# US 12,224,065 B2 · Augmenting files such as DICOM objects containing medical imaging information with additional medical information about the subject of the medical imaging information

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,224,065 B2
- Document ID: US12224065B2
- Status: Granted
- Kind: B2
- Application number: 17/940,628
- Filed: 2022-09-08
- Published: 2024-03-14
- Granted: 2025-02-11
- Earliest claimed: 2022-09-08
- Assignees: Providence St. Joseph Health
- Applicants: Providence St. Joseph Health
- Inventors: Lawrence Frederick Yapp; Janet Marie Vickers; Jennifer Grace Franks
- Web page: https://patentgrep.com/patent/US12224065B2

## CPC

- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 30/40: for processing medical images, e.g. editing
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A facility for performing an enrichment process is disclosed. The facility accesses a starting file emitted by a medical imaging device, which contains (1) medical imaging information captured from a subject, and information identifying the subject. The facility uses the information identifying the subject in the starting file to extract medical information from an electronic medical record corresponding to the subject. The facility then creates an enriched file by making a copy of the starting file and adding the extracted medical information to the copy.

## Claims

### Claim 1

One or more computer memories collectively storing an enrichment template data structure, comprising a plurality of entries, each entry corresponding to a different enrichment field for inclusion in an enriched DICOM object and comprising:
extraction directions to extract medical information for the enrichment field from an identified source location in an electronic medical record corresponding to a subject from whom medical imaging information has been captured; and
population directions to add to a copy of a starting DICOM object containing the medical imaging information captured from the subject the medical information extracted in accordance with the extraction directions in an identified target location in the DICOM object, the contents of the data structure being usable to generate from the starting DICOM object for the subject an enriched DICOM object.

### Claim 2 (depends on 1)

The one or more computer memories of claim 1 wherein a first one of the plurality of entries contains population directions directing addition of the enrichment field to which the first entry corresponds in a target location that is a standard DICOM field, and wherein a first one of the plurality of entries contains population directions directing addition of the enrichment field to which the first entry corresponds in a target location that is a custom DICOM field.

### Claim 3 (depends on 1)

The one or more computer memories of claim 1 wherein, for a first one of the plurality of entries, the extraction directions comprise a path that identifies a database column within a particular electronic medical record database.

### Claim 4

One or more computer memories collectively having contents configured to cause a computing system to perform a method, the method comprising:
receiving a plurality of enriched DICOM objects, each enriched DICOM object comprising:
medical imaging information captured from a subject using a medical imaging device, and
supplemental medical information about the subject extracted from an electronic medical record corresponding to the subject;
for each of the plurality of enriched DICOM objects, establishing a training observation in which the medical imaging information of the enriched DICOM object and at least one unit of the supplemental medical information of the enriched DICOM object are employed as independent variables, and at least one unit of the supplemental medical information of the enriched DICOM is employed as a dependent variable; and
training machine learning model with the established training observations.

### Claim 5 (depends on 4)

The one or more computer memories of claim 4, wherein, for each of the plurality of enriched DICOM objects, establishing a training observation for the enriched DICOM object comprises accessing an enrichment template specifying fields of the enriched DICOM object in which particular units of the supplemental medical information are stored.

### Claim 6

A method in a computing system, the method comprising:
receiving a plurality of enriched DICOM objects, each enriched DICOM object comprising:
medical imaging information captured from a subject using a medical imaging device, and
supplemental medical information about the subject extracted from an electronic medical record corresponding to the subject;
for each of the plurality of enriched DICOM objects, establishing a training observation in which the medical imaging information of the enriched DICOM object and at least one unit of the supplemental medical information of the enriched DICOM object are employed as independent variables, and at least one unit of the supplemental medical information of the enriched DICOM is employed as a dependent variable; and
training machine learning model with the established training observations.

### Claim 7 (depends on 6)

The method of claim 6, wherein, for each of the plurality of enriched DICOM objects, establishing a training observation for the enriched DICOM object comprises accessing an enrichment template specifying fields of the enriched DICOM object in which particular units of the supplemental medical information are stored.

### Claim 8

A computing system, comprising:
one or more processors; and
one or more memories collectively having contents executable by the one or more processors to perform a method, the method comprising:
receiving a plurality of enriched DICOM objects, each enriched DICOM object comprising:
medical imaging information captured from a subject using a medical imaging device, and
supplemental medical information about the subject extracted from an electronic medical record corresponding to the subject;
for each of the plurality of enriched DICOM objects, establishing a training observation in which the medical imaging information of the enriched DICOM object and at least one unit of the supplemental medical information of the enriched DICOM object are employed as independent variables, and at least one unit of the supplemental medical information of the enriched DICOM is employed as a dependent variable; and
training machine learning model with the established training observations.

### Claim 9 (depends on 8)

The computing system of claim 8, wherein, for each of the plurality of enriched DICOM objects, establishing a training observation for the enriched DICOM object comprises accessing an enrichment template specifying fields of the enriched DICOM object in which particular units of the supplemental medical information are stored.