). IEEE.

Masutani, E. M., Bahrami, N. & Hsiao, A. Deep learning single-frame and multiframe super-resolution for cardiac MRI. Radiology295(3), 552–561 (2020). 10.1148/radiol.2020192173 PubMed DOI PMC

Curiale, A. H., Colavecchia, F. D. & Mato, G. Automatic quantification of the LV function and mass: A deep learning approach for cardiovascular MRI. Comput. Methods Progr. Biomed.169, 37–50 (2019).10.1016/j.cmpb.2018.12.002 PubMed DOI

Wang, Z., Peng, Y., Li, D., Guo, Y. & Zhang, B. MMNet: A multi-scale deep learning network for the left ventricular segmentation of cardiac MRI images. Appl. Intell.52(5), 5225–5240 (2022).10.1007/s10489-021-02720-9 DOI

Liao, F., Chen, X., Hu, X. & Song, S. Estimation of the volume of the left ventricle from MRI images using deep neural networks. IEEE Trans. Cybern.49(2), 495–504 (2017). 10.1109/TCYB.2017.2778799 PubMed DOI

Zhou, T. et al. Automatic segmentation of left ventricle in cardiac cine MRI images based on deep learning In medical imaging. Image Process..10133(540), 547 (2017).

Abdeltawab, H. et al. A deep learning-based approach for automatic segmentation and quantification of the left ventricle from cardiac cine MR images. Comput. Med. Imaging Graph.81, 101717 (2020). 10.1016/j.compmedimag.2020.101717 PubMed DOI PMC

Zhang, N. et al. Deep learning for diagnosis of chronic myocardial infarction on nonenhanced cardiac cine MRI. Radiology291(3), 606–617 (2019). 10.1148/radiol.2019182304 PubMed DOI

Hauptmann, A., Arridge, S., Lucka, F., Muthurangu, V. & Steeden, J. A. Real-time cardiovascular MR with spatio-temporal artifact suppression using deep learning–proof of concept in congenital heart disease. Magn. Reson. Med.81(2), 1143–1156 (2019). 10.1002/mrm.27480 PubMed DOI PMC

Küstner, T. et al. CINENet: Deep learning-based 3D cardiac CINE MRI reconstruction with multi-coil complex-valued 4D spatio-temporal convolutions. Sci. Rep.10(1), 13710 (2020). 10.1038/s41598-020-70551-8 PubMed DOI PMC

Usman, O. L. & Muniyandi, R. C. CryptoDL: Predicting dyslexia biomarkers from encrypted neuroimaging dataset using energy-efficient residue number system and deep convolutional neural network. Symmetry12(5), 836 (2020).10.3390/sym12050836 DOI

Liu, Y., Ma, Z., Liu, X., Ma, S. & Ren, K. Privacy-preserving object detection for medical images with faster R-CNN. IEEE Trans. Inf. Forensics Secur.17, 69–84 (2019).10.1109/TIFS.2019.2946476 DOI

Chao, J., Badawi, A.A., Unnikrishnan, B., Lin, J., Mun, C.F., Brown, J.M., Campbell, J.P., Chiang, M., Kalpathy-Cramer, J., Chandrasekhar, V.R. and Krishnaswamy, P., 2019. CaRENets: Compact and resource-efficient CNN for homomorphic inference on encrypted medical images. arXiv preprint arXiv:1901.10074.

Usman, O.L., Muniyandi, R.C., Omar, K. and Mohamad, M., 2022, February. Privacy-Preserving Classification Method for Neural-Biomarkers using Homomorphic Residue Number System CNN: HoRNS-CNN. In 2022 International Conference on Business Analytics for Technology and Security (ICBATS) (pp. 1–8). IEEE.

Selvi, C. T., Amudha, J. & Sudhakar, R. Medical image encryption and compression by adaptive sigma filterized synorr certificateless signcryptiveLevenshtein entropy-coding-based deep neural learning. Multimed. Syst.21(1056), 1074 (2021).

Ahmad, I. & Shin, S. A perceptual encryption-based image communication system for deep learning-based tuberculosis diagnosis using healthcare cloud services. Electronics11(16), 2514 (2022).10.3390/electronics11162514 DOI

Kumar, A., Purohit, V., Bharti, V., Singh, R. & Singh, S. K. Medisecfed: Private and secure medical image classification in the presence of malicious clients. IEEE Trans. Ind. Inf.18(8), 5648–5657 (2021).10.1109/TII.2021.3138919 DOI

Hajjaji, M. A., Dridi, M. & Mtibaa, A. A medical image crypto-compression algorithm based on neural network and PWLCM. Multimed. Tools Appl.78, 14379–14396 (2019).10.1007/s11042-018-6795-6 DOI

Ding, Y. et al. DeepKeyGen: a deep learning-based stream cipher generator for medical image encryption and decryption. IEEE Trans. Neural Netw. Learn. Syst.33(9), 4915–4929 (2021).10.1109/TNNLS.2021.3062754 PubMed DOI

Krishna, A.A., Arikutharam, V., Ramnan, K.V., Bharathi, H. and Chandar, T.S., 2022, May. Dynamic Image Encryption using Neural Networks for Medical Images. In 2022 IEEE IAS Global Conference on Emerging Technologies (GlobConET) (pp. 739–745). IEEE.

