YoVDO

Unlocking Hearts by Locking Models: Solving Echocardiogram Problems Using a Self-Supervised Approach

Offered By: GAIA via YouTube

Tags

Self-supervised Learning Courses Machine Learning Courses Deep Learning Courses Image Classification Courses Cardiology Courses Feature Extraction Courses Image Segmentation Courses Medical Imaging Courses Echocardiography Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a groundbreaking self-supervised approach to solving multiple echocardiogram problems in this 20-minute conference talk from the 2023 GAIA Conference. Delve into the Adaptive Locked Agnostic Network (ALAN) concept, which enables label-free, self-supervised learning of visual features for medical imaging applications. Discover how this methodology overcomes the challenge of acquiring labeled data by training on large unlabeled datasets, producing rich informational features applicable to various downstream tasks. Examine the implementation of this approach in two typical echocardiogram tasks: anatomical region segmentation and view classification. Gain insights into the evaluation process using three publicly available datasets: EchoNet-Dynamic, CAMUS, and TMED-2. Learn from Anders Hildeman, a PhD holder in Spatial Statistics with extensive experience in predictive modeling of digital images and geospatial data, as he shares his research in medical image analysis and explores diverse methods and data types in the pharmaceutical industry.

Syllabus

Unlocking Hearts by Locking Models: Solving Echocardiogram Problems Using a Self-Supervised Approach


Taught by

GAIA

Related Courses

Neural Networks for Machine Learning
University of Toronto via Coursera
機器學習技法 (Machine Learning Techniques)
National Taiwan University via Coursera
Machine Learning Capstone: An Intelligent Application with Deep Learning
University of Washington via Coursera
Прикладные задачи анализа данных
Moscow Institute of Physics and Technology via Coursera
Leading Ambitious Teaching and Learning
Microsoft via edX