ISSN# 1545-4428 | Published date: 19 May, 2023
You must be logged in to view entire program, abstracts, and syllabi
At-A-Glance Session Detail
   
Artificial Intelligence in Musculoskeletal MRI
Weekend Course
ORGANIZERS: Iman Khodarahmi, Fang Liu
Saturday, 03 June 2023
715A/B
08:00 -  12:00
Moderators: Akshay Chaudhari & Weitian Chen
Skill Level: Basic to Advanced
Session Number: WE-03
CME Credit

Session Number: WE-03

Overview
This course offers a comprehensive overview of past, present, and future artificial intelligence (AI) techniques for musculoskeletal (MSK) imaging, including an introduction of fundamental AI principles in image acquisition, reconstruction, post-processing and analysis, reviews of current AI utility and impact in clinical MSK MRI, and outlook of challenges and future directions of AI in MSK translational and clinical applications.

Target Audience
Radiologists, clinicians, technologists, and scientists interested in learning about past, present, and future AI musculoskeletal imaging techniques.

Educational Objectives
As a result of attending this course, participants should be able to:
- Explain the basic principles of fast image acquisition, reconstruction, post-processing, and analysis using AI-based methods;
- Describe the current state-of-the-art AI methods applied to MSK imaging and their utility and impact in various clinical applications; and
- Identify emerging technical and clinical challenges, possible solutions, and future promises of AI in MSK clinical practices.

08:00 Basic Principles of Fast MRI with AI-Based Acquisition & Reconstruction
Chen Qin

Keywords: Image acquisition: Machine learning, Image acquisition: Reconstruction, Musculoskeletal: Knee

Artificial intelligence (AI) has been advancing rapidly and has shown great potential in accelerating MR imaging. This talk will aim to explain the basic principles of fast MRI with AI-based acquisition and reconstruction for broad audience. We will review the basic deep learning (DL) components that have been widely used in the field and provide an overview of the recent advances on DL-based MRI reconstruction from accelerated acquisitions. Based on that, we will introduce state-of-the-art DL reconstruction approaches with a particular focus on musculoskeletal imaging. We will also discuss about the current limitations, challenges and opportunities for AI-based fast MRI.
08:30 Basic Principles of AI-Based MR Image Analysis & Processing
Valentina Pedoia
09:00 AI in Fast MSK MRI: Clinical Applications & Evaluation
Joshua Trzasko

Keywords: Image acquisition: Reconstruction, Image acquisition: Machine learning

This talk will briefly review the technical mechanics of artificial intelligence (AI) and discuss – focusing on musculoskeletal (MSK) imaging – both how AI technically enables faster MRI exams, including how these tools can be integrated into routine clinical practice.  This will include coverage of incorporation of AI tools into the end-to-end Radiology digital framework, review of commercial AI reconstruction offerings, and discussion about practical considerations for incorporation tools into routine clinical practice.   
09:30 AI in MSK Diagnosis, Grading, Quantification & Prediction
Cem Deniz

Keywords: Musculoskeletal: Joints, Musculoskeletal: Knee, Musculoskeletal: Skeletal

The use of artificial intelligence (AI) has revolutionized areas of image recognition, speech recognition, and natural language processing. AI is transforming the world of medicine by helping doctors to improve detection, diagnosis, treatment, and management of a disease. In this lecture, we will focus on the AI approaches that are practical and currently used in diagnosis, grading, quantification and prediction of MSK disorders. The audience will learn various AI methods emerging in MR imaging for MSK disorders. At the end, the audience will be able to differentiate various AI approaches and choose the most appropriate ones for specific research problems.
10:00 Break & Meet the Teachers
10:15 AI in Quantitative MSK MRI Applications
Mingrui Yang

Keywords: Musculoskeletal: Joints

This talk will provide an overview of the recent development of artificial intelligence (AI), and its application in quantitative musculoskeletal (MSK) MRI, including T1rho and T2 relaxometry quantification. The speaker will discuss the current state of research, as well as the challenges and opportunities in the field. Attendees will gain an understanding of the benefits of AI-based quantitative MSK MRI applications, such as improved accuracy and efficiency in the diagnosis and prognosis of MSK diseases. Overall, this talk aims to provide valuable insights into the use of AI in quantitative MSK MRI applications and its potential impact on the field.
10:45 Impact of AI on MSK MRI Service Delivery
Jad Husseini

Keywords: Image acquisition: Machine learning, Musculoskeletal: Joints

Early AI-based MR image reconstruction techniques have been applied to spin-echo based 2D MR sequences. Musculoskeletal MR examinations, largely comprised of these types of pulse sequences, have benefited greatly from these advances with significant decreases in image acquisition time. In order to capitalize on this to increase patient throughput and patient access, non AI-based strategies such as MR suite layout improvement and scheduling optimization could be employed. AI applications predicting the likelihood that a patient will miss an appointment can allow for targeted notification of patients prior to appointments or overbooking to ensure maximal utilization of available slots.

11:15 Challenges & Future Directions of AI methods in musculoskeletal MRI
Florian Knoll

Keywords: Musculoskeletal: Joints, Image acquisition: Machine learning, Image acquisition: Artefacts

This talk will highlight potential issues during the translation of Artificial Intelligence (AI) methods from basic science to clinical use. Using selected examples, we will discuss these challenges and how they can be addressed.
11:45 Panel Discussion