Abstract: The present disclosure provides an operating method of a system for analyzing brain tissue based on computerized tomographic imaging, and the operation method includes steps as follows. A computed tomography image of a subject is aligned to a predetermined standard brain space image, to obtain a first normalized test computed tomography image. A voxel contrast of the first normalized test computed tomography image is enhanced to obtain an enhanced first normalized test computed tomography image. The enhanced first normalized test computed tomography image is aligned to an average computed tomographic image of a control group to obtain a second normalized test computed tomography image. An analysis based on the second normalized test computed tomography image and a plurality of computerized tomographic images of the control group is performed to obtain a t-score map.

Abstract: The present disclosure provides an operating method of a system for analyzing brain tissue based on computerized tomographic imaging, and the operation method includes steps as follows. A computed tomography image of a subject is aligned to a predetermined standard brain space image, to obtain a first normalized test computed tomography image. A voxel contrast of the first normalized test computed tomography image is enhanced to obtain an enhanced first normalized test computed tomography image. The enhanced first normalized test computed tomography image is aligned to an average computed tomographic image of a control group to obtain a second normalized test computed tomography image. An analysis based on the second normalized test computed tomography image and a plurality of computerized tomographic images of the control group is performed to obtain a t-score map.

Abstract: The present disclosure provides an operating method of an automatic brain infarction detection system on magnetic resonance imaging (MRI), which includes steps as follows. Images corresponding to different slices of a brain of a subject are received from the MRI machine. The image mask process is performed on first and second images of the images. It is determined whether the cerebellum image intensity and the brain image intensity in the first image are matched. When the cerebellum image intensity and the brain image intensity are not matched, the cerebellar image intensity in the first image is adjusted. The first image is processed through a nonlinear regression to obtain a third image. A neural network identify an infarct region by using the first, second and third images that are cut.

Abstract: A magnetic resonance imaging white matter hyperintensities region recognizing method and system are disclosed herein. The white matter hyperintensities region recognizing method includes receiving and storing a FLAIR MRI image, a spin-lattice relaxation time weighted MRI image, and a diffusion weighted MRI image. Registration and fusion are preformed, and a white matter mask is determined. An intersection image of the FLAIR MRI image and the white matter mask is taken, a first region is determined after normalizing the intersection image, a cerebral infarct region is removed from the first image through the diffusion weighted MRI image, and then a determination is made as to whether to remove a remaining region in order to form a white matter hyperintensities region in the FLAIR MRI image.

Abstract: A method for detecting a cerebral infarct includes receiving an image of a brain of a subject from a magnetic resonance imaging scanner, wherein the image has a plurality of voxels, and each of the voxels has a voxel intensity. Then, the voxel intensities are normalized, wherein the normalized voxel intensities have a distribution peak, and the normalized voxel intensity of the distribution peak is Ipeak. A threshold is determined, which is the Ipeak+ a value. Voxel having the normalized voxel intensity larger than the threshold is selected, wherein the selected voxel is the cerebral infarct. A method for quantifying the cerebral infarct is also provided.

Abstract: A magnetic resonance imaging white matter hyperintensities region recognizing method and system are disclosed herein. The white matter hyperintensities region recognizing method includes receiving and storing a FLAIR MRI image, a spin-lattice relaxation time weighted MRI image, and a diffusion weighted MRI image. Registration and fusion are preformed, and a white matter mask is determined. An intersection image of the FLAIR MRI image and the white matter mask is taken, a first region is determined after normalizing the intersection image, a cerebral infarct region is removed from the first image through the diffusion weighted MRI image, and then a determination is made as to whether to remove a remaining region in order to form a white matter hyperintensities region in the FLAIR MRI image.

Abstract: A method for detecting a cerebral infarct includes receiving an image of a brain of a subject from a magnetic resonance imaging scanner, wherein the image has a plurality of voxels, and each of the voxels has a voxel intensity. Then, the voxel intensities are normalized, wherein the normalized voxel intensities have a distribution peak, and the normalized voxel intensity of the distribution peak is Ipeak. A threshold is determined, which is the Ipeak+ a value. Voxel having the normalized voxel intensity larger than the threshold is selected, wherein the selected voxel is the cerebral infarct. A method for quantifying the cerebral infarct is also provided.