Biomedical Signal Processing

One of the main focus is the design of signal processing based feature extraction methods to build machine learning models for biomedical applications: Epileptic spikes detection using MEG/EEG/ECG signals, Hand Gesture detection using sEMG signals.

Signal Quality enhancement

In order to improve the biomedical signal quality, we designed different algorithms based on a quantum method called Semi-Classical Signal Analysis (SCSA). This method has the ability to decompose the input signal/image into a set of components based on the Eigen-spectrum of the Schrödinger operator.  

BSP 2

MRI image enhancement using adaptive algorithm based on image segmentation

BSP 3

MRS residual water suppression using the squared eigenfunctions of the Schrödinger operator

BSP 4

Complex MRS signal denoising using SCSA-based soft thresholding

BSP 5

Biomedical Signal/Image classification

In order to assist neurologist and biologist during their daily activity and save the time spent in the manual processing of the records, we need focus on building efficient machine learning models based on the extraction of pertinent and discriminative features for the prediction of biomedical signals. Our models are based on:

  • Using Digital Signal Processing (DSP) features
  • Improving the raw data quality and reducing feature vector size
  • Improving the classifier robustness or sensitivity to noise 

BSP 6

Assist biologists in defining accurately the Poly(A) locations in the DNA sequence

BSP 7

Assist clinicians in detecting spiky region in the brain using MEG/EEG/ECG signals epileptic  diagnosis

BSP 8

Predicting human cognitive tasks from their corresponding functional Magnetic Resonance Imaging (fMRI) data

BSP 9

Publications (Conference papers):

  • A. Chahid, H. Serrai, E. Achten, and T.-M. Laleg-Kirati, “A New ROI-Based performance evaluation method for image denoising using the Squared Eigenfunctions of the Schrödinger Operator,” in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2018.
  • A. Chahid, H. Serrai, E. Achten, and T.-M. Laleg-Kirati, “Adaptive method for MRI enhancement using squared eigenfunctions of the Schrödinger operator,” in 2017 IEEE Biomedical Circuits and Systems Conference, BioCAS 2017 - Proceedings, 2018, vol. 2018.

Publications (Abstracts):

  • A. Chahid, S. Bhaduri, M. Wali, E. Achten, H. Serrai, T.-M,  Laleg-Kirati, “Semi-Classical Signal Analysis Method with Soft-Thresholding for MRS denoising" ESMRMB 2019 , Canada, 2019.
  • A. Chahid, S. Bhaduri, E. Achten, H. Serrai, T.-M,  Laleg-Kirati “Matlab Tool for   Residual Water Suppression and Denoising of MRS Signal using the Schrodinger operator" ESMRMB 2019 , Canada, 2019.
  • A. Chahid, H. Serrai,  E. Achten, T.-M,  Laleg-Kirati, “Magnetic Resonance Spectroscopy data water suppression using squared eigenfunctions of the Schrodinger operator," ESMRMB 2017 , Spain, 2017.
  • A. Chahid, H. Serrai,  E. Achten, T.-M,  Laleg-Kirati, "Adaptive Magnetic Resonance Image signal enhancement using squared eigenfunctions of the Schrödinger operator", ISMRM 25th Annual Meeting, Hawai, 2017.​

Collaborators

Software

The developed software can be accessed through our Github account.