top of page
EMPAIAacademy_Logo-04 (002).jpg

Hands-on Workshop ECDP2022 in Berlin

At the European Congress on Digital Pathology 2022, we held a 90-minute workshop as a hands-on introduction to computational pathology both for pathologists and computer scientists. Participants were able choose between three tracks, where they worked in small groups to analyze histological images interactively, using scripted image processing or AI techniques. The workshop material is available via this page.

Whole-Slide Image Analysis with QuPath

In the tutorial “WSI Analysis with QuPath”‚ we explore the open source software QuPath, a free to use platform, which provides tools for analysis of scanned histopathological slides, so-called whole slide images (WSIs). You will learn: (1) How to install QuPath and use it for viewing and annotating a WSI. (2) How to train the AI-based classification algorithm, which is provided by QuPath, so that this algorithm can find tumor and non-tumor areas on a WSI. (3) How to use QuPath to determine the Ki-67 index, a well-known method for assessment of cancer cell proliferation in various tumors. Neither programming skills nor pathology knowledge are needed to participate in this tutorial.


 

Mitosis Detection using Image Processing Techniques in Python

In “Mitosis Detection using Image Processing Techniques in Python,” we gain a fundamental understanding of basic image processing techniques using mitosis detection in PHH3 slides as an example. We will cover the following topics:

  • Digital image representation

  • Basic operations (color deconvolution, thresholding, morphological operators, and segmentation)

  • Extraction of geometrical and statistical features

  • Classification of mitosis candidates

Python knowledge is useful but not mandatory, as the concepts of image processing are the main focus.

​

​

Histology Toy Example on Machine Learning

In the tutorial “Histology Toy Example Machine Learning,” we teach a computer to distinguish between tissue images of two classes. You set up a simple machine learning pipeline consisting of learning, applying, and displaying the results. You learn to interpret the results, the relationship of model complexity and training data as well as the importance of testing to detect some pitfalls of binary classifiers. You will need to read (and maybe modify) a few lines of Python code.

 

bottom of page