Emphasizing the synergy of radiologists' and machines' intelligence to enhance the performance of radiological AI systems!*
* This will be a tutorial taught at MICCAI2023
Microsoft Teams Meeting Link
Describes how radiologists and machine learning algorithms interact to solve radiological AI problems.
Introduces the concept of AL and how it differs from a random approach by using a systematic method for selecting data to be annotated.
Describes strategies for identifying images that are near a decision boundary in the current ML model.
Describes strategies for identifying unlabeled images that are underrepresented in the current ML model.
Demonstrates how to implement the image sampling strategies and apply them to real-world problems.
Explains how knowledge-transfer can be achieved.
How the concepts learned above can be used to perform liver view classification in ultrasound images (i.e., images with liver vs. images without liver).
Abder-Rahman Ali, PhD
Harvard Medical School/Massachusetts General Hospital
aali25 [at] mgh.harvard.edu
© Abder-Rahman Ali, PhD