Duke AI Health Data Studio: Hands-On Digital Pathology
Friday, October 28, 2022
This in-person workshop will give you hands-on experience in working with medical digital pathology images using machine learning. Our use case will be in whole slide images of lymph node sections. We will use the CAMELYON16 dataset (https://camelyon16.grand-challenge.org/), which consists of 400 hematoxylin and eosin stained whole-slide images. During the workshop, you will learn how to retrieve, manage, and process these images, and then apply a machine learning model based on a neural network architecture to classify image regions as normal or malignant. The techniques you learn will also be broadly applicable to other types of medical imaging.
This session has 2 coding notebooks developed by Akhil Ambekar:
- Hands-on studio: Data processing for digital pathology: https://github.com/dukeplusds/pathstudio2022/blob/main/pathologyAI_Session01.ipynb
- Hands-on studio: Implementation of the ML model: https://github.com/dukeplusds/pathstudio2022/blob/main/pathologyAI_Session02.ipynb
We will use pre-built software containers running PyTorch and Jupyter Notebooks hosted by Duke OIT’s Container Manager (https://cmgr.oit.duke.edu/containers). The containers are accessible via your web browser in this platform, and you will not need to install any software, making it easy for you to implement the data processing and ML modeling steps.
These notebooks are optimized to run in Duke's Container Manager, but if you wish to install PyTorch in your own environment, please visit https://github.com/dukeplusds/PyTorchTutorials
To learn more about this session, visit: https://aihealth.duke.edu/duke-ai-health-data-studio-hands-on-digital-pathology/