Medical image compression using topology-preserving neural networks

Authors:
Anke Meyer-Bäse;Karsten Jancke;Axel Wismüller;Simon Foo;Thomas Martinetz
Affiliations:
Department of Electrical Engineering, Florida State University, Tallahassee, FL 32310-6046, USA;Department of Electrical Engineering, Florida State University, Tallahassee, FL 32310-6046, USA;Department of Diagnostic Radiology, University of Munich, 80336 Munich, Germany;Department of Electrical Engineering, Florida State University, Tallahassee, FL 32310-6046, USA;Institute for Neuro- and Bioinformatics, University of Luebeck, Luebeck 23569, Germany
Venue:
Engineering Applications of Artificial Intelligence
Year:
2005

Citing 11
Cited 0

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Representation and separation of signals using nonlinear PCA type learning

Neural Networks
Topology representing networks

Neural Networks
Image quality in lossy compressed digital mammograms

Signal Processing
Embedded image coding using zerotrees of wavelet coefficients

IEEE Transactions on Signal Processing
Vector quantization of image subbands: a survey

IEEE Transactions on Image Processing
Optimal pyramidal and subband decompositions for hierarchical coding of noisy and quantized images

IEEE Transactions on Image Processing
Use of nonlinear principal component analysis and vector quantization for image coding

IEEE Transactions on Image Processing
A new, fast, and efficient image codec based on set partitioning in hierarchical trees

IEEE Transactions on Circuits and Systems for Video Technology
Image compression by self-organized Kohonen map

IEEE Transactions on Neural Networks
`Neural-gas' network for vector quantization and its application to time-series prediction

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

A novel method based on topology-preserving neural networks is used to implement vector quantization for medical image compression. The described method is an innovative image compression procedure, which differentiates itself from known systems in several ways. It can be applied to larger image blocks and represents better probability distribution estimation methods. A transformation-based operation is applied as part of the encoder on the block-decomposed image. The quantization process is performed by a ''neural-gas'' network which applied to vector quantization converges quickly to low distortion errors and reaches a distortion error lower than that resulting from Kohonen's feature map or the LBG algorithm. To study the efficiency of our algorithm, we blended mathematical phantom features into clinically proved cancer free mammograms. The influence of the neural compression method on the phantom features and the mammo-graphic image is not visually perceptible up to a high compression rate.