Data best practices

Different magnifications

For AI training, it is important to take into account the magnification of images produced by microscopy. One simple rule of thumb is that for best performance, objects in your images should be at least 10 pixels across for optimal performance.
In microscopy, images with different magnifications have different pixel resolutions and object sizes. If you only want to analyze 20x images, you should only include 20x images.
If instead, you will need to analyze images with different magnifications with one AI model, it is crucial to include images with different magnifications in the ground truth labels.
a)
b)
Example of images with different magnifications. a) 10x magnification b) 40x magnification.
In the above example, 10x magnification covers a larger tissue area, however, it does not allow you to see cell-level information, such as nuclei. It is unlikely that you will get good performance on 10x images.

Include images without any objects or a few objects.

It's important to include images that do not have any objects in your training cell as well, if you expect them to be part of the images during analysis time. In the absence of this, the performance of AI will suffer when it encounters these regions for the first time in actual image analysis.
For example, if you are building an AI model to identify and segment glomeruli, you should include different regions without any glomeruli, or even regions without any tissue.
a)
b)
c)
Example of images with different tissue regions a) Kidney tissue regions with glomeruli b) fat tissue region without any glomeruli or kidney tissue c) region of the image devoid of any tissues or objects
This will help reduce the occurrence of false positives when your model encounters these three types of images during testing and actual image analysis.
Copy link
On this page
Different magnifications
Include images without any objects or a few objects.