Present (in BOLD):

• NASA/JPL: Dan Crichton, Sean Kelly, Heather Kincaid, Ashish Mahabal
• Arizona State University: Ji Qiu
• Boston University: Jennifer Beane
• EVMS: Julius Nyalwidhe
• DMCC: Jackie Dahlgren, Chad He, Royce Malnik, Stephanie Page-Lester
• Johns Hopkins: Zhen Zhang
• Moffitt: Matt Schabath, John Heine, Yoga Balagurunathan, Radka Stoyanova
• NCI: Sidney Fu, Guillermo Marquez, Christos Patriotis, Juan Miguel Villanueva
• PNNL: Tao Liu
• University of California: William Hsu
• University of North Carolina: Kristen Anton
• University of Washington: Savannah Partridge

Current Action Items:

1. ONGOING: PIs are asked to review their data in LabCAS and let JPL know of any issues.
2. Discuss roadmap for additional hackathons and workshops.

Agenda/Discussion:

Update on DICOM Headers Subcommittee: Showed slide on EDRN DICOM Header Tag Standards Working Group Update: The goal is to define a set of minimal required DICOM header fields that make cancer biomarker imaging data reusable and AI-ready, while minimizing burden on participating sites. This will support future standardization and help guide SOP development for EDRN studies. Make sure data is anonymized, encoded. Link below is the document that describes what needs to happen with all the header tags.  Will meet with working group one more time to get this done before the September EDRN Steering Committee Meeting. Link to DICOM Header Tags: https://docs.google.com/spreadsheets/d/1Q56vKzK0nB4UAkfLJnBOy6C-7wtHccvZkWYGQHTMpBw/edit?gid=796697265#gid=796697265

Link to deidentification process: https://docs.google.com/document/d/17-NupQmnCPbsK030qGdLM_VJ3OS5GWZ-pXaB5U_y4Zw/edit?tab=t.0#heading=h.x0xliewwlt6w

• The EDRN Projects that are driving this are LTP2 and P-MRI.
• The de-identification process was also discussed:
• Remove direct identifiers (patient/staff names, IDs, MRNs, contact info)
• Remove or replace site/device identifiers; keep technical scan parameters
• Keep useful descriptions only after PHI cleaning (e.g., protocol/series/study descriptions)
• Check structured content and pixel data for embedded PHI
• Record what was done (audit fields) for traceability
• Offset dates consistently to preserve timelines
• Replace all UIDs (unique identifiers) so links still work without exposing originals l

Goal is to minimize burden at sites and still receive FAIR/AI Ready Data.   JPL will use script to update headers after images that are transferred to JPL. Recommendations for this:

• Use script to update headers after images re transferred to JPL (e.g., BlindedPatientID, VisitCode, EventID) to reduce site workload and avoid errors
• JPL exploring ways to help sites with:
• Apply consistent date offsetting across sites within a study (e.g., Prostate MRI)
• Replacing all UIDs so links remain intact without exposing originals
• Discussing/investigating TRIAD or other software for site-based anonymization
• JPL created a proposed workflow for sites and JPL when images are uploaded to LabCAS:
• JPL will verify images using core list of metadata tags. If images not deidentified, they will be sent back to site with specific list of things for them to review and deidentify.
• JPL investigating ways to either offset dates are re-encode the UI DS to make sure these are done consistently.
• Once images are published inLabCAS, sites will be asked to verify the images.

Heather Kincaid showed a list of proposed DICOM Header Updates with metadata from DMCC.  Working with Radka Stoyanova at Moffitt and Ashish Mahabal at JPL to make sure images are reusable.

2025 Dr. Robert Gillies Machine Learning Workshop in Cancer:  Matt Schabath mentioned this upcoming workshop at Moffitt, which will be held on October 30th and 31st  More information can be found here: https://fundraise.moffitt.org/campaign/626851/donate

Next Call: Monday, October 20, 2025 at 1pm Eastern/10 am Pacific