Determination method, determination apparatus, and recording medium
In a method of determining the type of each cell contained in a sample, one Raman spectrum is acquired from one undetermined cell, a plurality of degrees of matching of a Raman spectrum of the undetermined cell with respect to spectra of a plurality of principal components obtained by principal component analysis of a plurality of Raman spectra that are obtained one by one from each of a plurality of known types of cells are calculated, and a type of the undetermined cell is determined by classifying the plurality of degrees of matching based on a result obtained by classifying a plurality of principal component scores corresponding to each of the plurality of known types of cells obtained by the principal component analysis depending on the type of cells by a learning model using supervised learning.
1. A determination method of determining a type of each cell contained in a sample, comprising:
acquiring one Raman spectrum from one undetermined cell;
calculating a plurality of degrees of matching of a Raman spectrum of the undetermined cell with respect to spectra of a plurality of principal components obtained by principal component analysis of a plurality of Raman spectra that are obtained one by one from each of a plurality of known types of cells; and
determining a type of the undetermined cell by classifying the plurality of degrees of matching, based on a result obtained by classifying a plurality of principal component scores corresponding to each of the plurality of known types of cells obtained by the principal component analysis depending on the type of cells by a learning model using supervised learning.
2. The determination method according to claim 1 , wherein
the learning model is a support vector machine.
3. The determination method according to claim 1 , wherein
the machine learning of the learning model is performed using, as training data, the plurality of principal component scores corresponding to each of the plurality of known types of cells and each of the types of the plurality of cells.
4. The determination method according to claim 1 , wherein
one entire cell is irradiated with excitation light, and
a Raman spectrum is acquired by measuring Raman scattered light from the one entire cell.
5. A determination apparatus for determining a type of each cell contained in a sample, comprising:
a processor; and a memory, wherein the processor is operable to:
calculate a plurality of degrees of matching of a Raman spectrum acquired from an undetermined cell with respect to spectra of a plurality of principal components obtained by principal component analysis of a plurality of Raman spectra that are obtained one by one from each of a plurality of known types of cells; and
determine a type of the undetermined cell by classifying the plurality of degrees of matching based on a result obtained by classifying a plurality of principal component scores corresponding to each of the plurality of known types of cells obtained by the principal component analysis depending on the type of cells by a learning model using supervised learning.
6. The determination apparatus according to claim 5 , wherein the processor is further operable to
perform machine learning of the learning model using, as training data, the plurality of principal component scores corresponding to each of the plurality of known types of cells and each of the types of the plurality of cells.
7. The determination apparatus according to claim 6 , wherein the processor is further operable to
acquire the training data from outside.
8. The determination apparatus according to claim 5 , wherein the processor is further operable to
acquire, from outside, the spectra of the plurality of principal components and a result, which is obtained by classifying the plurality of principal component scores corresponding to each of the plurality of known types of cells depending on the type of cells by the learning model.
9. A recording medium recording a computer program for causing a computer to execute a process for determining a type of each cell contained in a sample, the computer program causing the computer to execute a process including:
a step of calculating a plurality of degrees of matching indicating a degree of contribution of a Raman spectrum acquired from an undetermined cell to spectra of a plurality of principal components obtained by principal component analysis of a plurality of Raman spectra that are obtained one by one from each of a plurality of known types of cells; and
a step of determining a type of the undetermined cell by classifying the plurality of degrees of matching, based on a result obtained by classifying a plurality of principal component scores corresponding to each of the plurality of known types of cells obtained by the principal component analysis depending on the type of cells by a learning model using supervised learning.