DeepInverse (JOSS 2024)
github.com/deepinv/deepinvPyTorch library and benchmark for solving imaging inverse problems (MRI, CT, deblurring, inpainting, phase retrieval) with deep learning, unifying plug-and-play, unrolled, diffusion, and equivariant priors with built-in physics operators, datasets, and metrics (deepinv.org, 846+ stars, BSD-3-Clause, actively maintained)
Sourced from
- Awesome AI for Science — github.com/deepinv/deepinv
- GitHub — github.com/deepinv/deepinv
Related resources
BIBSNet is an open-source deep learning model designed for robust and generalizable brain tissue segmentation in MRI scans of infants (0-8 months). It processes MR data to segment various brain tissues, which is critical for studying early brain development.
Open-source deep learning toolbox for bioimage analysis providing a unified, configuration-driven framework for 2D/3D semantic segmentation, instance segmentation, classification, denoising, super-resolution, and self-supervised learning; integrates state-of-the-art architectures including U-Net, Vision Transformers, and ConvNeXt, designed for microscopy and biomedical imaging researchers without extensive coding expertise (MIT License, actively maintained)
Deep-learning library for AI microscopy image restoration implementing CARE (content-aware restoration, Nature Methods 2018), Noise2Void/Noise2Fast self-supervised denoising, and related pixel-restoration algorithms as a unified, pip-installable training/inference API on a PyTorch Lightning backend, with Fiji plugin and napari integration for denoising, deconvolution, super-resolution, and virtual-staining workflows across light and electron microscopy (successor to CSBDeep, 157+ stars, BSD-3-Clause, actively maintained, 2023-2026)
A unified computational framework for performing cortical reconstruction and anatomical parcellation on high-resolution postmortem infant MRI. It combines deep learning segmentation with a specialized synthetic data generation engine (PostSynth) to handle postmortem domain shifts.