Magician's Corner: 9. Performance Metrics for Machine Learning Models.

I the previous articles, we showed how to process images and train classification models, segmentation models, generative adversarial networks, as well as image denoising models. We also provided a guide on how to visualize model training metrics with TensorBoard and how to connect a model to your picture archiving and communication system. In this article, we will show you how to evaluate the performance of your models by delving into some details about classification and segmentation metrics and show how to calculate them. Performance metrics are useful during model training and validation. We also provide an interactive way for you to see how a custom threshold influences these metrics. To follow this guide, open Colab by clicking on this link: https://colab.research.google.com. Make sure to use Google Chrome as your web browser. You should be prompted to open a file when you start it, but otherwise, select the File > Open Notebook menu option, select the “Github” tab at the top, enter “RSNA” into the search field, and then select the repository “RSNA/MagiciansCorner.” Select the entry called “Magicians_Corner_9_ Performance_Metrics_for_Machine_Learning.ipynb” to load the notebook. Click the arrow at the left of the first cell to run cell 1 (you may need to accept that it is not Google code).