Large language models for structured reporting in radiology: past, present, and future - Takeaways - MDSpire

Large language models for structured reporting in radiology: past, present, and future

  • By

  • Felix Busch

  • Lena Hoffmann

  • Daniel Pinto dos Santos

  • Marcus R. Makowski

  • Luca Saba

  • Philipp Prucker

  • Martin Hadamitzky

  • Nassir Navab

  • Jakob Nikolas Kather

  • Daniel Truhn

  • Renato Cuocolo

  • Lisa C. Adams

  • Keno K. Bressem

  • October 23, 2024

  • 0 min

Share

  • 1

    Structured reporting (SR) in radiology aims to standardize report content and improve quality, but faces challenges in flexibility and resource demands.

  • 2

    The American College of Radiology and Radiological Society of North America have made significant efforts to standardize radiology communication and reporting.

  • 3

    Large language models (LLMs) are emerging as potential solutions to integrate structured reporting into radiologists' workflows effectively.

  • 4

    Natural language processing (NLP) has evolved from basic models to advanced transformer-based models, enhancing their applicability in radiology.

  • 5

    The adoption of structured reporting in clinical practice is hindered by manual efforts and time-consuming template interactions, despite technological advancements.

Original Source(s)

Large language models for structured reporting in radiology: past, present, and future

  • by Felix Busch, Lena Hoffmann, Daniel Pinto dos Santos, Marcus R. Makowski, Luca Saba, Philipp Prucker, Martin Hadamitzky, Nassir Navab, Jakob Nikolas Kather, Daniel Truhn, Renato Cuocolo, Lisa C. Adams, Keno K. Bressem

  • October 23, 2024

Related Content

Tenecteplase Fails to Boost EVT Outcomes

Phase 3 stroke trial leaves open the possibility of clinically meaningful benefit or harm in selected late-window patients.

Elastography Enhances Diagnostic Accuracy of ACR TI-RADS in Thyroid Nodule Evaluation

CT and MRI radiomics in cardiovascular risk prediction: a systematic review and meta-analysis by the EuSoMII Radiomics Auditing Group