Settings
  • Light
  • Dark
  • Auto
Select Page

The authors of this study used a deep learning-based approach, MOdality Mapping and Orchestration (MOMO), to deal with potential issues that are caused when patients switch hospitals throughout the course of their treatment. These changes result in the staff at the new hospital, consisting of dedicated medical-technical personnel, being tasked with the processing and archiving of external DICOM studies. This fully-automated approach may have several implications for the future, as the authors found that neural networks “offered a boost in predictive power and the best performance in the task that was archived with a variant of MOMO utilizing neural networks”.

Key points

  • The algorithm can successfully identify 76 medical study types across seven modalities (CT, X-ray angiography, radiographs, MRI, PET (+CT/MRI), ultrasound, and mammograms).
  • The algorithm outperforms a commercial product performing the same task by a significant margin (> 9% accuracy gain).
  • The performance of the algorithm increases through the application of Deep Learning techniques.

Article: Deep Learning–driven classification of external DICOM studies for PACS archiving

Authors: Frederic Jonske, Maximilian Dederichs, Moon-Sung Kim, Julius Keyl, Jan Egger, Lale Umutlu, Michael Forsting, Felix Nensa & Jens Kleesiek

Latest posts

Welcome to the blog on Artificial Intelligence of the European Society of Radiology

This blog aims at bringing educational and critical perspectives on AI to readers. It should help imaging professionals to learn and keep up to date with the technologies being developed in this rapidly evolving field.