Issue 10 Volume 41 May 16, 2003

20030032957 Silesian Technical Univ., Gliwice
A New Approach to the P-Wave Detection and Classification Based Upon Application of Wavelet Neural Network
Domider, T.; Tkacz, E. J.; Kostka, P.; Wrzesniowski, A.; Oct 2001; 4 pp.; In English
Report No.(s): AD-A410247; No Copyright; Avail: CASI; A01, Hardcopy
Paper presents a new approach to P wave classification problem which is based upon the application of a new recently
develop and widely described tool such as Wavelet Neural Network, The novel idea of classification is based on creation of
own non-standard wavelet exactly as a P wave morphology template and then calculation of wavelet transform being a first
layer of classical multi-layer perceptron. The mentioned first layer works as a feature selector and extractor.
DTIC
Neural Nets; Wavelet Analysis; Electrocardiography
20030032986 Sophia Univ., Tokyo
Reconstruction of Bio-Conductivity Distribution from Tangential Magnet Field Measurements
Sumi, C.; Nagumo, K.; Oct 2001; 7 pp.; In English
Report No.(s): AD-A410510; No Copyright; Avail: CASI; A02, Hardcopy
We proposed a technique for reconstructing bio-electric conductivity distribution from measured tangential magnet field
data. That is, in the 2D ROI with an arbitrary depth two orthogonal tangential components of 3D current vector field were
respectively estimated from the synthetically measured two tangential magnetic fields, from which the 2D conductivity
distribution was estimated. To cope with inevitable measurement errors, a robust numerical solution was developed, in which
the modification method and the regularization method were efficiently utilized. By performing this 2D reconstruction at each
depth, 3D conductivity distribution could be estimated. As typical applications, pathological state and/or bio-electric
conductive path can be evaluated by monitoring the temporal change of the reconstructed 3D conductivity distribution. The
feasibility of this technique was briefly verified by reconstructing a conductivity distribution using simulated noise-filled
magnetic field data, with resultant reconstruction indicating that the approach could provide a practical means for robustly
reconstructing a conductivity distribution.
DTIC
Bioelectricity; Magnetic Fields; Electrical Resistivity; Numerical Analysis; Estimating
20030033101 Aristotle Univ. of Thessaloniki, Greece
Alignment of Serially Acquired Slices Using a Global Energy Function
Krinidis, Stelio; Nikou, Christophoros; Pitas, Ioannis; October 25, 2001; 5 pp.; In English
Report No.(s): AD-A410239; No Copyright; Avail: CASI; A01, Hardcopy
An accurate, computationally efficient and fully-automated algorithm for the alignment of 2D serially acquired sections
forming a 3D volume is presented. The method accounts for the main shortcomings of 3D image alignment: corrupted data
(cuts and tears), dissimilarities or discontinuities between slices, non parallel or missing slices. The approach relies on the
optimization of a global energy function, based on the object shape, measuring the similarity between a slice and its
neighborhood in the 3D volume. Slice similarity is computed using the distance transform measure in both directions. No
particular direction is privileged in the method avoiding global offsets, biases in the estimation and error propagation. The
method was evaluated on real images (medical and biological 3D data) and the experimental results demonstrated the
method’s accuracy as reconstruction errors are less than 1 degree in rotation and less than 1 pixel in translation.
DTIC
Algorithms; Alignment; Autonomy; Numerical Analysis; Optimization
20030033866 Inha Univ., Inchon, Korea, Republic of
A Speckle Reduction Filter Using Wavelet-Based Methods for Medical Imaging Application
Kang, Su Cheol; Hong, Seung Hong; October 25, 2001; 5 pp.; In English
Report No.(s): AD-A410299; No Copyright; Avail: CASI; A01, Hardcopy
One of the most significant features of diagnostic echocardiographic images is to reduce speckle noise and make better
image quality. In this paper we proposed a simple and effective filter design for image denoising and contrast enhancement
based on multiscale wavelet denoising method. Wavelet threshold algorithms replace wavelet coefficients with small
magnitude by zero and keep or shrink the other coefficients. This is basically a local procedure since wavelet coefficients
characterize the local regularity of a function. After we estimate distribution of noise within echocardiographic image then
apply to fitness Wavelet threshold algorithm. A common way of the estimating the speckle noise level in coherent imaging
175