Self-Organized three dimensional feature extraction of MRI and CT

Authors:
Satoru Morita
Affiliations:
Faculty of Engineering, Yamaguchi University, Ube, Japan
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part V
Year:
2012

Citing 4
Cited 0

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces

Neural Computation
Generating Saliency Map Related to Motion Based on Self-organized Feature Extracting

Advances in Neuro-Information Processing
Generating Self-organized Saliency Map Based on Color and Motion

ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We can observes a section of the body using MRI and CT . CT is suitable for the blood flow and the diagnosis of the wrong point of the bone by the computed tomograph, and MRI is suitable for the diagnosis of the cerebral brain infarction and the brain tumor. Because different nature is observed to so same the observation object, a, doctor, uses CT and an MRI image complementary, and sees a patient. The feature which appears in both images remarkably is extracted using the CT image and the MRI image by this paper. Various three-dimensional filters are generated using the ICA base in the self-histionic target from the characteristic image for that image, and how to extract a remarkable feature from the feature image which could get is proposed by this research. A remarkable feature is extracted from the CT image and the MRI image of the patient which actually has a tumor , and its effectiveness is shown.