Back to results
US 12,609,201 B2Granted
Prognosis prediction device, prognosis prediction method, and program
AssigneeTohoku University
InventorsNoriyuki Kadoya, Mariko Umeda, Yuto Sugai, Shohei Tanaka, Keiichi Jingu
Life of this patent
Estimating the term…
Abstract
An aspect of the invention is a prognosis prediction device including a prognosis prediction unit that predicts, using prognosis prediction information that indicates a relationship between graph tumor information that is information on an image of a tumor represented using an amount defined by a graph theory and a prognosis of a person or an animal having the tumor, a prognosis of an estimation target based on graph tumor information indicating an image of a tumor of the estimation target.
Claims6
A prognosis prediction device comprising:
- a processor;
- and
- a storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by the processor, perform processing of:
- predicting, using prognosis prediction information that indicates a relationship between graph tumor information that is information on an image of a tumor represented using an amount defined by a graph theory and a prognosis of a person or an animal having the tumor, a prognosis of an estimation target based on graph tumor information indicating an image of a tumor of the estimation target, and
- wherein
- the amount defined by the graph theory is an amount related to a vertex of a graph,
- the vertex of the graph is defined for each unit pixel that is a collection of one or more pixels adjacent to each other,
- the amount related to the vertex of the graph is an amount indicating a positional relationship between vertices for which weights are defined and a weight of each vertex, and
- the weight is a predefined index value related to a pixel value of each pixel in the unit pixel.
6 more elements
A prognosis prediction method comprising:
- predicting, using prognosis prediction information that indicates a relationship between graph tumor information that is information on an image of a tumor represented using an amount defined by a graph theory and a prognosis of a person or an animal having the tumor, a prognosis of an estimation target based on graph tumor information indicating an image of a tumor of the estimation target, wherein the amount defined by the graph theory is an amount related to a vertex of a graph, wherein the vertex of the graph is defined for each unit pixel that is a collection of one or more pixels adjacent to each other, wherein the amount related to the vertex of the graph is an amount indicating a positional relationship between vertices for which weights are defined and a weight of each vertex, and wherein the weight is a predefined index value related to a pixel value of each pixel in the unit pixel.
Dependencies are inferred from the claim text.