US 11,107,564 B2Granted

Accession number correction system

AssigneeEnlitic, Inc.

InventorsEric C. Poblenz, Kevin Lyman, Chris Croswhite

Life of this patent

Estimating the term…

Loading patent…

Abstract

An accession number correction system is operable to determine that an accession number of a received DICOM image does not link to any corresponding one of a plurality of medical reports. A query indicating medical report criteria, generated based on the first DICOM image, is transmitted to a report database, and a set of medical reports are received from the report database in response. One report of the set of medical reports that corresponds to the DICOM image is determined by performing a comparison function on the DICOM image and the one reports to generate a comparison value, and by determining the comparison value compares favorably to a comparison threshold. Updated report header data that includes the accession number of the first DICOM image is generated for the one report and is transmitted to the report database for storage.

Claims20

Dependent claims

An accession number correction system, comprising:

at least one processor;
and
a memory that stores executable instructions that, when executed by the at least one processor, cause the accession number correction system to:
train a computer vision model from a training set of DICOM images by utilizing artificial intelligence;
receive a first DICOM image from a picture archive integration system (PACS) server that stores a plurality of DICOM images;
determine that an accession number of the first DICOM image does not link to any corresponding one of a plurality of medical reports;
automatically generate medical report criteria based on the first DICOM image based on determining that the accession number of the first DICOM image does not link to any corresponding one of the plurality of medical reports;
transmit a first query indicating the medical report criteria to a report database that stores the plurality of medical reports;
receive a set of medical reports from the report database in response to the first query;
generate inference data for the first DICOM image via artificial intelligence by performing at least one inference function utilizing the computer vision model on image data of the first DICOM image;
perform a comparison function by comparing the inference data for the first DICOM image to text included in at least one of the set of medical reports to generate a comparison value for each of the at least one of the set of medical reports;
determine a selected one of the set of medical reports that corresponds to the first DICOM image by determining the comparison value corresponding to the selected one of the set of medical reports compares favorably to a comparison threshold;
generate updated report header data for the selected one of the set of medical reports, wherein the updated report header data includes the accession number of the first DICOM image;
and
transmit the updated report header data to the report database for storage in conjunction with the selected one of the set of medical reports.

12 more elements

A method for execution by an accession number correction system, comprising:

training a computer vision model from a training set of DICOM images by utilizing artificial intelligence;
receiving a first DICOM image from a picture archive integration system (PACS) server that stores a plurality of DICOM images;
determining that an accession number of the first DICOM image does not link to any corresponding one of a plurality of medical reports;
automatically generating medical report criteria based on the first DICOM image based on determining that the accession number of the first DICOM image does not link to any corresponding one of the plurality of medical reports;
transmitting a first query indicating the medical report criteria to a report database that stores the plurality of medical reports;
receiving a set of medical reports from the report database in response to the first query;
generating inference data for the first DICOM image via artificial intelligence by performing at least one inference function utilizing the computer vision model on image data of the first DICOM image;
performing a comparison function by comparing the inference data for the first DICOM image to text included in at least one of the set of medical reports to generate a comparison value for each of the at least one of the set of medical reports;
determining a selected one of the set of medical reports that corresponds to the first DICOM image by determining the comparison value corresponding to the selected one of the set of medical reports compares favorably to a comparison threshold;
generating updated report header data for the selected one of the set of medical reports, wherein the updated report header data includes the accession number of the first DICOM image;
and
transmitting the updated report header data to the report database for storage in conjunction with the selected one of the set of medical reports.

9 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/363,207Filed 25 Mar 2019 · us provisional application
Priority: 21 Nov 2018
Published: US 2020/0160969 A121 May 2020
Granted: 31 Aug 2021
Term ends: Not estimatedThe source records don’t support an estimate.

Classification99 codes

G06Q 10/06315
Resource planning, allocation, distributing or scheduling for enterprises or organisations: needs-based resource requirements planning or analysis
A61B 5/7264
Details of waveform analysis: classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems…
A61B 6/5205
Devices using data or image processing specially adapted for radiation diagnosis: involving processing of raw data to produce diagnostic data
A61B 6/563
Details of data transmission or power supply, e.g. use of slip rings: involving image data transmission via a network