| CPC G06V 20/698 (2022.01) [G06V 10/774 (2022.01); G06V 20/693 (2022.01)] | 12 Claims |
|
1. An information processing device that detects a cell candidate region for determining a unity of a cell from a vessel image obtained by imaging a vessel in which the cell is seeded, the information processing device comprising:
at least one processor,
wherein the processor:
performs an acquisition process of acquiring the vessel image;
performs a detection process of detecting, from the vessel image acquired by the acquisition process, a cell region including the cell and a cell-like region including an object similar to the cell as cell candidate regions, using a trained model for detection which has been created by training a learning model using training data, the training data being a data set including a plurality of cell sample images given a label indicating the cell and a plurality of non-cell sample images given a label indicating a non-cell; and
performs an output process of outputting information indicating the detected cell candidate regions;
wherein the processor further:
performs a classification process of classifying, among the non-cell sample images, a non-cell sample image misclassified as the cell candidate region as a cell-like sample image, using a trained model for classification that classifies only the cell sample images out of the cell sample images and the non-cell sample images as the cell candidate regions; and
performs a learning process of creating the trained model for detection that detects the cell sample images and the cell-like sample images as the cell candidate regions.
|