torchio and ttach
These are **complements** — TorchIO provides domain-specific medical image augmentations (3D volumes, anatomy-aware transforms) while ttach provides general-purpose test-time augmentation inference strategies (multi-crop/flip predictions), and both can be used together in a medical imaging pipeline.
About torchio
TorchIO-project/torchio
Medical imaging processing for AI applications.
This tool helps medical researchers and practitioners prepare 3D medical images, such as MRI or CT scans, for artificial intelligence applications. It takes raw medical imaging data and applies various transformations, augmentations, and preprocessing steps, outputting enhanced image datasets ready for training AI models. Radiologists, clinical researchers, and biomedical engineers developing AI for image analysis would find this useful.
About ttach
qubvel/ttach
Image Test Time Augmentation with PyTorch!
This tool helps machine learning engineers and researchers improve the accuracy of their image-based AI models during evaluation. It takes a trained model and a batch of test images, then applies various transformations like flips, rotations, and scaling to each image. The model then makes predictions on all augmented versions, which are then combined to produce a more robust and accurate final prediction for segmentation, classification, or keypoint detection tasks.
Scores updated daily from GitHub, PyPI, and npm data. How scores work