AI And DICOM
Artificial Intelligence (AI) in medical imaging is important from an interoperability standpoint. Just as modalities are producing DICOM instances, pre-processing and post-processing systems are creating secondary objects, and humans are supplementing DICOM studies with their own objects, there is a role to play for machine learning and deep learning systems to interact within the medical imaging ecosystem. As with any other DICOM producer, however, it is important to meet a set of criteria to be good stewards within the ecosystem. Some important points to consider include:[*]On any DICOM producer website, including AI algorithm providers, there should be a published DICOM conformance statement outlining the types of objects it creates and how it interacts with them within the ecosystem
[*]Consider important papers and presentations highlighting the following topics:
[*]Ethics of Artificial Intelligence in Radiology: Summary of the Joint European and North American Multisociety Statement (J. Raymond Geis , Adrian P. Brady, Carol C. Wu, Jack Spencer, Erik Ranschaert, Jacob L. Jaremko, Steve G. Langer, Andrea Borondy Kitts, Judy Birch, William F. Shields, Robert van den Hoven van Genderen, Elmar Kotter, Judy Wawira Gichoya, Tessa S. Cook, Matthew B. Morgan, An Tang, Nabile M. Safdar, Marc Kohli)
[*]Artificial Intelligence: Practical? Productive? Profitable? Percipient? Pansophical? Prescient? Perilous? (Lawrence Sim)
[*]Standardizing AI Annotations the DICOM Way (David Clunie)
[*]Ensure that objects bring created are conforming to specification, such as using the right SOP classes and appropriate metadata values. Examples include:
[*]Secondary capture series, when derived from other series, may need to have the SOP Class Secondary Capture Image Storage (1.2.840.10008.5.1.4.1.1.7) used, rather than the original SOP class
[*]AI-generated objects likely should have the DICOM tag Image Type (0008,0008) with values for derived images of a secondary nature
[*]Be sure to assign new unique identifiers to instances you create and be aware that it is generally not permitted to edit/overwrite DICOM instances through resubmitting altered objects with existing UIDs
[*]You should consider contributing to DICOM WG-23 on Artificial Intelligence / Application Hosting, whose role is to identify or develop the DICOM mechanisms to support AI workflows, concentrating on the clinical context
https://www.dicomstandard.org/ai http://dicom.nema.org/medical/dicom/current/output/html/part05.html#sect_8.2 10. Transfer Syntax
10.1. DICOM Default Transfer Syntax
10.2. Transfer Syntax for a DICOM Default of Lossless JPEG Compression
10.3. Transfer Syntaxes for a DICOM Default of Lossy JPEG Compression
10.4. Transfer Syntax For DICOM RLE Image Compression
10.5. Transfer Syntax For A DICOM Default of Lossless and Lossy (Near-lossless) JPEG-LS Compression
10.6. Transfer Syntax For JPEG 2000 Compression
10.7. Transfer Syntax For MPEG2 Main Profile / Main Level Video Compression
10.8. Transfer Syntax For JPIP Referenced Pixel Data
10.9. Transfer Syntax For MPEG2 Main Profile / High Level Video Compression
10.10. Transfer Syntax For MPEG-4 AVC/H.264 High Profile / Level 4.1 Video Compression
10.11. Transfer Syntaxes for MPEG-4 AVC/H.264 High Profile / Level 4.2 Video Compression
10.12. Transfer Syntax For MPEG-4 AVC/H.264 Stereo High Profile / Level 4.2 Video Compression
10.13. Transfer Syntax for HEVC/H.265 Main Profile / Level 5.1 Video Compression
10.14. Transfer Syntax for HEVC/H.265 Main 10 Profile / Level 5.1 Video Compression
10.15. Transfer Syntax for SMPTE ST 2110-20 Uncompressed Progressive Active Video
10.16. Transfer Syntax for SMPTE ST 2110-20 Uncompressed Interlaced Active Video
页:
[1]