Image processing device, program, image processing method, computer-readable medium, and image processing system
An image processing device 20 acquires captured images obtained by imaging a sample including a target cell, sets an object region for detecting the target cell in the captured images, extracts a plurality of cell regions each including a cell from a peripheral region including a region other than the object region, sets a range of a feature quantity of the target cell based on a feature quantity obtained from each of the plurality of cell regions, and determines whether or not the target cell is included in the object region when the feature quantity obtained from the object region is included in the set range of the feature quantity.
1. An image processing device comprising:
a memory configured to store at least one program; and
a processor configured to execute the at least one program to implement:
a setting unit that sets an object region for detecting a target cell in each of captured images obtained by imaging a sample including the target cell;
an extraction unit that extracts a plurality of cell regions from a peripheral region including a region different from the object region;
a range setting unit that sets a range of a feature quantity of the target cell based on a feature quantity obtained from each of the plurality of cell regions; and
a determination unit that determines whether or not the target cell is included in the object region in response to determining that a feature quantity obtained from the object region is included in the range of the feature quantity set by the range setting unit.
2. The image processing device according to claim 1 ,
wherein the extraction unit extracts a plurality of cell regions each having a nucleus from the peripheral region including the region different from the object region, and
the range setting unit sets the range of the feature quantity of the target cell equal to or less than a threshold value set in the range of the feature quantity obtained from each of the plurality of cell regions in terms of a feature quantity representing the size of at least one of a cell and a nucleus.
3. The image processing device according to claim 2 ,
wherein the feature quantity is at least one of a cell area, a nucleus area, and a cell-to-nucleus area ratio.
4. The image processing device according to claim 1 , further comprising:
a state determination unit that determines whether a cell included in each cell region extracted by the extraction unit is in a dense state or in a solitary state,
wherein the range setting unit sets a range of a feature quantity of the target cell for each cell state determined by the state determination unit, and
the determination unit determines whether or not the target cell is included in the object region when the feature quantity obtained from the object region is included in the range of the feature quantity set by the range setting unit for the state of the cell included in the object region.
5. The image processing device according to claim 1 ,
wherein the range setting unit sets the range of the feature quantity of the target cell equal to or less than an average value or a median of the feature quantity obtained from each of the plurality of cell regions.
6. The image processing device according to claim 1 , further comprising:
a learning unit that mechanically learns an identification condition for identifying the target cell based on sample images corresponding to a positive example and a negative example of the target cell,
wherein the determination unit determines whether or not the target cell is included in the object region based on the identification condition when the feature quantity obtained from the object region is included in the range of the feature quantity set by the range setting unit.
7. The image processing device according to claim 1 ,
wherein the target cell is a nucleated red blood cell having a nucleus,
the image processing device further comprises a region extraction unit that extracts a nucleus candidate region to be a candidate of the nucleus from the plurality of captured images based on at least one of the color and concentration of the nucleus, and
the setting unit sets the object regions based on the range of the possible size of the nucleus candidate region and the target cell.
8. An image processing method which causes a computer to execute a process comprising:
setting an object region for detecting a target cell in each of captured images obtained by imaging a sample including the target cell;
extracting a plurality of cell regions each including a cell from a peripheral region including a region other than the object region;
setting a range of a feature quantity of the target cell based on a feature quantity obtained from each of the plurality of cell regions; and
determining whether or not the target cell is included in the object region in response to determining that a feature quantity obtained from the object region is included in the set range of the feature quantity set.
9. A non-transitory computer readable medium which stores a program causing a computer to execute a process for image processing, the process comprising:
setting an object region for detecting a target cell in each of captured images obtained by imaging a sample including the target cell;
extracting a plurality of cell regions each including a cell from a peripheral region including a region other than the object region;
setting a range of a feature quantity of the target cell based on a feature quantity obtained from each of the plurality of cell regions; and
determining whether or not the target cell is included in the object region in response to determining that a feature quantity obtained from the object region is included in the set range of the feature quantity.
10. An image processing system comprising:
an image processing device;
an optical microscope that is connected to the image processing device; and
a display device that is connected to the image processing device,
wherein the image processing device comprises,
a memory configured to store at least one program; and
a processor configured to execute the at least one program to implement:
a setting unit that sets an object region for detecting a target cell in each of captured images obtained by imaging a sample including the target cell;
an extraction unit that extracts a plurality of cell regions each including a cell from a peripheral region including a region different from the object region;
a range setting unit that sets a range of a feature quantity of the target cell based on a feature quantity obtained from each of the plurality of cell regions; and
a determination unit that determines whether or not the target cell is included in the object region in response to determining that a feature quantity obtained from the object region is included in the range of the feature quantity set by the range setting unit.