Computer-based assessment for facioscapulohumeral dystrophy diagnosis.

The paper presents a computer-based assessment for facioscapulohumeral dystrophy (FSHD) diagnosis through characterisation of the fat and oedema percentages in the muscle region. A novel multi-slice method for the muscle-region segmentation in the T1-weighted magnetic resonance images is proposed using principles of the live-wire technique to find the path representing the muscle-region border. For this purpose, an exponential cost function is used that incorporates the edge information obtained after applying the edge-enhancement algorithm formerly designed for the fingerprint enhancement. The difference between the automatic segmentation and manual segmentation performed by a medical specialists is characterised using the Zijdenbos similarity index, indicating a high accuracy of the proposed method. Finally, the fat and oedema are quantified from the muscle region in the T1-weighted and T2-STIR magnetic resonance images, respectively, using the fuzzy c-mean clustering approach for 10 FSHD patients.

Detection of the electrocardiogram fiducial points in the phase space using the Euclidian distance measure.

The paper proposes a phase-space based algorithm applying the Euclidian distance measure enabling detection of heartbeats and characteristic (fiducial) points from a single-lead electrocardiogram (ECG) signal. It extends the QRS detection in the phase space by detecting the P and T fiducial points. The algorithm is derived by reconstructing the ECG signals in a two-dimensional (2D) phase space according to the delay method and utilizes geometrical properties of the reconstructed phase portrait of the signal in the phase space for the heartbeat and fiducial-point detection. It uses adaptive thresholding and the Euclidian distance measure between the signal points in the phase portrait as an alternative to the phase-portrait area calculation (Lee et al., 2002). It was verified with the QT Database (2011) and its performance was assessed using sensitivity (Se) and the positive predictive value (PPV). Results for the proposed algorithm are 99.06%, 99.75% and 99.66% for Se and 94.87%, 99.75% and 99.66% for PPV for the P points, heartbeats and T points, respectively.