- Use Image Acquisition Technology Specific Service/Object Pairs (SOP) Classes.
- For this interoperability need, reference DICOM Parts 3, 5, and 6: Image Object Definitions, Data Structures and Encoding, Data Dictionary. The DICOM Standard - Parts 3, 5 and 6 define the required meta information, and standard encoding for storing and exchanging most types of medical “Image Objects”.
- The adoption level reflects DICOM’s usage when exchanging data between an imaging modality and PACS. An adoption level of three would better reflect the standard’s usage when exchanging medical images between organizations.
- DICOM Image Object Definitions are “self-describing objects” that include the meta information and image information in one object.
- DICOM also specifies standard “meta objects” that can be used to reference specific images and describe other information that can be applied to those images (e.g., annotations, overlays, window/level settings, measurements, key objects, etc.)
- The DICOM standard includes the specification for encapsulating standard JPEG photos and MPEG videos with DICOM-defined meta information – so the photo/video becomes a DICOM object. The original JPEG image or MPEG video is preserved inside a DICOM shell. DICOM protocols can then be used to exchange these DICOM-wrapped photos/videos – the same as any other DICOM object.
- Currently machine learning output in radiology is not stored in a standard format - often it is encapsulated as a 'secondary capture' image or in a proprietary format. This means that ML output is not in a format that could be reused and that it is not portable. Algorithm output below the level of an image specified using the FHIR ImagingStudy object should use either a DICOM SR using Template TID 1500 (for graphical annotations) or DICOM Segmentation objects for segmentations.
|
- Image encryption - Encryption of “whole object” or “specific attributes of the image."
- Digital signatures - To ensure the object has not been altered.
|
Submitted by SeanDoyle on 2020-09-29
DICOM meta-objects need to be more tightly defined
Currently machine learning output in radiology is not stored in a standard format - often it is encapsulated as a 'secondary capture' image or in a proprietary format. This means that ML output is not in a format that could be reused and that it is not portable. Instead - this section should specify that algorithm output below the level of an image specified using the FHIR ImagingStudy object should use either a DICOM SR using Template TID 1500 (for graphical annotations) or DICOM Segmentation objects for segmentations.