AI for Improved Patient Care: Game or Game-Changer?
Sunrise Course
ORGANIZERS: Nandita DeSouza, Takeshi Yokoo
Monday, 06 May 2024
Nicoll 3
07:00 -
08:00
Moderators: Martin Graves & Steven Shea
Skill Level: Intermediate to Advanced
Session Number: S-M-04
CME Credit
Session Number: S-M-04
Overview
Areas in body imaging where the role of artificial intelligence as an assistive technology will be discussed.
Target Audience
Clinicians with an interest in implementing AI techniques for body imaging. Scientists seeking to develop and test AI tools in the clinic.
Educational Objectives
As a result of attending this course, participants should be able to:
- Identify how AI may be used to enhance and standardize image acquisition and segmenta;
- Describe how AI may be used for image processing, reconstruction, and quantitation; and
- Define the role of language models in radiology reporting and their current clinical utility.
| 07:00 | | AI for Image Reconstruction Marcel Nickel Keywords: Image acquisition: Reconstruction, Image acquisition: Machine learning With their capability to push MRI towards higher resolution, higher signal-to-noise and/or shorter acquisition time, AI-based reconstruction and image enhancement techniques have quickly transitioned into clinical routine. This educational talk will illustrate how conventional MR reconstructions can be combined with trainable components and outline how these architectures can be trained for prospective use in clinical applications. Based on examples the benefits, limitations and on-going developments will be discussed. |
| 07:20 | | Language Models: Help or Hindrance? Ito Rintaro Keywords: Transferable skills: Software engineering Large Language Models (LLMs) are increasingly utilized in diagnostic imaging, offering capabilities in processing text and images, and handling composite modalities. They assist in creating accurate diagnostic reports, interpreting images, and integrating clinical information. However, challenges include ensuring output reliability, addressing biases, and tackling ethical and privacy concerns. Future improvements involve continuous training, ethical standards, interdisciplinary collaboration, and regulatory validation. These steps aim to enhance LLMs' efficiency and accuracy in diagnostic imaging while addressing concerns about reproducibility, prompt handling, and ethical considerations. |
| 07:40 | | Detection and Segmentation in Medical Images Indrani Bhattacharya |