Panwar, K. et al. Encipher GAN: An end-to-end color image encryption system using a deep generative model. Systems11(1), 36 (2023).10.3390/systems11010036 DOI

Gaudio, A., Smailagic, A., Faloutsos, C., Mohan, S., Johnson, E., Liu, Y., Costa, P. and Campilho, A., 2023. DeepFixCX: Explainable privacy‐preserving image compression for medical image analysis. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, p.e1495.

Zhu, L., Qu, W., Wen, X. & Zhu, C. FEDResNet: a flexible image encryption and decryption scheme based on end-to-end image diffusion with dilated ResNet. Appl. Opt.61(31), 9124–9134 (2022). 10.1364/AO.469155 PubMed DOI

Pati, S. et al. GaNDLF: the generally nuanced deep learning framework for scalable end-to-end clinical workflows. Commun. Eng.2(1), 23 (2023).10.1038/s44172-023-00066-3 DOI

Ding, Y. et al. ToStaGAN: An end-to-end two-stage generative adversarial network for brain tumor segmentation. Neurocomputing462, 141–153 (2021).10.1016/j.neucom.2021.07.066 DOI

Diller, G. P. et al. Utility of deep learning networks for the generation of artificial cardiac magnetic resonance images in congenital heart disease. BMC Med. Imaging20, 1–8 (2020).10.1186/s12880-020-00511-1 PubMed DOI PMC

Bernard, O. et al. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved?. IEEE trans. Med. Imaging37(11), 2514–2525 (2018). 10.1109/TMI.2018.2837502 PubMed DOI

Blansit, K., Retson, T., Masutani, E., Bahrami, N. & Hsiao, A. Deep learning–based prescription of cardiac MRI planes. Radiol. Artif. Intell.1(6), 180069 (2019).10.1148/ryai.2019180069 PubMed DOI PMC

Chen, M., Fang, L., Zhuang, Q. & Liu, H. Deep learning assessment of myocardial infarction from MR image sequences. Ieee Access7, 5438–5446 (2019).10.1109/ACCESS.2018.2889744 DOI

Piccini, D. et al. Deep learning to automate reference-free image quality assessment of whole-heart MR images. Radiol. Artif. Intell.2(3), 190123 (2020).10.1148/ryai.2020190123 PubMed DOI PMC

Ullah, Z., Usman, M., Jeon, M. & Gwak, J. Cascade multiscale residual attention cnns with adaptive roi for automatic brain tumor segmentation. Inf. Sci.608, 1541–1556 (2022).10.1016/j.ins.2022.07.044 DOI

Ullah, Z., Usman, M., Latif, S. & Gwak, J. Densely attention mechanism based network for COVID-19 detection in chest X-rays. Scientific Reports13(1), 261 (2023). 10.1038/s41598-022-27266-9 PubMed DOI PMC

Ullah, Z., Usman, M., Latif, S., Khan, A. & Gwak, J. SSMD-UNet: Semi-supervised multi-task decoders network for diabetic retinopathy segmentation. Sci. Rep.13(1), 9087 (2023). 10.1038/s41598-023-36311-0 PubMed DOI PMC

Ali, S. et al. A comprehensive survey on brain tumor diagnosis using deep learning and emerging hybrid techniques with multi-modal MR image. Archives Comput. Methods Eng.29(7), 4871–4896 (2022).10.1007/s11831-022-09758-z DOI

Mahmood, T. et al. An automatic detection and localization of mammographic microcalcifications ROI with multi-scale features using the radiomics analysis approach. Cancers13(23), 5916 (2021). 10.3390/cancers13235916 PubMed DOI PMC

Mahmood, T., Saba, T., Rehman, A. & Alamri, F. S. Harnessing the power of radiomics and deep learning for improved breast cancer diagnosis with multiparametric breast mammography. Expert Syst. Appl.249, 123747 (2024).10.1016/j.eswa.2024.123747 DOI

Mahmood, T. et al. A brief survey on breast cancer diagnostic with deep learning schemes using multi-image modalities. IEEE Access8, 165779–165809 (2020).10.1109/ACCESS.2020.3021343 DOI

Sharma, L., Gupta, G. and Jaiswal, V., 2016, December. Classification and development of tool for heart diseases (MRI images) using machine learning. In 2016 Fourth International Conference on Parallel, Distributed and Grid Computing (PDGC) (pp. 219–224). IEEE.

Obayes, H. K. & Al-Shareefi, F. Secure heart disease classification system based on three pass protocol and machine learning. Iraqi J. Comput. Sci. Math.4(2), 72–82 (2023).

Hassan, C. A. U. et al. Effectively predicting the presence of coronary heart disease using machine learning classifiers. Sensors22(19), 7227 (2022). 10.3390/s22197227 PubMed DOI PMC