Method and system for measuring size change of target lesion in x-ray image
AssigneeLunit Inc.
InventorsMinchul Kim, Gunhee Nam, Thijs Kooi
Life of this patent
Estimating the term…
Abstract
A method for measuring a size change of a target lesion in an X-ray image is provided, including receiving a first X-ray image including the target lesion and a second X-ray image including the target lesion, calculating an occupancy of a region corresponding to the target lesion in criterion regions in each of the first X-ray image and the second X-ray image, and measuring a size change of the target lesion based on the calculated occupancies.
Claims14
A method performed by one or more computing devices to measure a size change of a target lesion in an X-ray image, the method comprising:
- receiving a first X-ray image including the target lesion and a second X-ray image including the target lesion;
- inputting the first X-ray image to a criterion region extraction model to obtain the first criterion region from the first X-ray image and inputting the second X-ray image to the criterion region extraction model to obtain the second criterion region from the second X-ray image, wherein the criterion region extraction model is trained, using a plurality of reference X-ray images and label information for reference criterion regions, to output a criterion region based on an input X-ray image;
- identifying the target lesion in the first criterion region and in the second criterion region by using a target lesion detection model to calculate target lesion prediction scores for each of a plurality of pixels in the first criterion region and the second criterion region, wherein a target lesion prediction score comprises a probability value between 0 and 1, inclusive;
- calculating an occupancy of a region corresponding to the target lesion with respect to a criterion region in each of the first X-ray image and the second X-ray image, the calculating comprising:
- calculating a first occupancy by dividing a sum of the target lesion prediction scores of the pixels in the first criterion region by a size of the first criterion region or by a prediction score of the first criterion region;
- and
- calculating a second occupancy by dividing a sum of the target lesion prediction scores of the pixels in the second criterion region by a size of the second criterion region or by a prediction score of the second criterion region;
- and
- obtaining a measurement result by measuring the size change of the target lesion based on a difference between the first occupancy and the second occupancy.
An information processing system comprising:
- a memory storing one or more instructions;
- and
- a processor configured to execute the stored one or more instructions to:
- receive a first X-ray image including the target lesion and a second X-ray image including the target lesion;
- input the first X-ray image to a criterion region extraction model to obtain the first criterion region from the first X-ray image and input the second X-ray image to the criterion region extraction model to obtain the second criterion region from the second X-ray image, wherein the criterion region extraction model is trained, using a plurality of reference X-ray images and label information for reference criterion regions, to output a criterion region based on an input X-ray image;
- identify the target lesion in the first criterion region and in the second criterion region by using a target lesion detection model to calculate target lesion prediction scores for each of a plurality of pixels in the first criterion region and the second criterion region, wherein a target lesion prediction score comprises a probability value between 0 and 1, inclusive;
- calculate an occupancy of a region corresponding to the target lesion with respect to a criterion region in each of the first X-ray image and the second X-ray image by:
- calculating a first occupancy by dividing a sum of the target lesion prediction scores of the pixels in the first criterion region by a size of the first criterion region or by a prediction score of the first criterion region;
- and
- calculating a second occupancy by dividing a sum of the target lesion prediction scores of the pixels in the second criterion region by a size of the second criterion region or by a prediction score of the second criterion region;
- obtain a measurement result by measuring the size change of the target lesion based on a difference between the first occupancy and the second occupancy.
Dependencies are inferred from the claim text.