Secured DICOM medical image transition with optimized chaos method for encryption and customized deep learning model for watermarking
The fields of telemedicine and aided medical diagnostics are benefiting greatly from medical imaging. For healthcare professionals to view patient medical images, a secure online transmitting technique is essential. The work introduces a DICOM image copyright protection by extended data encryption a...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-04-01
|
| Series: | Automatika |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/00051144.2025.2460877 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832095430103531520 |
|---|---|
| author | R. Abirami C. Malathy |
| author_facet | R. Abirami C. Malathy |
| author_sort | R. Abirami |
| collection | DOAJ |
| description | The fields of telemedicine and aided medical diagnostics are benefiting greatly from medical imaging. For healthcare professionals to view patient medical images, a secure online transmitting technique is essential. The work introduces a DICOM image copyright protection by extended data encryption and watermarking technique with several potential applications in the medical field. Encrypting watermark images before embedding them into a DICOM cover images ensures the confidentiality of medical data, allowing for high-security access. Encryption here makes use of enhanced chaos with fruit fly optimization. The chaotic encryption technique makes use of the Lorenz map and a Customized Deep Learning Model (CDLM) based on Convolution Neural Networks (CNNs) are presented for watermarking. Multiple DICOM images with varying numbers of watermarks were used to evaluate the proposed model, and the resulting output was subjected to qualitative analysis using metrics such as MSE, SNR, PSNR, NC, and Q. Additionally, the requirements are satisfied for many assaults. In comparison to the state-of-the-art model, the suggested model performs better in every respect. Moreover, the approach provides impressive metrics such as MSE at 1.41E-06, SNR at 59.9876, PSNR at 60.3456, NC at 0.9989, and Q at 0.9992, showcasing its outstanding performance and reliability. |
| format | Article |
| id | doaj-art-e1150afd405842ea87c00a1b94672766 |
| institution | Kabale University |
| issn | 0005-1144 1848-3380 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Automatika |
| spelling | doaj-art-e1150afd405842ea87c00a1b946727662025-02-05T18:44:31ZengTaylor & Francis GroupAutomatika0005-11441848-33802025-04-0166217318710.1080/00051144.2025.2460877Secured DICOM medical image transition with optimized chaos method for encryption and customized deep learning model for watermarkingR. Abirami0C. Malathy1Department of Networking and Communications, School of Computing, SRM Institute of Science and Technology, Kattankulathur, IndiaDepartment of Networking and Communications, School of Computing, SRM Institute of Science and Technology, Kattankulathur, IndiaThe fields of telemedicine and aided medical diagnostics are benefiting greatly from medical imaging. For healthcare professionals to view patient medical images, a secure online transmitting technique is essential. The work introduces a DICOM image copyright protection by extended data encryption and watermarking technique with several potential applications in the medical field. Encrypting watermark images before embedding them into a DICOM cover images ensures the confidentiality of medical data, allowing for high-security access. Encryption here makes use of enhanced chaos with fruit fly optimization. The chaotic encryption technique makes use of the Lorenz map and a Customized Deep Learning Model (CDLM) based on Convolution Neural Networks (CNNs) are presented for watermarking. Multiple DICOM images with varying numbers of watermarks were used to evaluate the proposed model, and the resulting output was subjected to qualitative analysis using metrics such as MSE, SNR, PSNR, NC, and Q. Additionally, the requirements are satisfied for many assaults. In comparison to the state-of-the-art model, the suggested model performs better in every respect. Moreover, the approach provides impressive metrics such as MSE at 1.41E-06, SNR at 59.9876, PSNR at 60.3456, NC at 0.9989, and Q at 0.9992, showcasing its outstanding performance and reliability.https://www.tandfonline.com/doi/10.1080/00051144.2025.2460877ChaosDICOM imageEncryptionFruit flyLorenz mapWatermarking |
| spellingShingle | R. Abirami C. Malathy Secured DICOM medical image transition with optimized chaos method for encryption and customized deep learning model for watermarking Automatika Chaos DICOM image Encryption Fruit fly Lorenz map Watermarking |
| title | Secured DICOM medical image transition with optimized chaos method for encryption and customized deep learning model for watermarking |
| title_full | Secured DICOM medical image transition with optimized chaos method for encryption and customized deep learning model for watermarking |
| title_fullStr | Secured DICOM medical image transition with optimized chaos method for encryption and customized deep learning model for watermarking |
| title_full_unstemmed | Secured DICOM medical image transition with optimized chaos method for encryption and customized deep learning model for watermarking |
| title_short | Secured DICOM medical image transition with optimized chaos method for encryption and customized deep learning model for watermarking |
| title_sort | secured dicom medical image transition with optimized chaos method for encryption and customized deep learning model for watermarking |
| topic | Chaos DICOM image Encryption Fruit fly Lorenz map Watermarking |
| url | https://www.tandfonline.com/doi/10.1080/00051144.2025.2460877 |
| work_keys_str_mv | AT rabirami secureddicommedicalimagetransitionwithoptimizedchaosmethodforencryptionandcustomizeddeeplearningmodelforwatermarking AT cmalathy secureddicommedicalimagetransitionwithoptimizedchaosmethodforencryptionandcustomizeddeeplearningmodelforwatermarking |