Multi-modal dataset creation for federated learning with DICOM-structured reports - Takeaways - MDSpire

Multi-modal dataset creation for federated learning with DICOM-structured reports

  • By

  • Malte Tölle

  • Lukas Burger

  • Halvar Kelm

  • Florian André

  • Peter Bannas

  • Gerhard Diller

  • Norbert Frey

  • Philipp Garthe

  • Stefan Groß

  • Anja Hennemuth

  • Lars Kaderali

  • Nina Krüger

  • Andreas Leha

  • Simon Martin

  • Alexander Meyer

  • Eike Nagel

  • Stefan Orwat

  • Clemens Scherer

  • Moritz Seiffert

  • Jan Moritz Seliger

  • Stefan Simm

  • Tim Friede

  • Tim Seidler

  • Sandy Engelhardt

  • February 3, 2025

  • 0 min

Share

  • 1

    Large-scale multi-modal datasets are essential for effective training of deep learning models in medicine, but are scarce due to privacy regulations.

  • 2

    Federated learning allows model training without centralized data storage, but requires data harmonization across institutions for effective results.

  • 3

    The study introduces a method leveraging DICOM standards to harmonize imaging, waveform, and metadata for improved federated cohort selection.

  • 4

    An intuitive dashboard is developed for filtering DICOM data, enabling users to create cohorts from images, waveforms, and structured reports.

  • 5

    Publicly available scripts facilitate the conversion of data into DICOM format, ensuring interoperability and enabling SQL queries across systems.

Original Source(s)

Multi-modal dataset creation for federated learning with DICOM-structured reports

  • by Malte Tölle, Lukas Burger, Halvar Kelm, Florian André, Peter Bannas, Gerhard Diller, Norbert Frey, Philipp Garthe, Stefan Groß, Anja Hennemuth, Lars Kaderali, Nina Krüger, Andreas Leha, Simon Martin, Alexander Meyer, Eike Nagel, Stefan Orwat, Clemens Scherer, Moritz Seiffert, Jan Moritz Seliger, Stefan Simm, Tim Friede, Tim Seidler, Sandy Engelhardt

  • February 3, 2025

Related Content

AI Supports Glaucoma Surgical Planning

Predictive models identify high-risk patients and support earlier treatment decisions.

AI in Clinical Decision Support Systems: Promising Applications and Strategies for Managing Data Challenges

A mobile robotic approach to autonomous surface scanning in legal medicine