Intelligent Atlas for Automatic Image Analysis of Magnetic Resonance Imaging

Abstract

A non-invasive imaging system, including an imaging scanner suitable to generate an imaging signal from a tissue region of a subject under observation, the tissue region having at least one substructure; a signal processing system in communication with the imaging scanner to receive the imaging signal from the imaging scanner; and a data storage unit in communication with the signal processing system, wherein the data storage unit stores an anatomical atlas comprising data encoding spatial information of the at least one substructure in the tissue region, and a pathological atlas corresponding to an abnormality of the tissue region, wherein the signal processing system is adapted to automatically identify, using the imaging signal, the anatomical atlas, and the pathological atlas, a presence of the abnormality or a precursor abnormality in the subject under observation.

Description

CROSS-REFERENCE OF RELATED APPLICATION[0001]This application claims priority to U.S. Provisional Application No. 61 / 329,857 filed on Apr. 30, 2010, the entire contents of which are hereby incorporated by reference.[0002]The U.S. Government has a paid-up license in this invention and the right in limited circumstances to require the patent owner to license others on reasonable terms as provided for by the terms of Grant No.: R01AG20012 and P41RR15241, awarded by the National Institutes of Health.BACKGROUND[0003]1. Field of Invention[0004]The current invention relates to non-invasive imaging systems and methods, and more particularly to imaging systems and methods that provide computer assisted diagnosis of tissue abnormalities in human and animal subjects.[0005]2. Discussion of Related Art[0006]Conventional radiological diagnosis can be qualitative or subjective. Even though quantitative analyses may significantly improve our ability to detect and characterize abnormalities, currentl...

AI Technical Summary

Benefits of technology

The present invention is a non-invasive imaging system that can generate an imaging signal to observe tissue abnormalities. The system includes an imaging scanner, a signal processing system, and a data storage unit. The data storage unit contains anatomical and pathological atlases that describe the spatial information of substructures in a tissue region, including abnormalities. The signal processing system automatically identifies the abnormality or pre-cursor abnormality in the subject under observation by comparing the imaging signal to the atlases. This allows the system to provide a normalized image data that highlights the affected substructures and the statistical relationships between them. The pathological atlas also describes the transformation used to normalize the first image data. Overall, the invention improves the accuracy and efficiency of identifying abnormalities in tissue regions using non-invasive imaging techniques.

Problems solved by technology

Even though quantitative analyses may significantly improve our ability to detect and characterize abnormalities, currently almost no quantitative techniques can be accepted as a part of routine radiological diagnosis.

This is partly due to difficulties in analyzing tissue based on radiological, such as Magnetic Resonance (MR) images.

For example, high quality segmentation of the brain boundary requires a considerable amount of manual labor, which typically takes 2-4 hours for individual brains.

Further segmentation of the brain into tissue substructures takes even more time.

There are many automated programs for various types of tissue segmentation but they can only provide approximate results.

This approach has not proven to be effective and there is a need in the art for an automatic means to improve the ability to detect and characterize abnormalities from current radiological images.

Images