Mexico City, January 12, 2023.- From November 9 to 11, 2022, Dr. Ernesto Moya-Albor and Dr. Jorge Brieva, research professors from the School of Engineering, Mexico campus , attended the 18th International Symposium on Medical Information Processing and Analysis (SIPAIM 2022) held in Valparaiso, Chile.
In this edition of SIPAIM, both researchers, together with faculty research professor Dr. Karina Ruby Pérez Daniel and in collaboration with academics from the Instituto Politécnico Nacional and the Centro de Investigación en Matemáticas, A.C., presented two research papers.
Both Dr. Brieva, who is a member of the SIPAIM Steering Committee, and Dr. Moya-Albor were part of the Scientific Committee. But, additionally, Brieva participated as moderator of plenary conferences and was part of the event's organizer.
Modeling of the major temporal arcade
In presenting the paper Modeling of the major temporal arcade using genetic algorithms and orthogonal polynomials, the researchers presented a novel method to verify the state of the retina and to detect changes in the vascular structure in both adults and children with diabetic retinopathy, one of the main causes of blindness.
For this purpose, a numerical model of the major temporal arch in fundus images was presented using orthogonal Legendre, Chebyshev and Laguerre polynomials and an evolutionary algorithm. To evaluate the proposal, a set of twenty fundus images was used, where an expert performed the delineation of the major temporal arch.
The proposed method was compared with three others in the state of the art and it was found that Legendre polynomials are the most suitable for generating a tool to aid in computer-aided ophthalmic diagnosis.
Authentication of medical images
They also participated with the work Authentication of Medical Images through a Hybrid Watermarking Method based on Hermite-Jigsaw-SVDin which they presented the results of a robust method for watermarking medical images.
The doctors used the rotated Hermite transform (SHT), a spatial and frequency image decomposition technique inspired by the human vision system, to invisibly embed the watermark.
In addition, they included in the proposal the singular value decomposition (SVD) to obtain robustness of the watermark against attacks. The Jigsaw transform was also used to encrypt the watermark before being embedded in the medical image. Finally, 40 X-ray images and the caduceus medical symbol as watermark were used to evaluate the proposed watermarking method.
The results obtained showed that the watermark is invisible to the human eye and is extracted without any loss of visual information. As for the watermarked medical images, it was demonstrated that they do not suffer significant visual alterations, preserving the visual information for the patient's diagnosis.
On the other hand, in tests involving attacks on the marked medical image, the results verified that the proposed method is robust to common geometric and processing attacks (Gaussian noise, salt and pepper noise, median filter, JPEG compression, rotation and translation), allowing to extract in a perceptible way the watermark even in strong attacks where the marked medical image has lost a lot of information.
