Specimen analysis method and image processing method
An image processing using a plurality of specimen images obtained by successively applying a plurality of types of staining to a specimen to be evaluated and imaging the specimen after staining for at least two types of staining is performed. The image processing comprises: extracting an inner region corresponding to inward of a cell membrane of a single cell in the specimen based on at least one of the specimen images; specifying a cell region corresponding to an individual cell included in the specimen by expanding the inner region outwardly; and performing image cytometry for the cell region based on the specimen images. In analyzing a pathological specimen on a cell-by-cell basis, it is possible to deal with multiple immunostaining and specify the positions of individual cells and evaluate each cell separately even when a cell density in the specimen is high.
1. A specimen analysis method, comprising:
obtaining a plurality of specimen images by successively applying a plurality of types of staining to a specimen to be evaluated and imaging the specimen after staining for at least two types of staining;
extracting an inner region being a closed region surrounded by a cell membrane and corresponding to inward of the cell membrane of a cell in the specimen by inputting at least one of the specimen images to a learning model constructed by machine learning in advance and obtaining an output image;
separating each extracted inner region as an individual cell included in the specimen from other inner region of other cells;
specifying a cell region corresponding to the individual cell by expanding the extracted inner region outwardly, and
performing image cytometry for the specified cell region based on the specimen images,
wherein the inner region is extracted based on the plurality of specimen images aligned with each other by executing alignment utilizing positions corresponding to each other among the plurality of specimen images,
wherein, for specifying the cell region:
an image processing which expands each point on a contour of the extracted inner region outwardly is performed until an expansion amount at the point reaches a predetermined specified value or a point on an expanded contour of the inner region contacts the other expanded inner region; and
a total region of the inner region and an expanded region by the image processing is specified as the cell region, and
wherein the inner region is extracted based on a combination of a plurality of the specimen images of different types of staining including a staining in which the cell membrane is selectively stained.
2. The specimen analysis method according to claim 1 , wherein the specimen is a tissue section having a thickness of less than 4 μm.
3. The specimen analysis method according to claim 1 , wherein the specimen is a tissue section having a thickness equal to or less than 2 μm.
4. The specimen analysis method according to claim 1 , wherein
the inner region is extracted from a specimen image captured after a staining in which a biological material present only inside of the cell membrane is selectively stained out of the plurality of types of staining.
5. The specimen analysis method according to claim 1 , wherein the specimen is decolorized before next staining after the imaging.
6. An image processing method using a plurality of specimen images obtained by successively applying a plurality of types of staining to a specimen to be evaluated and imaging the specimen after staining for at least two types of staining, the image processing method comprising:
extracting an inner region being a closed region surrounded by a cell membrane and corresponding to inward of the cell membrane of a cell in the specimen by inputting at least one of the specimen images to a learning model constructed by machine learning in advance and obtaining an output image;
separating each extracted inner region as an individual cell included in the specimen from other inner region of other cells;
specifying a cell region corresponding to the individual cell by expanding the extracted inner region outwardly, and
performing image cytometry for the specified cell region based on the specimen images,
wherein the inner region is extracted based on the plurality of specimen images aligned with each other by executing alignment utilizing positions corresponding to each other among the plurality of specimen images,
wherein for specifying the cell region:
an image processing which expands each point on a contour of the extracted inner region outwardly is performed until an expansion amount at the point reaches a predetermined specified value or a point on an expanded contour of the inner region contacts the other expanded inner region; and
a total region of the inner region and an expanded region by the image processing is specified as the cell region, and
wherein the inner region is extracted based on a combination of a plurality of the specimen images of different types of staining including a staining in which the cell membrane is selectively stained.
7. The specimen analysis method according to claim 1 , wherein a closed region surrounded by the cell membrane and not including the cell membrane is extracted as the inner region.
8. The image processing method according to claim 6 , wherein a closed region surrounded by the cell membrane and not including the cell membrane is extracted as the inner region.