This is why your deep learning models don’t work on another microscopy scanner

 By Medium - 2021-03-12

Description

We’ve recently seen quite some large-scale data sets popping up, allowing to train deep learning models to automate a variety of tasks, such as plant cell assessment, cellular nucleus segmentation…

Summary

  • So, while some people already talk about another AI winter, and promises that are not fulfilled, in the biomedical field we just see deep learning models really delivering on the promise and achieving superb results.
  • The digital microscope (or microscopy whole slide scanner) you are using should capture the hardware microscopy slide exactly as it is, and it even can control for light conditions, etc.
  • The drop is especially pronounced for the Hamamatsu scanners, and rather weak for the Aperio CS2 scanner.
  • And this is why it won’t work well, once we change those.

 

Topics

  1. Backend (0.33)
  2. Machine_Learning (0.28)
  3. Database (0.12)

Similar Articles

K-fold Cross Validation with PyTorch

By MachineCurve - 2021-02-02

Explanations and code examples showing you how to use K-fold Cross Validation for Machine Learning model evaluation/testing with PyTorch.

Introduction to Active Learning

By KDnuggets - 2020-12-15

An extensive overview of Active Learning, with an explanation into how it works and can assist with data labeling, as well as its performance and potential limitations.