Edit this page

NA-MIC Project Weeks

Back to Projects List

WSI-DICOM Improvement - From Viewer to Analysis

Key Investigators

Presenter location: In-person

Project Description

Despite various existing solutions for the conversion of WSI data into DICOM, there is a distinct lack of conversion tools (vendor agnostic) that result in DICOM files. Current solutions fall short in generating DICOM files compatible with OpenSlide (4.0.0) and OHIF/SLIM-Viewer, including a PACS, impeding seamless integration and compromising overall performance.

Our objective is to 1. assess available conversion tools, 2. examine their seamless integration capabilities, and 3. enhance or develop our own solutions for WSI-DICOM conversion that integrates into PACS systems connected to web-based viewers (OHIF/SLIM), but also works locally with open-source Viewers such like QuPath (newest version 0.5.0). As automatic slide analysis with AI algorithms (mostly Python) is a cornerstone of computational pathology, OpenSlide integration is another necessary requirement.


This project aims to test existing software solutions for vendor-agnostic WSI to DICOM conversion in digital pathology and deliver/develop an open-source, community-maintained software solution. The tool must adhere to established software design patterns, ensuring ease of contribution from the community.

Approach and Plan

  1. Provide a testing suite for testing resulting DICOM files, consisting of PACS/Viewer/Analysis-Components
  2. Test existing WSI DICOM solutions and find shortcomings
  3. Develop/Improve WSI DICOM conversions
  4. Deliver key insights into shortcomings to push conversion forward

Progress and Next Steps

  1. Test Bench has been published under: WSI-DICOM-TESTBench

    Tools and Notebooks are going to be updated soon

  2. Compared Tools:

    OrthancWSIDicomizer bfconvert dicom_wsi GCP WSI to DICOM pixelmed IMI Big Picture
    Working, but excessive metadata generation. Multiple edge cases with established tools (inconsistent compatibility) Slow for large WSI, precompressed option results in color splits (shifted color due to RGB - YBR issue) Too slow Not checked yet Still working for svs and tiff, stable backup solution Decent solution, but ICC color profile is not transfered to the respective DICOM tags. Should not be that hard to fix.
  3. Viewer

    Link: Find the code here: Slim-Orthanc

    Tools Tested: Several viewers were tested, including the Slim-Viewer (both native and with OHIF integration), OpenLayers, and integration with Orthanc as a PACS system (refer to Image 1).

    Performance Issues: During testing, performance issues were observed at high zoom levels, with delays attributed to extended wait times for server responses. The problem was identified in the WebDICOM adapter (refer to Image 2).

    Comparison with Another PACS System: In comparison with another PACS system (DCM4CHE), no such performance issues were encountered.

    DICOM Web Plugin and Delays: The DICOM Web plugin appears to introduce delays, possibly due to implementation issues, specifically with pathological microscopy images. This aspect will be further evaluated in the next project phase.

    Next Steps: The healthcare-dicom-dicomweb-adapter will be evaluated as an alternative to the native DICOM-web plugin for Orthanc in the upcoming phase of the project.




Background and References

Overview of Tools for WSI-DICOM Conversion:

thanks to @dclunie and @fedorov

  1. bfconvert (BioFormats): Converting a file to different format — Bio-Formats 7.1.0 documentation. Link: https://bioformats.readthedocs.io/en/v7.1.0/users/comlinetools/conversion.html
  2. dicom_wsi Gu Q, Prodduturi N, Jiang J, Flotte TJ, Hart SN. Dicom_wsi: A Python Implementation for Converting Whole-Slide Images to Digital Imaging and Communications in Medicine Compliant Files. J Pathol Inform. 2021;12(1):21. doi:10.4103/jpi.jpi_88_20 Link: https://github.com/Steven-N-Hart/dicom_wsi
  3. GoogleCloudPlatform. WSI to DICOM Converter. Google Cloud Platform; 2022. Link: https://github.com/GoogleCloudPlatform/wsi-to-dicom-converter
  4. wsidicomizer. Sectra AB Sectra AB. wsidicomizer. imi-bigpicture; 2021. Link: https://github.com/imi-bigpicture/wsidicomizer
  5. Jodogne S, Lenaerts É, Marquet L, Erpicum C, Greimers R, Gillet P, et al. Open Implementation of DICOM for Whole-Slide Microscopic Imaging: In: Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Porto, Portugal: SCITEPRESS - Science and Technology Publications; 2017. p. 81–7. Available from: https://orbi.uliege.be/handle/2268/204498 doi:10.5220/0006155100810087
  6. Clunie D. com.pixelmed.convert.TIFFToDicom. Link: http://www.dclunie.com/pixelmed/software/javadoc/com/pixelmed/convert/TIFFToDicom.html
  7. Pocock J. wsic. 2023. Link: https://github.com/John-P/wsic
  8. Orthanc WSI “Dicomizer” Link: https://www.orthanc-server.com/static.php?page=wsi Documentation: https://orthanc.uclouvain.be/book/plugins/wsi.html

Background Information

DICOM-WSI: https://dicom.nema.org/dicom/dicomwsi/

Test Data

OpenSlide: https://openslide.org/ Test data can be downloaded there for some vendors.

Imaging Data Commons has >23TB of DICOM WSI (converted from original SVS): https://portal.imaging.datacommons.cancer.gov/explore/filters/?Modality_op=OR&Modality=SM

NEMA ftp server including WG 26 Connectathon ECDP 2023 data from vendors (some have issues; older data is more variable in quality): ftp://medical.nema.org/MEDICAL/Dicom/DataSets/WG26/

Other Resources

Test-Suite: TBD

Link to Lean Study Host: https://github.com/TIO-IKIM/LeanStudyHost

Validation tool (checks compliance with standard): https://www.dclunie.com/dicom3tools/dciodvfy.html