Optimum Segmentation of Medical Images with Hopfield Neural Networks

In this chapter we present a general purpose neural architecture for segmenting 2{D and 3{D medical images. The architecture is based on a continuous Hop eld neural network including one or more sets of 2{D layers of neurons with local connections. This architecture can be specialised to perform the segmentation of 2{D images, the multi-scale segmentation of 2{D images and the segmentation of 3-D images by simply changing the number of such sets and/or the size of the component layers. By changing synaptic weights the architecture can adapt to the di erences existing between tomographic and radiographic images. The segmentation produced by this architecture is optimum with respect to a goodness criterion which establishes the tradeo between sensitivity and robustness. The chapter describes the derivation of the architecture and some experimental results obtained with synthetic and real medical images.

[1]  Wesley E. Snyder,et al.  Image segmentation with neurocomputers , 1989 .

[2]  T Lei,et al.  Statistical approach to X-ray CT imaging and its applications in image analysis. II. A new stochastic model-based image segmentation technique for X-ray CT image , 1992, IEEE Trans. Medical Imaging.

[3]  Benoit M. Dawant,et al.  Neural-network-based segmentation of multi-modal medical images: a comparative and prospective study , 1993, IEEE Trans. Medical Imaging.

[4]  David Sinclair,et al.  Automatic segmentation of hand-wrist radiographs , 1993, Image Vis. Comput..

[5]  Andrew S. Noetzel,et al.  Image processing and pattern recognition in ultrasonograms by backpropagation , 1990, Neural Networks.

[6]  Kim L. Boyer,et al.  Hypothesizing structures in edge-focused cerebral magnetic resonance images using graph-theoretic cycle enumeration , 1993 .

[7]  Bernard Mazoyer,et al.  Three-dimensional segmentation and interpolation of magnetic resonance brain images , 1993, IEEE Trans. Medical Imaging.

[8]  E L Ritman,et al.  Extraction of left-ventricular chamber from 3-D CT images of the heart. , 1990, IEEE transactions on medical imaging.

[9]  T. Reed.  Region Growing Using Neural Networks , 1992 .

[10]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[11]  London Wc.  Segmentation Of MR Images Using Neural Nets , 1991 .

[12]  C. Chen,et al.  Medical Image Segmentation By A Constraint Satisfaction Neural Network , 1990, 1990 IEEE Nuclear Science Symposium Conference Record.

[13]  R A Peters,et al.  Automatic segmentation of ultrasound images using morphological operators. , 1991, IEEE transactions on medical imaging.

[14]  G Coppini,et al.  A neural network architecture for understanding discrete three-dimensional scenes in medical imaging. , 1992, Computers and biomedical research, an international journal.

[15]  Riccardo Poli,et al.  An Artificial Vision System for X-ray Images of Human Coronary Trees , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[17]  Xinhua Zhuang,et al.  Robust segmentation of noisy images using a neural network model , 1992, Image Vis. Comput..

[18]  Jean-Yves Catros,et al.  An artificial intelligence approach for medical picture analysis , 1988, Pattern Recognit. Lett..

[19]  S P Raya,et al.  Low-level segmentation of 3-D magnetic resonance brain images-a rule-based system. , 1990, IEEE transactions on medical imaging.

[20]  L. T. Andrews,et al.  Segmentation of echocardiographic images using mathematical morphology , 1988, IEEE Transactions on Biomedical Engineering.

[21]  Lawrence O. Hall,et al.  Knowledge-based classification and tissue labeling of MR images of human brain , 1993, IEEE Trans. Medical Imaging.

[22]  Riccardo Poli,et al.  Recovery of 3D closed surfaces from sparse data , 1994 .

[23]  Jan Cornelis,et al.  Segmentation of medical images , 1993, Image Vis. Comput..

[24]  Yoshiyasu Takefuji,et al.  Optimization neural networks for the segmentation of magnetic resonance images , 1992, IEEE Trans. Medical Imaging.

[25]  Guido Gerig,et al.  Unsupervised tissue type segmentation of 3D dual-echo MR head data , 1992, Image Vis. Comput..