Biomedical Data Analysis
Data analysis is an important part of neural engineering. So far, we have had the opportunity to work on:
- Measurement and analysis of motor evoked potentials (MEPs) in non-invasive brain stimulation
- Analysis of magnetic resonance images (MRIs) of patients with Multiple Sclerosis (MS) using the concept of phase congruency
Measurement and analysis of motor evoked potentials in non-invasive brain stimulation
Analysis of magnetic resonance images (MRIs) of patients with Multiple Sclerosis (MS) using the concept of phase congruency
Biomedical image processing aims to provide novel tools for the extraction of bio-markers for diagnosis, treatment planning and therapy. . The majority of image processing techniques are based on the magnitude of the Fourier transform. Inspired by the work of Oppenheim and Lim (IEEE Proceedings, vol. 69, pp. 529–541, 1981) who demonstrated that the phase of the image contains more information than its magnitude, we have been developing novel tools for the optimal detection of image features based on the concept of phase congruency (PC) that employs both the magnitude and phase information of the image. The PC principle states that image features are mainly perceived at the points where the Fourier components of the image are maximally in phase. Many papers have been published detailing the PC application in the study of history, media, basic sciences, and medicine; however, the PC computation requires several parameters to be tuned a priori for which there is no clear rule as of yet.
We have proposed several optimization frameworks for automatic and optimal tuning of PC parameters. We developed PC tools to better understand and analyze magnetic resonance images (MRIs) of patients with Multiple Sclerosis (MS). We showed that MS lesions can accurately be detected and localized by using PC. We also illustrated that PC enables us to detect the direction of maximum information of an image.
Left: The original image of a brain slice of a patient with multiple sclerosis (MS).
Right: The image produced by phase-congruency optimization technique.
- L Nourbala, SN Niyakan, SMM Alavi, Development of Phase Congruency to Estimate the Direction of Maximum Information (tDMI) in Images with Straight Line Segments, Proc. 27th Iranian Conference on Electrical Engineering (ICEE 2019), pp. 1413 – 1419, 2019.
- SMM Alavi, Y Zhang, Phase Congruency Parameter Optimization for Enhanced Detection of Image Features for both Natural and Medical Applications, arXiv: 1705.02102, 2017. [Link]
- SMM Alavi, Image Analysis Using Phase Congruency and Optimization, Seminar, Shahid Beheshti University, February 2017. [Link]