Course curriculum

    1. Course agenda - 1.5

    1. Module objectives 1.1

    2. Machine learning in life sciences - 1.2

    3. Automatic analysis of Medical Images 1.3

    4. Semantic segmentation 1.4

    1. Module objectives 2-1

    2. Introduction to NVIDIA MONAI

    3. What is MONAI Workflow?

    4. MONAI stack

    5. Find out more about NVIDIA

    6. MONAI Model Zoo

    7. Getting started and further resources

    8. Introduction to W&B

    1. Module objectives 3-1

    2. Introduction to the challenge 3-2

    3. The dataset 3-3

    4. Getting started with code 3-4

    1. Module objective 4.1

    1. Module objective 5.1

About this course

  • Free
  • 25 lessons
  • 1 hour of video content

The course instructors

Soumik Rakshit

Machine Learning Engineer @ Weights & Biases

Soumik Rakshit is a Machine Learning Engineer at Weights & Biases with a background in computer vision, with research interests in foundation models, generative models for images, and representation learning. He develops and maintains integrations with open-source libraries, prototypes experimental tools, writes captivating blog posts, and shares his expertise through webinars. Soumik is an active open-source contributor, regularly contributing to projects such as Keras, KerasCV, Ultralytics, Super-Gradients, Kaolin-Wisp, PyTorch Geometric, and Weave, while also maintaining Weights & Biases integrations and developing new ML-centric tools.

Michael Zephyr

Technical product manager for Healthcare AI @ NVIDIA

Michael Zephyr is a technical product manager for healthcare AI at NVIDIA. He leads both NVIDIA MONAI Services and the open-source Project MONAI Outreach Working Group. With a focus on enhancing annotation, fine-tuning, and training through API Services, Michael is dedicated to transforming how organizations use AI in healthcare. He sees API Services as the essential tool for enterprises to seamlessly adopt cutting-edge solutions.

Learning objectives

  • Visualize medical imaging datasets

    Explore, analyze, and visualize complex medical imaging datasets using industry-standard tools.

  • Implement state-of-the-art models

    Gain hands-on experience implementing cutting-edge 3D segmentation models in PyTorch.

  • Execute medical imaging workflow

    Build reproducible, production-ready medical imaging pipelines using industry-standard MLOps tools.

Recommended prerequisites

  • Foundational machine learning concepts

  • Familiarity with PyTorch framework

  • Basic understanding of computer vision principles

  • Working knowledge of Python programming

“It's been a great solution for logging and tracking training runs. It's nice that you can easily superimpose different runs too. That was particularly useful for us, for example, during our ablation studies.”

Gustaf Ahdritz, Lead Developer @ OpenFold

“The systems tab gives us great insight into how to efficiently allocate resources while also keeping costs low—if we don’t see above 95% GPU utilization, we know there is room to optimize, making our experiments run faster and helping control our costs.”

Mozzi Etemadi, Anesthesiologist and Director of Advanced Technologies @ Northwestern Medicine

“W&B has made it easy for knowledge sharing. I can quickly show someone an experiment I ran, the outcomes, and explain my work.”

Theo Wolf, Machine Learning Engineer @ Carbon Re

“[With Weights & Biases] we demonstrated our workflow in training high-capacity models, reducing overfitting while increasing model capacity, and maintaining fast iteration speed.”

Andrew Zhong & Qiangui (Jack) Huang fromLyft