Medical image abnormality detection system and abnormality detection method
An abnormality detection system is a system that detects, based on a medical image, whether a prespecified anatomical structure included in the medical image is abnormal, and includes: an obtainer that obtains block information indicating one or more blocks that are each a region in which pixels representing the anatomical structure are connected in the medical image; and a determiner that determines and outputs whether the anatomical structure is abnormal, based on the number of blocks indicated by the block information obtained by the obtainer, wherein the determiner determines that the anatomical structure is not abnormal when the number of blocks indicated by the block information is 1, and determines that the anatomical structure is abnormal when the number of blocks indicated by the block information is 2 or more and the two or more blocks indicated by the block information satisfy a predetermined condition.
1. An abnormality detection system that detects, based on a medical image, whether a prespecified anatomical structure included in the medical image is abnormal, the abnormality detection system comprising:
an obtainer that obtains block information indicating one or more blocks that are each a region in which pixels representing the anatomical structure are connected in the medical image; and
a determiner that determines and outputs whether the anatomical structure is abnormal, based on a total number of the one or more blocks indicated by the block information obtained by the obtainer,
wherein the determiner determines that the anatomical structure is not abnormal when the total number of the one or more blocks indicated by the block information is 1, and determines that the anatomical structure is abnormal when the total number of the one or more blocks indicated by the block information is 2 or more and the two or more blocks indicated by the block information satisfy a predetermined condition,
the predetermined condition relates to a block with a second largest area in the medical image out of the two or more blocks indicated by the block information,
the predetermined condition is that the block with the second largest area in the medical image out of the two or more blocks indicated by the block information has an area greater than or equal to a first threshold, and
the first threshold is a value that depends on a receiver operating characteristic (ROC) curve for distinguishing between abnormality and normality of the anatomical structure, the ROC curve being obtained for various areas beforehand.
2. The abnormality detection system according to claim 1 ,
wherein the predetermined condition is that a minimum value of a distance in the medical image between a block with a largest area in the medical image and each other block out of the two or more blocks indicated by the block information is less than or equal to a second threshold.
3. The abnormality detection system according to claim 2 ,
wherein the predetermined condition further includes a condition that a block with a second largest area in the medical image out of the two or more blocks indicated by the block information has an area greater than or equal to a first threshold.
4. The abnormality detection system according to claim 2 ,
wherein the second threshold is a value that depends on a ROC curve for distinguishing between abnormality and normality of the anatomical structure, the ROC curve being obtained for various distances beforehand.
5. An abnormality detection method executed by an abnormality detection system that detects, based on a medical image, whether a prespecified anatomical structure included in the medical image is abnormal, the abnormality detection method comprising:
obtaining block information indicating one or more blocks that are each a region in which pixels representing the anatomical structure are connected in the medical image; and
determining and outputting whether the anatomical structure is abnormal, based on a total number of the one or more blocks indicated by the block information obtained in the obtaining,
wherein in the determining, the anatomical structure is determined to be not abnormal when the total number of the one or more blocks indicated by the block information is 1, and determined to be abnormal when the total number of the one or more blocks indicated by the block information is 2 or more and the two or more blocks indicated by the block information satisfy a predetermined condition,
the predetermined condition relates to a block with a second largest area in the medical image out of the two or more blocks indicated by the block information,
the predetermined condition is that the block with the second largest area in the medical image out of the two or more blocks indicated by the block information has an area greater than or equal to a first threshold, and
the first threshold is a value that depends on a receiver operating characteristic (ROC) curve for distinguishing between abnormality and normality of the anatomical structure, the ROC curve being obtained for various areas beforehand.
6. The abnormality detection method according to claim 5 , further comprising:
obtaining a ROC curve for distinguishing between abnormality and normality of the anatomical structure, and determining the predetermined condition based on the ROC curve obtained.