US 2012/0237103 A1 · METHOD AND DEVICE FOR DETECTING BRIGHT BRAIN REGIONS FROM COMPUTED TOMOGRAPHY IMAGES

Abstract

A method and devices are disclosed to detect bright brain regions (BBRs) from clinical non-enhanced computed tomography images through large grayscale, large grayscale asymmetry with respect to the midsagittal plane (MSP), and large grayscale local contrast. An adaptive approach is disclosed to determine thresholds of the 3 features and adjust the window width for data conversion. The substantial grayscale variability of BBRs for a subject is addressed by finding the bright portion followed by recovering. Those BBR voxels symmetrical to the MSP are recovered, partial volume effects are compensated and the high grayscale regions which may not correspond to intracerebral hemorrhage are excluded. The disclosed method and system could be a useful tool to aid classifying stroke types, quantifying intracerebral hemorrhage and enhancing stroke therapy.

Claims34

Dependent claims

A method for detecting the bright brain regions from computed tomography images, comprising:

loading computed tomography images data;
deriving the skull images;
deriving the brain images;
converting said brain images to the lower bit images data;
calculating the generalized asymmetry map with respect to the midsagittal plane;
calculating grayscale threshold, threshold of local contrast, threshold of asymmetry, and threshold of partial volume voxels for bright brain regions;
deriving initial bright brain regions;
recovering bright brain voxels symmetrical to the midsagittal plane;
refining the initial bright brain regions;
checking if the detected BBRs is low or high in average grayscale and the window width being increased or decreased when the detected BBRs is low or high in average grayscale and going back to the converting step;
and
outputting the bright brain regions.

9 more elements

A device for detecting the bright brain regions from computed tomography images, comprising:

an input unit loading computed tomography images data;
a first deriving unit deriving the skull images;
a second deriving unit deriving the brain images;
a convertor converting said brain images to the lower bit images data;
a first calculator calculating the generalized asymmetry map with respect to the midsagittal plane;
a second calculator calculating grayscale threshold, threshold of local contrast, threshold of asymmetry, and threshold of partial volume voxels for bright brain regions;
a third deriving unit derive initial bright brain regions;
a recovering unit recovering bright brain voxels symmetrical to the midsagittal plane;
a refining unit refining the initial bright brain regions;
a judging unit checking if the detected BBRs is low or high in average grayscale and the window width being increased or decreased when the detected BBRs is low or high in average grayscale and going back to the converting step;
and
an output unit outputting the bright brain regions.

9 more elements

Dependencies are inferred from the claim text.

Method and device for detecting bright brain regions from computed tomography images

Life of this patent

Method and device for detecting bright brain regions from computed tomography images

Life of this patent

Abstract

Claims34