Watermarking scheme proposes to enhance image security

Article

The rapid spread of digital imaging and teleradiology raises the specter of malicious interception of and tampering with sensitive medical data. Now researchers in China have reported a lossless watermarking method capable of verifying the authenticity and integrity of medical images.

The rapid spread of digital imaging and teleradiology raises the specter of malicious interception of and tampering with sensitive medical data. Now researchers in China have reported a lossless watermarking method capable of verifying the authenticity and integrity of medical images.

"The watermarked image may still be used for diagnostic purposes, since this scheme has the capability of not introducing any embedding-induced distortion in the region of interest of a medical image," said Xiaotao Guo, Ph.D., of the biomedical engineering department at Shanghai Jiaotong University.

Digital watermarking is an emerging technology that allows users to add hidden copyright notices or other verification messages to digital files. The watermarked image used in a medical environment can still conform to DICOM format.

Although a reversible watermark allows exact recovery of the original host image, it is still desirable to keep the embedding distortion to a minimum. One reason is that the ROI may be different for different applications.

"Ideally, we hope the difference between the watermarked image and the original image is imperceptible," Guo said.

Guo evaluated the embedding capacity under different distortion levels for a large number of medical images (J Digit Imaging 2007 Jul 10; [Epub ahead of print]).

"Experimental results indicate that this scheme achieves high embedding capacity with low levels of embedding-induced distortion," he said.

One limitation of this method is the lack of a way to automatically identify the ROI, Guo said. This now requires manual intervention, because the ROI may vary significantly for different organs or modalities. Manual intervention can be reduced, however, if the nature of a particular family of images is understood.

"If we know the host image is a head CT, then it is reasonable to deduce that the regions outside the skull are non-ROI," he said.

The healthcare industry has taken the security threat seriously. Not only has the federal government issued mandates for ensuring health data security in the form of the Health Insurance Portability and Accountability Act, but Part 15 of the DICOM Standard specifies security profiles and technical means to implement security policies (PS 3.15-2001).

Also, the Society for Computer Applications in Radiology (now the Society for Imaging Informatics in Medicine) issued two editions of a primer, Security Issues in the Digital Medical Enterprise, one in 2000 and an update in 2004.

Recent Videos
Improving Access to Nuclear Imaging: An Interview with SNMMI President Jean-Luc C. Urbain, MD, PhD
SNMMI: 18F-Piflufolastat PSMA PET/CT Offers High PPV for Local PCa Recurrence Regardless of PSA Level
SNMMI: NIH Researcher Discusses Potential of 18F-Fluciclovine for Multiple Myeloma Detection
SNMMI: What Tau PET Findings May Reveal About Modifiable Factors for Alzheimer’s Disease
Emerging Insights on the Use of FES PET for Women with Lobular Breast Cancer
Can Generative AI Reinvent Radiology Reporting?: An Interview with Samir Abboud, MD
Mammography Study Reveals Over Sixfold Higher Risk of Advanced Cancer Presentation with Symptom-Detected Cancers
Combining Advances in Computed Tomography Angiography with AI to Enhance Preventive Care
Study: MRI-Based AI Enhances Detection of Seminal Vesicle Invasion in Prostate Cancer
What New Research Reveals About the Impact of AI and DBT Screening: An Interview with Manisha Bahl, MD
Related Content
© 2025 MJH Life Sciences

All rights reserved.