Tracking lesion diameter measurements in multiple medical scans

Abstract

A lesion tracking system is operable to detect a first lesion in a first subset of image slices of a first medical scan corresponding to a patient via artificial intelligence by utilizing a computer vision model. The first lesion is detected in a second subset of image slices of a second medical scan corresponding to the patient via artificial intelligence by utilizing the computer vision model. A lesion diameter measurement function is performed on at least one of the first subset of image slices to generate a first lesion diameter measurement, and is performed on at least one of the second subset of image slices to generate a second lesion diameter measurement. RECIST evaluation data is generated based on a computed difference between the first lesion diameter measurement and the second lesion diameter measurement. The RECIST evaluation data is transmitted for display via a display device.

What is claimed is: 
     
         1 . A lesion tracking system comprising:
 at least one processor; and   a memory that stores operational instructions that, when executed by the at least one processor, cause the lesion tracking system to:   train a computer vision model via artificial intelligence based on a training set of medical scans;   receive a first medical scan that is associated with a first patient and a first scan date;   detect a first lesion in first subset of image slices of a first plurality of image slices of the first medical scan via artificial intelligence by utilizing the computer vision model;   perform a lesion diameter measurement function on at least one of the first subset of image slices to generate a first lesion diameter measurement;   receive a second medical scan that is associated with the first patient and a second scan date, wherein the second scan date is different from the first scan date;   detect the first lesion in a second subset of image slices of a second plurality of image slices of the second medical scan via artificial intelligence by utilizing the computer vision model;   perform the lesion diameter measurement function on at least one of the second subset of image slices to generate a second lesion diameter measurement;   generate Response Evaluation Criteria in Solid Tumors (RECIST) evaluation data based on a computed difference between the first lesion diameter measurement and the second lesion diameter measurement; and   transmit the RECIST evaluation data for display via a display device.   
     
     
         2 . The lesion tracking system of  claim 1 , wherein the first scan date is more recent than the second scan date. 
     
     
         3 . The lesion tracking system of  claim 1 , wherein the operational instructions, when executed by the at least one processor, further cause the lesion tracking system to:
 determine a patient identifier corresponding to the first patient based on the first medical scan; and   retrieve the second medical scan from a medical scan database based on the patient identifier.   
     
     
         4 . The lesion tracking system of  claim 1 , wherein the operational instructions, when executed by the at least one processor, further cause the lesion tracking system to:
 determine a set of pixels in at least one of the first subset of image slices that correspond to the first lesion via artificial intelligence by utilizing the computer vision model;   determine pixel value data for the set of pixels, wherein the pixel value data includes at least one of: a density value, a density range, or coordinate data; and   identifying the first lesion in other ones of the first subset of image slices neighboring the at least one of the first subset of image slices in the first plurality of image slices based on applying the pixel value data.   
     
     
         5 . The lesion tracking system of  claim 1 , wherein detecting the first lesion in the second medical scan includes at least one of:
 searching only a subset of image slices of the second medical scan based on the first subset of image slices of the first medical scan determined to include the first lesion;   searching an anatomical region in the second medical scan determined to include the first lesion in the first medical scan; or   searching only a subset of pixels of image slices of the second medical scan based on pixels of the first subset of image slices determined to include the first lesion in the first medical scan.   
     
     
         6 . The lesion tracking system of  claim 1 , wherein the operational instructions, when executed by the at least one processor, further cause the lesion tracking system to:
 determine that the first lesion is a target lesion based on comparing the first lesion diameter measurement to at least one diameter threshold;   wherein detecting the first lesion in the second medical scan, generating the second lesion diameter measurement, and generating the RECIST evaluation data is based on determining that the first lesion is the target lesion.   
     
     
         7 . The lesion tracking system of  claim 6 , wherein determining that the first lesion is a target lesion includes generating RECIST eligibility data for the first lesion in the first medical scan, wherein the RECIST eligibility data indicates an eligibility criterion is met when the first lesion diameter measurement compares favorably to the diameter threshold, and wherein the RECIST eligibility data indicates the eligibility criterion is not met when the first lesion diameter measurement compares unfavorably to the diameter threshold; and wherein the operational instructions, when executed by the at least one processor, further cause the lesion tracking system to:
 transmit the RECIST eligibility data for the first lesion in the first medical scan for display.   
     
     
         8 . The lesion tracking system of  claim 1 , wherein the operational instructions, when executed by the at least one processor, further cause the lesion tracking system to:
 receive human measurement data associated with the first medical scan that includes a prior diameter measurement of the first lesion in the first medical scan performed by a human that previously reviewed the first medical scan;   generate measurement accuracy data by comparing the prior diameter measurement to the first lesion diameter measurement; and   transmit the measurement accuracy data for display.   
     
     
         9 . The lesion tracking system of  claim 1 , wherein the lesion diameter measurement function is performed on each of the first subset of image slices to generate a set of diameter measurements, and wherein generating the first lesion diameter measurement includes selecting a maximum of the set of diameter measurements. 
     
