Loading patent…
OwnerStanley C. Kwasny, Barry L. Kalman +1inventors
InventorsStanley C. Kwasny, Barry L. Kalman, William R. Reinus
Estimating the term…
Fully automated methods and systems for processing complex data sets to identify abnormalities are described. In one embodiment, the system includes wavelet processing, recursive processing to determine prominent features, and then utilizing feed forward neural networks (FFNNs) to classify feature vectors generated in the wavelet and recursive processing. With respect to wavelet processing, multiresolution (five-level) and multidirection (two-dimensional) wavelet analysis with quadratic spline wavelets is performed to transform each image. The wavelets are a first-order derivative of a smoothing function and enhance the edges of image objects. Because two-dimensional wavelet transforms quantize an image in terms of space and spatial frequency and can be ordered linearly, the data is processed recursively to determine prominent features. A neural network approach derived from sequential recursive auto-associative memory is then used to parse the wavelet coefficients and hierarchy data. Since the wavelet coefficients are continuous, linear output instead of sigmoidal output is used. This variation is therefore referred to as linear output sequential recursive auto-associative memory, or LOSRAAM. The objective of training the LOSRAAM network is to have the output exactly match the input. Context units arising from serial evaluation of the wavelet coefficient triplets may be collected as vectors. These vectors are subjected to cluster analysis. This analysis yields a number of identifiable and discrete states. From these states, feature vectors are created. Each element in the feature vector represents the number of times the corresponding state from the above cluster analysis is found. Then, feed forward neural networks (FFNNs) are trained to classify feature vectors.
A system for analyzing digitized x-ray mammography image data to identify abnormalities, said system comprising a processor programmed to perform:
A system for compressing an entire complex data set to a size sufficient for presentation to a neural network for the neural network to detect abnormalities in the data set, the complex data set comprising waveform signal data in one or more dimensions that is susceptible to wavelet transformation, said system comprising a processor programmed to perform wavelet processing of the complex data set with quadratic spline wavelets, and recursive processing of the complex data set.
A system for processing a complex data set to identify abnormalities, said system comprising a processor programmed to perform:
A system for processing image data to identify abnormalities in a image, said system comprising a processor programmed to perform:
A method for processing waveform signal data in one or more dimensions to identify abnormalities, said method comprising the steps of:
A method for processing image data to identify abnormalities, said method comprising the steps of:
A method for processing waveform signal data in one or more dimensions to identify abnormalities in the waveform signal data, said method comprising:
Dependencies are inferred from the claim text.