Cytologic diagnosis support apparatus, cytologic diagnosis support method, remote diagnosis support system, service providing system, and image processing method
The present invention realizes determination of tissues and cells from an image by calculating feature values of a deformed degree of the cells even in a case where the tissues or the cells have various shapes. An image diagnosis support apparatus according to the present invention executes processing of inputting an image of cells, processing of extracting the feature values of a plurality of direction components from a target image of the processing, processing of determining whether or not the image corresponds to one-classification by using the plurality of feature values, and processing of determining whether or not the determination processing is finished with respect to all of the classifications set in advance (FIG. 1 ).
1. A cytologic diagnosis support apparatus that improves classification of abnormal cells, the apparatus comprising:
an input that receives a target image of potentially abnormal cells;
a memory;
a processor that is communicatively coupled to the input and the memory; wherein the processor is configured to: rotate the target image by a predetermined amount a predetermined number of times to form a plurality of rotated images,
determine a plurality of feature values for the plurality of rotated images, wherein each of the plurality of feature values corresponds to a respective rotated image from the plurality of rotated images,
calculate a variance of the plurality of feature values between the plurality of rotated images,
perform a comparison of the variance of the plurality of feature values between the plurality of rotated images and a threshold, and
determine a final determination result that indicates whether or not the target image corresponds to one-classification based on the comparison.
2. The cytologic diagnosis support apparatus according to claim 1 ,
wherein the plurality of feature values are determined by applying an image filter.
3. The cytologic diagnosis support apparatus according to claim 1 ,
wherein the threshold is acquired by performing machine learning with respect to previously classified images.
4. The cytologic diagnosis support apparatus according to claim 1 , wherein the processor is further configured to:
display the final determination result.
5. A cytologic diagnosis support method that improves classification of abnormal cells, the method comprising:
receiving, by a processor, a target image of potentially abnormal cells;
rotating, by the processor, the target image by a predetermined amount a predetermined number of times to form a plurality of rotated images;
determining, by the processor, a plurality of feature values for the plurality of rotated images, wherein each of the plurality of feature values corresponds to a respective rotated image from the plurality of rotated images;
calculating, by the processor, a variance of the plurality of feature values between the plurality of rotated images;
performing, by the processor, a comparison of the variance of the plurality of feature values between the plurality of rotated images and a threshold; and
determining a final determination result that indicates whether or not the target image corresponds to one-classification based on the comparison.
6. The cytologic diagnosis support method according to claim 5 ,
wherein the plurality of feature values are determined by applying an image filter.
7. The cytologic diagnosis support method according to claim 5 ,
wherein the threshold is acquired by performing machine learning with respect to previously classified images.
8. The cytologic diagnosis support method according to claim 5 , further comprising:
displaying, by the processor, the final determination result.
9. The cytologic diagnosis support apparatus according to claim 1 , wherein:
the input receives the target image from an imager that is located at a remote location; and
the processor further sends the determination result to a display located at the remote location.