Bannière

Librairie

Week 5 – Ultrasound and instance segmentation

Présenté par

McMedHacks

En ligne

Activités de formation

July 10th at 10:00-11:30 EDT

Speaker: Dr. Reza Forghani

Artificial Intelligence in Medical Imaging: Image-Based Biomarkers & Beyon

This presentation will provide and overview of image-based quantitative features (radiomics) and machine learning for prediction modeling and precisions diagnostics. The presentation will conclude by discussing some of the broader potential applications of artificial intelligence in medical imaging.

Workshop

July 11th at 10:00-11:30 AM EDT

Instructors: Dr. Peter Watson, Yujing Zou, Luca Weishaupt

Primer on Ultrasound Imaging

Deep learning methods have shown great success in tackling challenging computer vision tasks in contexts This talk will cover the basic principles of US imaging, and possible image artifacts you may encounter.

Mask-RCNN a popular instance segmentation architecture

A high-level introduction to Mask-RCNN, how it works, and its strengths and weaknesses.

Mask-RCNN on 2018 Data Science Bowl

A worked-out example of nucleus segmentation using Mask-RCNN.

Activities

Discover

Featured project

Radiotherapy treatments currently used in the clinical field are rarely modified. They generally consist of a global therapy of 50 grays, fractionated in five treatments of two grays every week for five weeks.
Thus, it could be worthwhile to develop a numeric tool, based on mathematical models found in the literature, in order to compare different types of treatment without having to test them on real tissues. Several parameters are known to alter the tissue response after irradiation including oxygen

Read more