| { |
| "_ilex": { |
| "architecture": "ilex.models.brain_ldm_vae.model.BrainLDMVAE", |
| "constructor_kwargs": {}, |
| "format": "ilex", |
| "framework_version": { |
| "equinox": "0.13.8", |
| "ilex": "0.0.0.dev0", |
| "jax": "0.10.0", |
| "jaxlib": "0.10.0", |
| "numpy": "2.4.4", |
| "safetensors": "0.7.0" |
| }, |
| "has_state": false, |
| "origin": "ilex-native", |
| "weights_status": "bundled" |
| }, |
| "authors": "Walter H. L. Pinaya, Petru-Daniel Tudosiu, Jessica Dafflon, Pedro F. Da Costa, Virginia Fernandez, Parashkev Nachev, Sebastien Ourselin, M. Jorge Cardoso", |
| "copyright": "Network architecture and pretrained weights -- copyright (c) MONAI Consortium, released under the Apache License 2.0. JAX / Equinox port code -- copyright (c) the ilex authors, released under the Apache-2.0 / GPL-3.0 dual license used by ilex itself.", |
| "data_type": "nibabel", |
| "description": "The image-latent compressor sub-network of the MONAI Brain LDM release (Pinaya et al., MICCAI Workshop 2022). A 3D KL-regularized VAE that maps T1w brain MRI volumes into a 3-channel latent space at 8x spatial downsampling -- the latent representation that drives the conditional diffusion U-Net in the composite Brain LDM. Architecture (MONAI-canonical): spatial_dims=3, in/out channels=1, latent_channels=3, channel ladder (64, 128, 128, 128), 2 residual blocks per level, GroupNorm with eps=1e-6, no attention (pure ResNet). Trained on 31,740 UK Biobank T1w MRIs at 1mm isotropic, intensity-normalised to [0, 1]. Shipped as its own bundle so future 3D latent-diffusion models for medical imaging can reuse the same VAE backbone via the canonical bundle.", |
| "equinox_version": "0.13.8", |
| "ilex_version": "0.0.0.dev0", |
| "image_classes": "Single-channel 3D T1-weighted brain MRI, 1 mm isotropic, intensity in [0, 1].", |
| "intended_use": "Research tool / prototype. Encode a 3D T1-weighted brain MRI volume into a 3-channel latent representation, or decode a latent back to image space. Inputs must be conformed to 1 mm isotropic and intensity- normalised to [0, 1] per the upstream's preprocessing recipe (UniRes rigid-body to MNI + min-max [0, 1] normalisation). Each spatial dim of the input must be a multiple of 8 (the 3-level stride-2 encoder downsample). Use this bundle directly when the latent representation is the desired output (e.g., as input to a downstream diffusion model or for latent-space analysis); use ilex.models.brain_ldm.BrainLDM for the full conditional sampling pipeline.", |
| "jax_version": "0.10.0", |
| "network_data_format": { |
| "inputs": {}, |
| "outputs": {} |
| }, |
| "numpy_version": "2.4.4", |
| "pred_classes": "3-channel latent volume at 1/8 spatial resolution (encode_mean) or single-channel reconstructed volume at the input spatial resolution (decode).", |
| "references": [ |
| "Pinaya W. H. L., Tudosiu P.-D., Dafflon J., Da Costa P. F., Fernandez V., Nachev P., Ourselin S., Cardoso M. J. (2022). Brain imaging generation with latent diffusion models. MICCAI Workshop on Deep Generative Models, Springer, pp. 117-126.", |
| "Upstream bundle: huggingface.co/MONAI/brain_image_synthesis_latent_diffusion_model (autoencoder.pt; ~13.77M params).", |
| "Architecture: monai.networks.nets.AutoencoderKL (MONAI 1.4+)." |
| ], |
| "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20240725.json", |
| "task": "3D KL-regularized brain MRI autoencoder (latent-diffusion backbone)", |
| "version": "0.0.0" |
| } |
