A Multi-Model, Pixel-Native Framework for Automated Computed Tomography Series Labeling and Characterization: Proof-of-Concept Study - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

A Comprehensive Pixel-Based Approach for the Automated Labeling and Analysis of Computed Tomography Series: A Proof-of-Concept Investigation

  • By

  • Yutong Wen

  • Anton Sheahan Quinsten

  • Cynthia Sabrina Schmidt

  • Christian Bojahr

  • Judith Kohnke

  • Kamyar Arzideh

  • Sina Warmer

  • Sebastian Blex

  • Ann-Christin Jacoby

  • Max Eberts

  • Hanna Lehmann

  • Olivia Barbara Pollok

  • Mathias Holtkamp

  • Luca Salhöfer

  • Lale Umutlu

  • Michael Forsting

  • Johannes Haubold

  • Felix Nensa

  • Katarzyna Borys

  • René Hosch

  • September 29, 2026

Share

  • 1

    AI advancements in radiology have improved tasks like anatomical landmark segmentation and body composition assessment.

  • 2

    Current workflows for CT imaging rely on DICOM metadata, which often lacks completeness and clarity.

  • 3

    Inconsistent DICOM metadata across institutions hinders automated routing and identification of relevant image series.

  • 4

    Nonstandardized free-text fields in DICOM can lead to ambiguity, necessitating manual inspection for series identification.

  • 5

    These metadata constraints create inefficiencies, increase workflow burdens, and complicate multi-institutional model development.

Original Source(s)

A Multi-Model, Pixel-Native Framework for Automated Computed Tomography Series Labeling and Characterization: Proof-of-Concept Study

  • by Yutong Wen, Anton Sheahan Quinsten, Cynthia Sabrina Schmidt, Christian Bojahr, Judith Kohnke, Kamyar Arzideh, Sina Warmer, Sebastian Blex, Ann-Christin Jacoby, Max Eberts, Hanna Lehmann, Olivia Barbara Pollok, Mathias Holtkamp, Luca Salhöfer, Lale Umutlu, Michael Forsting, Johannes Haubold, Felix Nensa, Katarzyna Borys, René Hosch

  • September 29, 2026

Related Content

FDA guidance spurs adoption of change control plans for radiology AI devices

Investigators examined adoption and public documentation of change control plans for FDA-cleared radiology AI devices.

Oversight May Be Critical in Patient Acceptance of AI in Radiology

A UK survey found that patients supported AI as a clinical tool but wanted physicians to remain responsible for medical decisions.

FDA monthly preview: Key September decisions to watch

Several FDA decisions across multiple specialties are expected this month.