Architecture Zoo · Aperivue/medsci-skills
Choose a model architecture for medical-imaging research
Maps a medical-imaging research task, modality, and data scale to a shortlist of published architectures such as U-Net, ResNet, ViT, and nnU-Net, each with a when-to-use note, reference implementation, and typical validation setup.
Good for
- Pick a segmentation architecture for a new dataset
- Compare CNN and transformer backbones for classification
- Find a reference validation setup for a chosen architecture
- Source repository
- Aperivue/medsci-skills
- Category
- Medicine
Open-source skills are maintained by their authors and listed as published, with attribution. Results depend on how well the skill fits your task and material.
A good place to start
I have a small labeled 3D MRI segmentation dataset — which architecture should I use, with a reference implementation?
Make your next great thing.
Bring a question, a file, or an idea that’s not quite there yet.