Lung screening assessment system
First Claim
Patent Images
1. A lung screening assessment system, comprising:
- a processing system that includes a processor; and
a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations comprising;
receiving a first chest computed tomography (CT) scan that includes a plurality of cross sectional images;
generating nodule classification data of the first chest CT scan by utilizing a computer vision model to identify a first nodule in the plurality of cross sectional images and determine an assessment score, wherein the computer vision model is trained on a plurality of training chest CT scans;
generating a first subset of chest CT scans from the plurality of training chest CT scans by applying a similarity function to determine that a set of nodules included in the first subset of chest CT scans compare favorably to the first nodule;
retrieving a set of patient records corresponding to the first subset of chest CT scans wherein each of the set of patient records includes a plurality of record entries and a corresponding plurality of dates;
identifying a subset of the plurality of dates in the each of the set of patient records that are more recent than a date associated with the one of the plurality of chest CT scans corresponding to the each of the set of patient records;
identifying a subset of the plurality of record entries of the each of the set of patient records that correspond to the subset of the plurality of dates;
generating longitudinal data corresponding to each of the set of patient records based on each corresponding subset of the plurality of record entries;
generating a lung screening report for display on a display device associated with a user of the lung screening assessment system, wherein the lung screening report includes the assessment score of the nodule classification data, data from at least one patient record in the set of patient records and the longitudinal data; and
selecting at least one cross sectional image from each chest CT scan of the first subset of chest CT scans for display on the display device in conjunction with the lung screening report.
1 Assignment
0 Petitions
Accused Products
Abstract
A lung screening assessment system is operable to receive a chest computed tomography (CT) scan that includes a plurality of cross sectional images. Nodule classification data of the chest CT scan is generated by utilizing a computer vision model that is trained on a plurality of training chest CT scans to identify a nodule in the plurality of cross sectional images and determine an assessment score. A lung screening report that includes the assessment score of the nodule classification data is generated for display on a display device associated with a user of the lung screening assessment system.
-
Citations
14 Claims
-
1. A lung screening assessment system, comprising:
-
a processing system that includes a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations comprising; receiving a first chest computed tomography (CT) scan that includes a plurality of cross sectional images; generating nodule classification data of the first chest CT scan by utilizing a computer vision model to identify a first nodule in the plurality of cross sectional images and determine an assessment score, wherein the computer vision model is trained on a plurality of training chest CT scans; generating a first subset of chest CT scans from the plurality of training chest CT scans by applying a similarity function to determine that a set of nodules included in the first subset of chest CT scans compare favorably to the first nodule; retrieving a set of patient records corresponding to the first subset of chest CT scans wherein each of the set of patient records includes a plurality of record entries and a corresponding plurality of dates; identifying a subset of the plurality of dates in the each of the set of patient records that are more recent than a date associated with the one of the plurality of chest CT scans corresponding to the each of the set of patient records; identifying a subset of the plurality of record entries of the each of the set of patient records that correspond to the subset of the plurality of dates; generating longitudinal data corresponding to each of the set of patient records based on each corresponding subset of the plurality of record entries; generating a lung screening report for display on a display device associated with a user of the lung screening assessment system, wherein the lung screening report includes the assessment score of the nodule classification data, data from at least one patient record in the set of patient records and the longitudinal data; and selecting at least one cross sectional image from each chest CT scan of the first subset of chest CT scans for display on the display device in conjunction with the lung screening report. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A method for execution by a lung screening assessment system that includes a processor, the method comprising:
-
receiving a first chest computed tomography (CT) scan that includes a plurality of cross sectional images; generating nodule classification data of the first chest CT scan by utilizing a computer vision model to identify a first nodule in the plurality of cross sectional images and determine an assessment score, wherein the computer vision model is trained on a plurality of training chest CT scans; generating a first subset of chest CT scans from the plurality of training chest CT scans by applying a similarity function to determine that a set of nodules included in the first subset of chest CT scans compare favorably to the first nodule; retrieving a set of patient records corresponding to the first subset of chest CT scans wherein each of the set of patient records includes a plurality of record entries and a corresponding plurality of dates; identifying a subset of the plurality of dates in the each of the set of patient records that are more recent than a date associated with the one of the plurality of chest CT scans corresponding to the each of the set of patient records; identifying a subset of the plurality of record entries of the each of the set of patient records that correspond to the subset of the plurality of dates; generating longitudinal data corresponding to each of the set of patient records based on each corresponding subset of the plurality of record entries; generating a lung screening report for display on a display device associated with a user of the lung screening assessment system, wherein the lung screening report includes the assessment score of the nodule classification data, data from at least one patient record in the set of patient records and the longitudinal data; and selecting at least one cross sectional image from each chest CT scan of the first subset of chest CT scans for display on the display device in conjunction with the lung screening report. - View Dependent Claims (10, 11, 12, 13)
-
-
14. An article of manufacture that includes a tangible storage medium that stores operational instructions, that when executed by a processor, causes the processor to:
-
receive a first chest computed tomography (CT) scan that includes a plurality of cross sectional images; generate nodule classification data of the first chest CT scan by utilizing a computer vision model to identify a first nodule in the plurality of cross sectional images and determine an assessment score, wherein the computer vision model is trained on a plurality of training chest CT scans; generate a first subset of chest CT scans from the plurality of training chest CT scans by applying a similarity function to determine that a set of nodules included in the first subset of chest CT scans compare favorably to the first nodule; retrieve a set of patient records corresponding to the first subset of chest CT scans wherein each of the set of patient records includes a plurality of record entries and a corresponding plurality of dates; identify a subset of the plurality of dates in the each of the set of patient records that are more recent than a date associated with the one of the plurality of chest CT scans corresponding to the each of the set of patient records; identify a subset of the plurality of record entries of the each of the set of patient records that correspond to the subset of the plurality of dates; generate longitudinal data corresponding to each of the set of patient records based on each corresponding subset of the plurality of record entries; generate a lung screening report for display on a display device, wherein the lung screening report includes the assessment score of the nodule classification data, data from at least one patient record in the set of patient records and the longitudinal data; and select at least one cross sectional image from each chest CT scan of the first subset of chest CT scans for display on the display device in conjunction with the lung screening report.
-
Specification