Signal Processing

The physiological data collected with biomagnetic (MCG and infant MEG), EEG and fMRI systems, are analyzed using both linear and nonlinear signal processing techniques. Depending on the information of interest to be extracted from the recorded signals, diverse type of signal processing techniques can be performed.

Since 2004, our group has extensively employed Independent Component Analysis (ICA) for the processing of biomedical data of different origin, with the purpose of separating physiological signals and denoising the signals of interest. Signal denoising is also achieved by means of techniques that utilize wavelets decomposition.

More recently, our interest has focused on the development of methods to assess the non linear dynamics of complex physiological systems such as the heart or the brain, and to perform an automatic pattern recognition between clinical and non clinical data sets.

Independent Component Analysis

Independent component analysis (ICA) is a statistical Blind Source Separation (BSS) technique that models a set of input data in terms of statistically independent variables. ICA algorithms aim at separating mutually independent source signals from their linear instantaneous mixtures, without any a priori information about the spatial mixing.

During the last decade, ICA has been successfully used for signal extraction tasks in sound and image processing and in telecommunications. More recently, ICA has been employed in the field of biomedical signal processing, with the primary application of noise reduction. We use ICA for the separation of physiological signals recorded with multi-channel devices, such as biomagnetic, EEG and fMRI systems. This is possible because one major requirement for ICA application i.e. that the number of input signals be larger than or equal to the number of expected signals, is fulfilled when using data sets recorded with multi-channel devices.

Publications (selected):

  • S. Comani, P. van Leeuwen, S. Lange, D. Geue, D. Grönemeyer 2009 Processing the fetal magnetocardiogram: advantages and disadvantages of template matching technique (TMT) and independent component analysis (ICA). Biomedizinische Technik, 54(1): 29-37
  • K.E. Hild II, H.T. Attias, S. Comani, S.S. Nagarajan 2007 Fetal cardiac signal extraction from magnetocardiographic data using a probabilistic algorithm. Signal Processing, 87: 1993-2004
  • K.E. Hild II, G. Alleva, S.S. Nagarajan, S. Comani 2007 Performance comparison of six Independent Components Analysis algorithms for fetal signal extraction from real fMCG data. Phys Med Biol, 52: 449-462
  • A. Aragri, T. Scarabino, E. Seifritz, S. Comani, S. Cirillo, G. Tedeschi, F. Esposito, F. Di Salle 2006 How does spatial extent of fMRI datasets affect Independent Component Analysis decomposition?. Hum Brain Map, 27(9): 736-746
  • S. Comani, D. Mantini, G. Alleva, E. Gabriele, M. Liberati, G.L. Romani 2005 Simultaneous monitoring of separate fetal magnetocardiographic signals in twin pregnancy. Physiol Meas, 26: 193-201
  • F. Esposito, T. Scarabino, A. Hyvärinen, J. Himberg, E. Formisano, S. Comani, G. Tedeschi, R. Goebel, E Seifritz, F. Di Salle 2005 Independent Component Analysis of fMRI group studies by self-organizing clustering. Neuroimage, 25(1): 193-205
  • S. Comani, D. Mantini, G. Alleva, S. Di Luzio, G.L. Romani 2004 Fetal Magnetocardiographic Mapping using Independent Component Analysis. Physiol Meas, 25(6): 1459-1472
  • S. Comani, D. Mantini, A. Lagatta, F. Esposito, S. Di Luzio, G.L. Romani 2004 Time course reconstruction of fetal cardiac signals from fMCG: Independent Component Analysis vs. Adaptive Maternal Beat Subtraction. Physiol Meas, 25(5): 1305-1321

Conferences:

  • L.O. Murta Jr, D. Guilhon, E. Moraes, O. Baffa, S. Comani 2008 Segmented ICA method to separate the fetal magnetocardiogram from fMCG signals affected by fetal movements. Biomag 2008 – 16th International Conference on Biomagnetism, 25-29 August 2008, Ryoton (Sapporo, Japan).
  • D. Guilhon, A. Mensah-Brown, S. Comani, M. Liberati, A.K. Barros, J.F. Strasburger, R.T. Wakai 2008 Separation of fetal magnetocardiograms in triplet pregnancies. Biomag 2008 – 16th International Conference on Biomagnetism, 25-29 August 2008, Ryoton (Sapporo, Japan).
  • D. Guilhon, A.K. Barros, S. Comani 2007 ECG compression by efficient coding. ICA2007 – 7th International Conference on Independent Component Analysis and Signal Separation, London (UK), 9-12 September 2007
  • P. van Leeuwen, S. Comani, D. Geue, D. Mantini, S. Lange, G. Alleva, D. Grönemeyer 2006 Effect of independent component analysis on processing the fetal magnetocardiogram. Biomag 2006 – 15th International Conference on Biomagnetism, Vancouver (Canada) 20-26 August 2006.
  • S. Comani, H. Preissl, D. Mantini, Q. Campbell, G. Alleva, H. Eswaran 2006 Comparison of algorithms for fetal signal reconstruction: Projector Operator vs. Independent Component Analysis. Biomag 2006 – 15th International Conference on Biomagnetism, Vancouver (Canada) 20-26 August 2006.
  • S. Comani, G. Alleva, K. Melchiorre, M. Liberati 2006 Fetal magnetocardiography: a new technique for the monitoring of the fetal cardiac activity. EBCOG 2006 – 19th European Congress on Obstestrics and Gynecology, Torino (Italy), 5-8 April 2006.
  • S. Comani, D. Mantini, K. Melchiorre, M. Liberati 2006 Independent Component Analysis (ICA) for the reconstruction of reliable fetal magnetocardiograms. EBCOG 2006 – 19th European Congress on Obstestrics and Gynecology, Torino (Italy), 5-8 April 2006.

