Blood flow field estimation apparatus, learning apparatus, blood flow field estimation method, and program
A blood flow field estimation apparatus is provided, including an estimation unit that uses a learned model obtained in advance by performing machine learning to learn a relationship between organ tissue three-dimensional structure data including image data of a plurality of organ cross-sectional images serving as cross-sectional images of an organ and having each pixel provided with two or more bit depths and image position information serving as information indicating a position of an image reflected on each of the organ cross-sectional images in the organ, and a blood flow field in the organ, and estimates the blood flow field in the organ of an estimation target, based on the organ tissue three-dimensional structure data of the organ of the estimation target, and an output unit that outputs an estimation result of the estimation unit.
1. A blood flow field estimation apparatus, comprising:
a processor; and
a storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by the processor, perform:
by using a learned model obtained in advance by performing machine learning to learn a relationship between organ tissue three-dimensional structure data including image data of a plurality of organ cross-sectional images serving as cross-sectional images of an organ and having each pixel provided with two or more bit depths and image position information serving as information indicating a position of an image reflected on each of the organ cross-sectional images in the organ, and a blood flow field in the organ, estimating the blood flow field in the organ of an estimation target, based on the organ tissue three-dimensional structure data of the organ of the estimation target;
outputting an estimation result of the estimation,
dividing the organ tissue three-dimensional structure data into a plurality of partial data serving as data satisfying a partial condition; and
estimating the blood flow field in the organ of the estimation target by using the learned model for each of the partial data,
wherein the partial condition includes a condition that the partial data is partial information of the organ tissue three-dimensional structure data, a condition that the partial data indicates a pixel value at each position of a partial space in the organ out of pixel values indicated by the organ tissue three-dimensional structure data, and a condition that information indicated by a sum of all of the divided partial data is the same as information indicated by the organ tissue three-dimensional structure data.
2. The blood flow field estimation apparatus according to claim 1 ,
wherein in the organ, fluid characteristics of blood vessels are substantially the same as each other regardless of the estimation target.
3. The blood flow field estimation apparatus according to claim 2 ,
wherein the organ is a brain.
4. The blood flow field estimation apparatus according to any one of claim 1 ,
wherein a method of the machine learning is deep learning.
5. The blood flow field estimation apparatus according to claim 4 ,
wherein a method of the deep learning is a U-Net method.
6. A non-transitory computer readable medium which stores a program for operating a computer to function as the blood flow field estimation apparatus according to claim 1 .