Information processing apparatus, information processing method, and program
View Patent ↗Provided is an information processing apparatus including an image supply unit that supplies a plurality of input images showing corresponding objects to an image processing unit and obtains a plurality of object images as an image processed result from the image processing unit, and a display control unit that synchronously displays the plurality of object images that have been obtained. The object images are regions including the corresponding objects extracted from the plurality of input images, and orientations, positions, and sizes of the corresponding objects of the plurality of object images are unified.
1. An information processing apparatus comprising:
a processor; and
a memory device, the memory device storing instructions that cause the processor to:
obtain a first pathological image and a second pathological image,
identify a first tissue area from the first pathological image based on an identification function using a detection dictionary which is pre-generated through statistical learning using learning cellular tissue region images,
identify a second tissue area from the second pathological image based on the identification function using the detection dictionary,
associate the first tissue area and the second tissue area with respective tissue samples using an automatic clustering technique,
wherein the first pathological image is at least one of a dark field image, a bright field image or a phase difference image,
wherein the second pathological image is at least one of the dark field image, the bright field image or the phase difference image,
wherein the first pathological image and the second pathological image are images including cell tissue obtained from the same specimen,
adjust at least one of shapes, orientations, positions, and sizes of the second tissue area,
cause a display device to display the first tissue area, and
cause the display device to display a second part of the second tissue area on a first part of the first tissue area, wherein the second part of the second tissue area is corresponding to the first part of the first tissue area.
2. The information processing apparatus according to claim 1 , wherein the first pathological image and the second pathological image are images obtained by imaging tissue obtained by staining cell tissues cut out from the same specimen with different reagents.
3. The information processing apparatus according to claim 1 , wherein the memory device stores instructions that cause the processor to classify the first tissue area and the second tissue area into groups based on an image pattern.
4. The information processing apparatus according to claim 3 , wherein the instructions that cause the processor to adjust at least one of shapes, orientations, positions, and sizes of the second tissue area are instructions that cause the processor to adjust at least one of shapes, orientations, positions, and sizes of the second tissue area when the first tissue area and the second tissue area are classified into the same group.
5. The information processing apparatus according to claim 1 , wherein the identification function is based on training data comprising an image whose center is a cellular tissue region and an image whose center is a background portion.
6. An information processing method performed by an information processing apparatus, comprising:
obtaining a first pathological image and a second pathological image,
identifying a first tissue area from the first pathological image based on an identification function using a detection dictionary which is pre-generated through statistical learning using learning cellular tissue region images,
identifying a second tissue area from the second pathological image based on the identification function using the detection dictionary,
associating the first tissue area and the second tissue area with respective tissue samples using an automatic clustering technique,
wherein the first pathological image is at least one of a dark field image, a bright field image or a phase difference image,
wherein the second pathological image is at least one of the dark field image, the bright field image or the phase difference image,
wherein the first pathological image and the second pathological image are images including cell tissue obtained from the same specimen,
adjusting at least one of shapes, orientations, positions, and sizes of the second tissue area,
causing a display device to display the first tissue area, and
causing the display device to display a second part of the second tissue area on a first part of the first tissue area, wherein the second part of the second tissue area is corresponding to the first part of the first tissue area.
7. The information processing method according to claim 6 , wherein the first pathological image and the second pathological image are images obtained by imaging tissue obtained by staining cell tissues cut out from the same specimen with different reagents.
8. The information processing method according to claim 6 , further comprising classifying the first tissue area and the second tissue area into groups based on an image pattern.
9. The information processing method according to claim 8 , wherein adjusting at least one of shapes, orientations, positions, and sizes of the second tissue area comprises adjusting at least one of shapes, orientations, positions, and sizes of the second tissue area when the first tissue area and the second tissue area are classified into the same group.
10. The information processing method according to claim 6 , wherein the identification function is based on training data comprising an image whose center is a cellular tissue region and an image whose center is a background portion.
11. A non-transitory computer-readable medium having stored thereon a computer-readable program for causing a computer to:
obtain a first pathological image and a second pathological image,
identify a first tissue area from the first pathological image based on an identification function using a detection dictionary which is pre-generated through statistical learning using learning cellular tissue region images,
identify a second tissue area from the second pathological image based on the identification function using the detection dictionary,
associate the first tissue area and the second tissue area with respective tissue samples using an automatic clustering technique,
wherein the first pathological image is at least one of a dark field image, a bright field image or a phase difference image,
wherein the second pathological image is at least one of the dark field image, the bright field image or the phase difference image,
wherein the first pathological image and the second pathological image are images including cell tissue obtained from the same specimen,
adjust at least one of shapes, orientations, positions, and sizes of the second tissue area,
cause a display device to display the first tissue area, and
cause the display device to display a second part of the second tissue area on a first part of the first tissue area, wherein the second part of the second tissue area is corresponding to the first part of the first tissue area.
12. The computer-readable medium according to claim 11 , wherein the first pathological image and the second pathological image are images obtained by imaging tissue obtained by staining cell tissues cut out from the same specimen with different reagents.
13. The computer-readable medium according to claim 11 , wherein the computer-readable program further causes the computer to classify the first tissue area and the second tissue area into groups based on an image pattern.
14. The computer-readable medium according to claim 13 , wherein causing the computer to adjust at least one of shapes, orientations, positions, and sizes of the second tissue area, comprises causing the computer to adjust at least one of shapes, orientations, positions, and sizes of the second tissue area when the first tissue area and the second tissue area are classified into the same group.
15. The computer-readable medium according to claim 11 , wherein the identification function is based on training data comprising an image whose center is a cellular tissue region and an image whose center is a background portion.
16. An information processing apparatus comprising:
a processor; and
a memory device, the memory device storing instructions that cause the processor to:
obtain a first pathological image and information regarding a first area of the first pathological image,
determine a second area of a second pathological image corresponding to the first area of the first pathological image,
and
cause a display device to display a portion of the second area of the second pathological image and a portion of the first area of the first pathological image, wherein of the portion of the second area of the second pathological image that is displayed and the portion of the first area of the first pathological image that is displayed are changeable by a user operation during display, such that a ratio of a displayed amount of the second area of the second pathological image to a displayed amount of the first area of the first pathological image is changeable by the user operation during display.