Nonlinear dynamics

We estimate linear and nonlinear parameters (such as Short Term Variability (STV), Approximated Entropy (ApE), Sample Entropy (SE) and Multiscale Entropy (MSE)) in order to describe more comprehensively the behavior of complex physiological systems.

We are developing a method that, by means of dynamic estimators of chaos, such as correlation dimensions and Lyapunov exponents, might permit to assess the dynamics of physiological systems that exhibit a complex behavior. Furthermore, by means of those estimators we intend to characterize the evolution of systems such as the heart and the brain during their development in the life span.

Publications:

  • S. Comani, V. Srinivasan, G. Alleva, G.L. Romani. 2007 Entropy based automated classification of independent components separated from fMCG. Phys Med Biol, 52(5): N87-N97

Conferences:

  • Moraes E.R., Murta Jr. L.O., Guilhon D.,Baffa O., Wakai, R. T., Comani S. 2009 Correlation of Linear and Non-Linear Parameters on fetal Magnetocardiograms. PB2009 – First International Workshop on Perinatal Biomagnetism, Chieti, Italy, 4 April 2009.
  • Di Bari M.T., Cipriani P., Guilhon D. and Comani S. 2009 Non linear dynamical analysis of the evolution of the fetal cardiovascular system. PB2009 – First International Workshop on Perinatal Biomagnetism, Chieti, Italy, 4 April 2009.
  • Cipriani P., Comani S. and Di Bari M.T.2008 Non linear dynamics of fetal magnetocardiographic signals. ESGCO 2008 – 5th International Conference on the European Study Group on Cardiovascular Oscillations, Parma, Italy, 7-9 April 2008.
  • Di Bari M.T., Cipriani P. and Comani S. 2008 Dynamical indicators of chaos for fetal magnetocardiographic signals. Biomag 2008 – 16th International Conference on Biomagnetism, 25-29 August 2008, Ryoton (Sapporo, Japan).
  • E. Moraes, L.O. Murta Jr, D. Guilhon, D. de Araujo, O. Baffa, S. Comani 2008 Early assessment of fetal well-being by means of nonlinear parameters (STV, ApEn and SampEn): a fMCG study on normal pregnancies. Biomag 2008 – 16th International Conference on Biomagnetism, 25-29 August 2008, Ryoton (Sapporo, Japan).
  • L.O. Murta Jr, D. Guilhon, E. Moraes, O. Baffa, S. Comani 2008 Multiscale entropy analysis of fMCG heart rate variability at different pregnancy ages: preliminary results. Biomag 2008 – 16th International Conference on Biomagnetism, 25-29 August 2008, Ryoton (Sapporo, Japan).

Automatic pattern recognition systems

We are developing a system for the automatic detection of functional patterns embedded in physiological data sets recorded with multi-channel systems. This system aims at classifying, in a observer-independent manner, clinical and non clinical populations. Our system is based on the conjoint use of a multilayer perceptron (MLP) neural network that is trained with estimates of linear and nonlinear system parameters, such as ICA features and entropy estimators.

Publications:

  • S. Comani, D. Guilhon, P. van Leeuwen, D. Duarte Costa, A.K. Barros, B. Hailer, D. Grönemeyer. 2007 Effectiveness of ICA processing for feature extraction in magneto-cardiographic signals. Biomedizinische Technik, 52: CD-ROM, 2007

Conferences:

  • D. Guilhon, D.D. Costa, P. Van Leeuwen, B. Hailer, A.K. Barros, S. Comani 2008 ICA-based pattern recognition system for the classification of Coronary Artery Disease patients studied with Magnetocardiography. Biomag 2008 – 16th International Conference on Biomagnetism, 25-29 August 2008, Ryoton (Sapporo, Japan).