     
         10 . The lesion tracking system of  claim 1 , wherein the first lesion diameter measurement corresponds to a segment connecting a first point and a second point of a perimeter of the first lesion in a first slice of the first subset of image slices, and wherein the segment is oblique to an x-axis of the one of the first subset of image slices. 
     
     
         11 . The lesion tracking system of  claim 10 , wherein the second lesion diameter measurement corresponds to a second segment connecting another first point and another second point of another perimeter of the first lesion in a second slice of the second subset of image slices, and wherein the second segment is oblique to the segment based on a change of shape of the first lesion. 
     
     
         12 . The lesion tracking system of  claim 11 , wherein the first plurality of image slices and the second plurality of image slices are indexed via slice indexes, wherein the first slice has a first slice index, and wherein the second slice has a second slice index that is different from the first slice index based on the change of shape of the first lesion. 
     
     
         13 . The lesion tracking system of  claim 10  wherein generating the first lesion diameter measurement is based on:
 determine a set of pixels of the one of the first subset of image slices that correspond to the perimeter of the first lesion in the first slice via artificial intelligence by utilizing the computer vision model, wherein the set of pixels includes a first pixel corresponding to the first point and a second pixel corresponding to the second point; and 
 determine the first lesion diameter measurement utilizing the first point and the second point by determining a distance between the first pixel and the second pixel is a maximum distance between for any pair of pixels of the set of pixels. 
 
     
     
         14 . The lesion tracking system of  claim 1 , wherein the first lesion diameter measurement corresponds to a segment connecting a first point on a first one of the first subset of image slices and a second point on a second one of the first subset of image slices, and wherein the first lesion diameter measurement is based on a slice thickness of the plurality of slices. 
     
     
         15 . The lesion tracking system of  claim 14 , wherein generating the first lesion diameter measurement is based on:
 determining a set of pixels of the first subset of image slices that correspond to a three-dimensional surface of the first lesion in the first subset of image slices via artificial intelligence by utilizing the computer vision model, wherein the set of pixels includes a first pixel corresponding to the first point and a second pixel corresponding to the second point; and   determining the first lesion diameter measurement utilizing the first point and the second point based on determining a distance between the first pixel and the second pixel is a maximum distance between for any pair of pixels of the set of pixels.   
     
     
         16 . The lesion tracking system of  claim 1 , wherein the operational instructions, when executed by the at least one processor, further cause the lesion tracking system to:
 training the lesion diameter measurement function via artificial intelligence based on the training set of medical scans.   
     
     
         17 . The lesion tracking system of  claim 1 , wherein the RECIST evaluation data indicates one of: Complete Response, Partial Response, Stable Disease, or Progressive Disease. 
     
     
         18 . The lesion tracking system of  claim 1 , wherein the operational instructions, when executed by the at least one processor, further cause the lesion tracking system to:
 determine that the first lesion corresponds to a lung nodule;
 determine a Lung-RADS score for the second medical scan based on the second lesion diameter measurement, wherein the Lung-RADS score is different from a prior Lung-RADS score determined for the first medical scan; and 
 transmit the Lung-RADS score for display. 
   
     
     
         19 . A method comprising:
 training a computer vision model via artificial intelligence based on a training set of medical scans;   receiving a first medical scan that is associated with a first patient and a first scan date;   detecting a first lesion in first subset of image slices of a first plurality of image slices of the first medical scan via artificial intelligence by utilizing the computer vision model;   performing a lesion diameter measurement function on at least one of the first subset of image slices to generate a first lesion diameter measurement;   receiving a second medical scan that is associated with the first patient and a second scan date, wherein the second scan date is different from the first scan date;   detecting the first lesion in a second subset of image slices of a second plurality of image slices of the second medical scan via artificial intelligence by utilizing the computer vision model;   performing the lesion diameter measurement function on at least one of the second subset of image slices to generate a second lesion diameter measurement;   generating Response Evaluation Criteria in Solid Tumors (RECIST) evaluation data based on a computed difference between the first lesion diameter measurement and the second lesion diameter measurement; and   transmitting the RECIST evaluation data for display via a display device.   
     
     
         20 . A lesion tracking system comprising:
 at least one processor; and   a memory that stores operational instructions that, when executed by the at least one processor, cause the lesion tracking system to:   train a computer vision model via artificial intelligence based on a training set of medical scans;   receive a first medical scan that is associated with a first patient and a first scan date;   detect a first lesion in first subset of image slices of a first plurality of image slices of the first medical scan via artificial intelligence by utilizing the computer vision model;   perform a lesion diameter measurement function on at least one of the first subset of image slices to generate a first lesion diameter measurement;   receive a second medical scan that is associated with the first patient and a second scan date, wherein the second scan date is different from the first scan date;   detect the first lesion in a second subset of image slices of a second plurality of image slices of the second medical scan via artificial intelligence by utilizing the computer vision model;   perform the lesion diameter measurement function on at least one of the second subset of image slices to generate a second lesion diameter measurement;   generate Response Evaluation Criteria in Solid Tumors (RECIST) evaluation data based on a computed difference between the first lesion diameter measurement and the second lesion diameter measurement; and   transmit the RECIST evaluation data for storage via a database storage system.