Making Medical Scans Easy to View and Safe to Share

By Nuruzzaman Faruqui

·

Medical scans are stored in a special format called DICOM that ordinary computers cannot open, and the files contain sensitive patient details. This research converts them into encrypted images that are easy to view but only for people with the key.

<0.5 saverage conversion time
EJPEGencrypted JPEG format
2024published

The problem

DICOM is the standard file format for medical imaging, but most operating systems cannot display it without extra software. DICOM files also contain confidential information about the patient’s condition.

What the research did

We proposed a framework that converts DICOM images into an Encrypted JPEG (EJPEG) format. Anyone with the decryption key can view the image without special software.

What we found

The framework kept medical images confidential, made them easier to view and saved disk space, taking less than half a second per image on average.

Who benefits

  • Patients who want to view and share their scans
  • Doctors consulting remotely
  • Hospitals with limited IT resources

Limits and what comes next

Converting to JPEG can lose some image detail that matters for diagnosis, so the original DICOM files should still be used for clinical decisions.

The team

This research was led by Safayat Jamil Siam with me and colleagues at Universiti Malaysia Perlis, including Nur Farhan Kahar, R. Badlishah Ahmad, Naimah Yaakob and Ong Bi Lynn.

Frequently asked questions

What is DICOM?

The standard file format for medical images such as CT and MRI scans.

Why encrypt medical images?

They contain sensitive patient information that must be protected.

How fast is the conversion?

Under half a second per image on average.

About the author

Nuruzzaman Faruqui is an award-winning AI educator and researcher who has taught artificial intelligence and machine learning at university level since 2018. A two-time winner of the Excellence in Teaching Award (2023, 2024) and winner of the Best Researcher Award (2024) at Daffodil International University, he is now a doctoral researcher in AI at Monash University, Australia. He has published 53 papers and six books, and writes these articles to make AI research easy for everyone to understand. His teaching · About Zaman · Get in touch

Keep reading