# Prodigy and Skin Cancer Detection **URL:** \ **Category:** Uncategorized\ **Tags:** custom, medical\ **Created:** [December 19, 2022, 12:06pm UTC](https://support.prodi.gy/t/prodigy-and-skin-cancer-detection/6193 "2022-12-19T12:06:18Z")\ **Posts on this page:** 1\ **Showing post:** 2
**Author:** ![ryanwesslen](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ryanwesslen/32/2969_2.png) [@ryanwesslen](https://support.prodi.gy/u/ryanwesslen)\ **Post date:** [December 19, 2022, 1:27pm UTC](https://support.prodi.gy/t/prodigy-and-skin-cancer-detection/6193/2 "2022-12-19T13:27:25Z")
hi @KSK! Thanks for your message! Out-of-the-box, Prodigy works with spaCy which focuses on NLP/information retrieval problems. However, Prodigy was designed to be extensible that developers can custom Prodigy for their workflows like with PyTorch or TensorFlow, which are popular libraries for image recognition. First, I'd start with [our computer vision docs](https://prodi.gy/docs/computer-vision#custom-model) where we have a section on how to develop a [custom Prodigy recipe](https://prodi.gy/docs/custom-recipes) with a custom image model. As an example, we have a tutorial on creating a [custom TensorFlow object recognition recipe for Prodigy](https://support.prodi.gy/t/integrating-tensorflows-object-detection-api-with-prodigy/1965) based on TensorFlow's object recognition API. You can view the code [here](https://github.com/explosion/prodigy-recipes/tree/master/image/tf_odapi). Next, I'd also recommend this post from Ines on good tips of working with PyTorch and Prodigy's bounding box annotations: > [@Pytorch based bounding box annotations](https://support.prodi.gy/t/pytorch-based-bounding-box-annotations/3791/2): > > Hi and sorry you were having trouble with TensorFlow! If you already have a PyTorch model, it's probably better to just use that slightly_smiling_face (Also, the modelling it typically the "hard part" so if you have a model that's trained and that predicts something, it should hopefully be no problem to integrate it with Prodigy). For your annotation workflow, you probably want to use a [custom recipe](https://prodi.gy/docs/custom-recipes) with the [image\_manual](https://prodi.gy/docs/api-interfaces#image_manual) interface. Here's a basic template you can use to get started: Funda… Also, I would recommend looking at Prodigy's docs on [input data formatting for images](https://prodi.gy/docs/api-loaders/#input-images). I don't have a lot of experience with skin cancer detection models, but I've found [some online PyTorch resources](https://ngoc-pham.medium.com/skin-cancer-classification-with-transfer-learning-in-pytorch-389254e39ac1) that fine-tune general purpose image models. This may be a good approach to start with. Hope these help to get you started! --- _[View the full topic](https://support.prodi.gy/t/prodigy-and-skin-cancer-detection/6193)._