{"id":4987,"date":"2026-01-16T12:48:50","date_gmt":"2026-01-16T11:48:50","guid":{"rendered":"https:\/\/websites.fraunhofer.de\/smart-sensing-insights\/?p=4987"},"modified":"2026-01-27T20:44:08","modified_gmt":"2026-01-27T19:44:08","slug":"train-your-own-ai","status":"publish","type":"post","link":"https:\/\/websites.fraunhofer.de\/smart-sensing-insights\/train-your-own-ai\/","title":{"rendered":"Train your own AI with the Segmentation AI Author: Ovarian Cancer Example"},"content":{"rendered":"\n

This MIKAIA\u00ae<\/sup> University<\/a> app note demonstrates how to quickly and interactively train your own AI using just a few training annotations, all in a matter of minutes. <\/p>\n\n\n

\n
\"Information:<\/figure>\n<\/div>\n\n\n

In the app center, select the Segmentation AI Author App, click “+” to create a new trainable AI, and pick a name. Then, add the tissue classes you want the AI to recognize. In this example. we annotated “Tumor”, “Necrosis”, “Stroma”, “Background”, “Inflammation”, and “Other”. Next, create a few small training annotations. If a class has several slightly different appearances, it is best to draw multiple small annotations. The screenshot below shows the training annotations.<\/p>\n\n\n\n

\"screenshot
Training annotations for six tissue classes (here only max three annotations per class) created by hand<\/figcaption><\/figure>\n\n\n\n

Now, click “train.” The Segmentation AI Author app will use its foundation model backend to extract features from the training annotations and derive a prototypical representation of each class in the high-dimensional feature space. No actual “AI training” in the technical sense is happening here, so the training phase typically only takes less than a minute.<\/p>\n\n\n\n

The features can be visualized in a t-SNE or UMAP plot: <\/p>\n\n\n\n