MAGNETIC RESONANCE IMAGING APPARATUS, IMAGE PROCESSOR, AND IMAGE PROCESSING METHOD
Provided is a means that uses a two-dimensional image to distinguish a small region from other regions within the image and to highlight the small region. On the basis of the two-dimensional image where an organ such as blood vessels or a lesion such as microbleeds (collectively referred to as a designated region) is visualized, the designated region is discriminated from other regions, using a shape feature of the designated region and spatial feature of the space where the designated region exists. The spatial feature includes at least one of the followings; a spatial tissue distribution (presence probability for each tissue) of the designated region, and a spatial brightness distribution of pixel values of the designated region.
1 . A magnetic resonance imaging apparatus comprising
a reconstruction unit configured to collect magnetic resonance signals of an examination target and to reconstruct an image, and
an image processing unit configured to process the image reconstructed by the reconstruction unit, and to specify a region having a certain contrast, referred to as a designated region, included in the image, wherein
the image processing unit comprises a highlighting unit configured to highlight the designated region based on shape information of the designated region and spatial information of the designated region.
2 . The magnetic resonance imaging apparatus according to claim 1 , wherein
the spatial information includes at least one of a tissue distribution of the designated region in tissues of the examination target and a brightness distribution within the designated region.
3 . The magnetic resonance imaging apparatus according to claim 1 , wherein
the highlighting unit comprises
a shape filtering unit configure to create as a candidate image, an image of only a predetermined shape based on the shape information of the designated region, and a discrimination unit configured to discriminate between the designated region and other regions, wherein
the discrimination unit discriminates the designated region based on the spatial information of the candidate image created by the shape filtering unit.
4 . The magnetic resonance imaging apparatus according to claim 3 , wherein
the shape filtering unit comprises a first filter configured to extracting a first geometric feature of the designated region, and a second filter configured to extract a second geometric feature different from the first geometric feature, wherein
the shape filtering unit removes the second geometric feature extracted by the second filter from the first geometric feature, and creates the candidate image.
5 . The magnetic resonance imaging apparatus according to claim 4 , wherein
the designated region is a region of microbleeds, and the shape filtering unit comprises as the first filter, a granular shape highlighting filter configured to extract a circular shape, and comprises as the second filter, a linear shape highlighting filter configured to extract a linear shape.
6 . The magnetic resonance imaging apparatus according to claim 1 , wherein
the highlighting unit comprises a probability calculator configured to calculate a probability that the designated region exists in a specific organ or tissue of the examination target, and the highlighting unit makes discrimination of the designated region, using as the spatial information of the designated region, the probability that is calculated by the probability calculator.
7 . The magnetic resonance imaging apparatus according to claim 6 , wherein
the highlighting unit further comprises a segmentation unit configured to create segmentation images of the organ or the tissue of the examination target, wherein
the probability calculator calculates the probability of the designated region with respect to the segmentation images created by the segmentation unit.
8 . The magnetic resonance imaging apparatus according to claim 7 , wherein
an image of the examination target is a brain image, and the segmentation unit creates as the segmentation images, a brain parenchyma image and a cerebrospinal fluid image.
9 . The magnetic resonance imaging apparatus according to claim 1 , wherein
the highlighting unit comprises a discrimination unit configured to discriminate between the designated region and other tissue, wherein
the discrimination unit uses a CNN trained with features of the images including the designated region and the surrounding region thereof, to discriminate the designated region.
10 . The magnetic resonance imaging apparatus according to claim 1 , wherein
the highlighting unit uses a brightness distribution of the designated region, as the spatial information of the designated region.
11 . The magnetic resonance imaging apparatus according to claim 10 , wherein
the highlighting unit further comprises a CNN trained with multiple images having different brightness distributions of a predetermined shape, wherein
the highlighting unit uses the CNN to acquire information of the brightness distribution of the designated region.
12 . The magnetic resonance imaging apparatus according to claim 11 , wherein
the image processing unit comprises as the CNN, multiple CNNs trained respectively under multiple imaging conditions, wherein
the highlighting unit selects and applies one of the multiple CNNs in response to the imaging condition under which the image processing unit acquires the image to be processed.
13 . The magnetic resonance imaging apparatus according to claim 10 , wherein
the highlighting unit uses as the brightness distribution, a brightness gradient on the outline of the designated region.
14 . The magnetic resonance imaging apparatus according to claim 1 , wherein
the image processed by the image processing unit is a two-dimensional image.
15 . The magnetic resonance imaging apparatus according to claim 1 , wherein
the image processed by the image processing unit is at least one of a T2* weighted image and a susceptibility-weighted image.
16 . The magnetic resonance imaging apparatus according to claim 1 , further comprising
a display control unit configured to display on a display device, a processing result of the highlighting unit, together with the image.
17 . The magnetic resonance imaging apparatus according to claim 16 , wherein
the display control unit displays a GUI configured to accept user's modification on the result displayed on the display device, and passes the contents modified via the GUI, to the image processing unit.
18 . An image processor that processes an image acquired by magnetic resonance imaging, comprising
a shape filtering unit configured to acquire an image of only a predetermined shape included in the image, and
a highlighting unit configured to use at least one of a tissue distribution of the image of only the predetermined shape and a brightness distribution of the predetermined shape, to highlight a designated region having the predetermined shape.
19 . An image processing method that processes an image acquired by magnetic resonance imaging and highlights a designated region included in the image, comprising
a step of acquiring a candidate image of only a predetermined shape included in the image,
a step of acquiring spatial information of the predetermined shape, and
a step of highlighting the designated region based on the spatial information, wherein
the step of acquiring the spatial information includes either of a step of calculating a tissue distribution of the predetermined shape in the image, and a step of calculating a brightness distribution of an image of the predetermined shape.
20 . The image processing method according to claim 19 , wherein
the image acquired by magnetic resonance imaging is a two-dimensional T2* weighted image.