Cell image evaluation device and cell image evaluation control program
An evaluator 21 that evaluates states of cells included in each region of interest of a cell image, and a predictor 22 that performs, in advance, machine learning of a relationship between evaluation results for a specific region of interest within a first cell image obtained by imaging cells before a staining process and regions around the specific region of interest and staining states of cells of the specific region of interest within a second cell image obtained by imaging the same imaging targets as the cells of the first cell image after the staining process are provided. The predictor 22 predicts staining states of cells of a specific region of interest based on evaluation results for the specific region of interest and regions around the specific region of interest among the evaluation results for the third cell image of the cells before the staining process.
1. A cell image evaluation device comprising:
an evaluator that evaluates states of cells included in each region of interest for each region of interest of a cell image obtained by imaging cells, and outputs evaluation results; and
a predictor that performs, in advance, machine learning of a relationship between evaluation results of the evaluator for regions around a specific region of interest within at least one first cell image obtained by imaging cells before a staining process and staining states of cells of the specific region of interest within a second cell image obtained by imaging the same imaging targets as the cells of the first cell image after the staining process,
wherein the predictor predicts staining states of cells of a specific region of interest based on evaluation results for regions around the specific region of interest among the evaluation results of the evaluator for at least one third cell image obtained by imaging cells before the staining process, and outputs the predicted staining states.
2. The cell image evaluation device according to claim 1 ,
wherein the predictor outputs transition probabilities of two or more staining color intensities, as outputs of the staining states of the cells.
3. The cell image evaluation device according to claim 2 ,
wherein the predictor receives, as inputs, the evaluation results for the third cell image obtained by imaging an inside of a container that contains cells, and outputs staining states of cells of a plurality of regions of interest within the container, and
the cell image evaluation device further comprises an integration unit that integrates the staining states of the cells of each region of interest, and obtains staining states of the cells of the entire container.
4. The cell image evaluation device according to claim 2 ,
wherein the predictor receives, as an input, at least one culture condition.
5. The cell image evaluation device according to claim 3 ,
wherein the predictor outputs the transition probabilities of the two or more staining color intensities, as the outputs of the staining states of the cells, and
the integration unit integrates the transition probabilities of the two or more staining color intensities of each region of interest for each staining color intensity, and obtains the staining states of the cells of the entire container.
6. The cell image evaluation device according to claim 3 ,
wherein the predictor outputs the transition probabilities of the two or more staining color intensities, as the outputs of the staining states of the cells, and
the integration unit integrates the staining color intensities of the highest transition probabilities of the transition probabilities of the two or more staining color intensities of each region of interest, and obtains the staining states of the cells of the entire container.
7. The cell image evaluation device according to claim 1 ,
wherein the predictor receives, as inputs, the evaluation results for the third cell image obtained by imaging an inside of a container that contains cells, and outputs staining states of cells of a plurality of regions of interest within the container, and
the cell image evaluation device further comprises an integration unit that integrates the staining states of the cells of each region of interest, and obtains staining states of the cells of the entire container.
8. The cell image evaluation device according to claim 7 ,
wherein the predictor outputs the transition probabilities of the two or more staining color intensities, as the outputs of the staining states of the cells, and
the integration unit integrates the transition probabilities of the two or more staining color intensities of each region of interest for each staining color intensity, and obtains the staining states of the cells of the entire container.
9. The cell image evaluation device according to claim 7 ,
wherein the predictor outputs the transition probabilities of the two or more staining color intensities, as the outputs of the staining states of the cells, and
the integration unit integrates the staining color intensities of the highest transition probabilities of the transition probabilities of the two or more staining color intensities of each region of interest, and obtains the staining states of the cells of the entire container.
10. The cell image evaluation device according to claim 1 ,
wherein the predictor receives, as an input, at least one culture condition.
11. The cell image evaluation device according to claim 1 ,
wherein the evaluator evaluates at least whether the cells are in an undifferentiated state or a differentiated state.
12. The cell image evaluation device according to claim 1 ,
wherein the evaluator evaluates at least a density of nucleoli.
13. The cell image evaluation device according to claim 1 ,
wherein the evaluator evaluates at least a density of white streaks.
14. The cell image evaluation device according to claim 1 ,
wherein the evaluator evaluates at least whether the cells are fibroblasts or feeder cells.
15. The cell image evaluation device according to claim 1 ,
wherein the evaluator evaluates at least whether the cells are pluripotent stem cells or feeder cells.
16. The cell image evaluation device according to claim 1 ,
wherein the evaluator evaluates at least whether the cells are cells or non-cells.
17. The cell image evaluation device according to claim 1 ,
wherein the evaluator evaluates at least whether the cells are living cells or dead cells.
18. The cell image evaluation device according to claim 1 , further comprising:
an operation content determination unit that obtains information on the staining state of the cell output from the predictor, and determines an operation content for the cell based on the information on the staining state of the cell.
19. The cell image evaluation device according to claim 18 ,
wherein the operation content for the cell is subculturing, culture medium replacement, culture medium change, agent addition, picking, or genetic testing.
20. A non-transitory computer readable recording medium storing a cell image evaluation program causing a computer to function as:
an evaluator that evaluates states of cells included in each region of interest for each region of interest of a cell image obtained by imaging cells, and outputs evaluation results; and
a predictor that performs, in advance, machine learning of a relationship between evaluation results of the evaluator for regions around a specific region of interest within at least one first cell image obtained by imaging cells before a staining process and staining states of cells of the specific region of interest within a second cell image obtained by imaging the same imaging targets as the cells of the first cell image after the staining process,
wherein the predictor predicts staining states of cells of a specific region of interest based on evaluation results for regions around the specific region of interest among the evaluation results of the evaluator for at least one third cell image obtained by imaging cells before the staining process, and outputs the predicted staining states.