Image analysis method, image analysis apparatus, and image analysis program for analyzing cell with deep learning algorithm
AssigneeSysmex Corporation
InventorsYoshinori SASAGAWA, Yoshiaki MIYAMOTO, Kazumi HAKAMADA, Kengo GOTOH, Yosuke SEKIGUCHI
Life of this patent
Estimating the term…
Abstract
An image analysis method according one or more embodiments may analyze a form of a cell using a deep learning algorithm with a structure of a neural network. The image analysis method may include: generating data for analysis from an image for analysis in which an analysis target cell is captured; inputting the data for analysis into the deep learning algorithm; and generating data indicating a form of the analysis target cell using the deep learning algorithm.
Claims21
1-20. (canceled)
An image analysis method of analyzing a form of a cell using a deep learning algorithm with a structure of a neural network, comprising:
- generating, for each window set on an image for analysis in which an analysis target cell is captured, data for analysis based on the image for analysis, wherein the window is different depending on a type or a size of the analysis target cell;
- inputting the data for analysis into the deep learning algorithm;
- and
- outputting, from the deep learning algorithm, labels indicating whether each of pixels in the image for analysis is a pixel of the analysis target cell or a pixel of background.
An image analysis apparatus that analyzes a form of a cell using a deep learning algorithm with a structure of a neural network, comprising a controller that performs operations comprising:
- generating, for each window set on an image for analysis in which an analysis target cell is captured, data for analysis based on the image for analysis, wherein the window is different depending on a type or a size of the analysis target cell;
- inputting the data for analysis into the deep learning algorithm;
- and
- outputting, from the deep learning algorithm, labels indicating whether each of pixels in the image for analysis is a pixel of the analysis target cell or a pixel of background.
A non-transitory computer-readable recording medium storing a computer program for analyzing a form of a cell using a deep learning algorithm with a structure of a neural network and that causes a computer to perform operations comprising:
- generating, for each window set on an image for analysis in which an analysis target cell is captured, data for analysis based on the image for analysis, wherein the window is different depending on a type or a size of the analysis target cell;
- inputting the data for analysis into the deep learning algorithm;
- and
- outputting, from the deep learning algorithm, labels indicating whether each of pixels in the image for analysis is a pixel of the analysis target cell or a pixel of background.
Dependencies are inferred from the claim text.