Course Information
Registration period
Year-round Recruitment
Course Level
Study Mode
Duration
12 Hour(s) 5 Minute(s)
Language
English
Taught by
Jose Portilla, Marcel Früh, Sergios Gatidis, Tobias Hepp, Pierian Training
Certificate
- Available
- *The delivery and distribution of the certificate are subject to the policies and arrangements of the course provider.
Rating
2 views
Course Overview
Learn how to use Pytorch-Lightning to solve real world medical imaging tasks!
Did you ever want to apply Deep Neural Networks to more than MNIST, CIFAR10 or cats vs dogs?
Do you want to learn about state of the art Machine Learning frameworks while segmenting cancer in CT-images?
Then this is the right course for you!
Welcome to one of the most comprehensive courses on Deep Learning in medical imaging!
This course focuses on the application of state of the art Deep Learning architectures to various medical imaging challenges.
You will tackle several different tasks, including cancer segmentation, pneumonia classification, cardiac detection, Interpretability and many more.
The following topics are covered:
NumPy
Machine Learning Theory
Test/Train/Validation Data Splits
Model Evaluation - Regression and Classification Tasks
Tensors with PyTorch
Convolutional Neural Networks
Medical Imaging
Interpretability of a network's decision - Why does the network do what it does?
A state of the art high level pytorch library: pytorch-lightning
Tumor Segmentation
Three-dimensional data
and many more
Why choose this specific Deep Learning with PyTorch for Medical Image Analysis course ?
This course provides unique knowledge on the application of deep learning to highly complex and non-standard (medical) problems (in 2D and 3D)
All lessons include clearly summarized theory and code-along examples, so that you can understand and follow every step.
Powerful online community with our QA Forums with thousands of students and dedicated Teaching Assistants, as well as student interaction on our Discord Server.
You will learn skills and techniques that the vast majority of AI engineers do not have!
--------------
Jose, Marcel, Sergios & Tobias
Course Content
- 13 section(s)
- 88 lecture(s)
- Section 1 Introduction
- Section 2 Crash Course: NumPy
- Section 3 Machine Learning Concepts Overview
- Section 4 PyTorch Basics
- Section 5 CNN - Convolutional Neural Networks
- Section 6 Medical Imaging - A short Introduction
- Section 7 Data Formats in Medical Imaging
- Section 8 Pneumonia-Classification
- Section 9 Cardiac-Detection
- Section 10 Atrium-Segmentation
- Section 11 Capstone-Project: Lung Tumor Segmentation
- Section 12 3D Liver and Liver Tumor Segmentation
- Section 13 BONUS SECTION: THANK YOU!
What You’ll Learn
- Learn how to use NumPy
- Learn classic machine learning theory principals
- Foundations of Medical Imaging
- Data Formats in Medical Imaging
- Creating Artificial Neural Networks with PyTorch
- Use PyTorch-Lightning for state of the art training
- Visualize the decision of a CNN
- 2D & 3D data handling
- Automatic Cancer Segmentation
Reviews
-
RRümeysa
Akıcı ve öğretici bir içerik tavsiye ederim
-
AAzaz Hussain
Very nice course for people who just start deep learning. I had very little knowledge about deep learning. The projects really enhanced my undestanding and now I am confident to start a project independently
-
CChristopher Bachstrazza
Section 8 uses an Accuracy optimizer for the model, when Precision or F-1 should likely be used. Its often that medical image datasets experience imbalance, and the dataset in place also is imbalanced, and so the models' ability to identify true positives becomes much more important especially considering that this model could be used to detect something much more critical than pneumonia. The model still works, just not as good as it could be. Recommend re-recording!
-
AAnna Lyamkina
This course is exactly I was looking for: short basics, a short introduction to medical images problems and detailed examples of all main pipelines. Excellent work, thanks a lot!
