This course will teach you how to apply deep learning to radiology and medical imaging. You’ll learn image segmentation, how to train convolutional neural networks (CNNs), and techniques for using radiomics to identify the genomics of a disease.

This course is offered in partnership with NVIDIA. It has been developed with the expertise of the Mayo Clinic. The course will be offered at a distance and the number of participants will be limited to 40 in order to encourage interaction with the instructor.

 

Access the registration form (limited to 40 participants)

 

Duration: 8 hours

Assessment type: Code-based

Certificate: Upon successful completion of the assessment, participants will receive an NVIDIA DLI certificate to recognize their subject matter competency and support professional career growth.

Prerequisites: Basic familiarity with deep neural networks; basic coding experience in Python or a similar language

Tools, libraries, and frameworks: Caffe, NVIDIA DIGITS, R, MXNet, TensorFlow

 

Learning Objectives
At the conclusion of the workshop, you’ll understand how to use deep learning in healthcare image analysis and be able to:

• Train CNNs to infer the volume of the left ventricle of the human heart from time-series MRI data
• Perform image segmentation on MRI images to determine the location of the left ventricle
• Use CNNs to detect heart disease and calculate ejection fractions by measuring the differences between diastole and systole
• Apply CNNs to MRI scans of low-grade gliomas (LGGs) to determine 1p/19q chromosome co-deletion status

Programme

Introduction (15 mins)

> Meet the instructor.
> Create an account at courses.nvidia.com/join

Image Segmentation (120 mins)

Learn techniques for placing each pixel of an image into a specific class:
> Extend Caffe with custom Python layers.
> Implement the process of transfer learning.
> Create fully convolutional neural networks from popular image classification networks.

 

Break (60 mins)

 

Image Analysis (120 mins)

Leverage CNNs for medical image analysis to infer patient status from non-visible images:
> Extend a canonical 2D CNN to more complex data.
> Use the framework MXNet through the standard Python API and R.
> Process high-dimensional imagery that may be volumetric and temporal.

Image Classification with TensorFlow (120 mins)

Learn about deep learning techniques for detecting imaging genomics (radiomics) from MRIs:
> Design and train CNNs.
> Use radiomics to create biomarkers that identify the genomics of a disease
without the use of an invasive biopsy.
> Explore the radiogenomics work being done at the Mayo Clinic, which has led to more effective treatments and better health outcomes for patients with brain tumors.

Final Review (15 mins)

> Review key learnings and wrap up questions.
> Complete the assessment to earn a certificate.
> Take the workshop survey.