diff --git a/model-zoo/models/brain_image_synthesis_latent_diffusion_model/LICENSE b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/LICENSE new file mode 100644 index 00000000..261eeb9e --- /dev/null +++ b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/LICENSE @@ -0,0 +1,201 @@ + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. diff --git a/model-zoo/models/brain_image_synthesis_latent_diffusion_model/configs/inference.json b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/configs/inference.json new file mode 100644 index 00000000..9edac693 --- /dev/null +++ b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/configs/inference.json @@ -0,0 +1,104 @@ +{ + "imports": [ + "$import torch", + "$from datetime import datetime", + "$from pathlib import Path" + ], + "bundle_root": ".", + "model_dir": "$@bundle_root + '/models'", + "output_dir": "$@bundle_root + '/output'", + "create_output_dir": "$Path(@output_dir).mkdir(exist_ok=True)", + "gender": 0.0, + "age": 0.1, + "ventricular_vol": 0.2, + "brain_vol": 0.4, + "device": "$torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')", + "conditioning": "$torch.tensor([[@gender, @age, @ventricular_vol, @brain_vol]]).to(@device).unsqueeze(1)", + "out_file": "$datetime.now().strftime('sample_%H%M%S_%d%m%Y') + '_' + str(@gender) + '_' + str(@age) + '_' + str(@ventricular_vol) + '_' + str(@brain_vol)", + "autoencoder_def": { + "_target_": "generative.networks.nets.AutoencoderKL", + "spatial_dims": 3, + "in_channels": 1, + "out_channels": 1, + "latent_channels": 3, + "num_channels": [ + 64, + 128, + 128, + 128 + ], + "num_res_blocks": 2, + "norm_num_groups": 32, + "norm_eps": 1e-06, + "attention_levels": [ + false, + false, + false, + false + ], + "with_encoder_nonlocal_attn": false, + "with_decoder_nonlocal_attn": false + }, + "load_autoencoder_path": "$@model_dir + '/autoencoder.pth'", + "load_autoencoder": "$@autoencoder_def.load_state_dict(torch.load(@load_autoencoder_path))", + "autoencoder": "$@autoencoder_def.to(@device)", + "diffusion_def": { + "_target_": "generative.networks.nets.DiffusionModelUNet", + "spatial_dims": 3, + "in_channels": 7, + "out_channels": 3, + "num_channels": [ + 256, + 512, + 768 + ], + "num_res_blocks": 2, + "attention_levels": [ + false, + true, + true + ], + "norm_num_groups": 32, + "norm_eps": 1e-06, + "resblock_updown": true, + "num_head_channels": [ + 0, + 512, + 768 + ], + "with_conditioning": true, + "transformer_num_layers": 1, + "cross_attention_dim": 4, + "upcast_attention": true, + "use_flash_attention": false + }, + "load_diffusion_path": "$@model_dir + '/diffusion_model.pth'", + "load_diffusion": "$@diffusion_def.load_state_dict(torch.load(@load_diffusion_path))", + "diffusion": "$@diffusion_def.to(@device)", + "scheduler": { + "_target_": "generative.networks.schedulers.DDIMScheduler", + "_requires_": [ + "@load_diffusion", + "@load_autoencoder" + ], + "beta_start": 0.0015, + "beta_end": 0.0205, + "num_train_timesteps": 1000, + "beta_schedule": "scaled_linear", + "clip_sample": false + }, + "noise": "$torch.randn((1, 3, 20, 28, 20)).to(@device)", + "set_timesteps": "$@scheduler.set_timesteps(num_inference_steps=50)", + "sampler": { + "_target_": "scripts.sampler.Sampler", + "_requires_": "@set_timesteps" + }, + "sample": "$@sampler.sampling_fn(@noise, @autoencoder, @diffusion, @scheduler, @conditioning)", + "saver": { + "_target_": "scripts.saver.NiftiSaver", + "_requires_": "@create_output_dir", + "output_dir": "@output_dir" + }, + "save_nii": "$@saver.save(@sample, @out_file)", + "save": "$torch.save(@sample, @output_dir + '/' + @out_file + '.pt')" +} diff --git a/model-zoo/models/brain_image_synthesis_latent_diffusion_model/configs/logging.conf b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/configs/logging.conf new file mode 100644 index 00000000..91c1a21c --- /dev/null +++ b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/configs/logging.conf @@ -0,0 +1,21 @@ +[loggers] +keys=root + +[handlers] +keys=consoleHandler + +[formatters] +keys=fullFormatter + +[logger_root] +level=INFO +handlers=consoleHandler + +[handler_consoleHandler] +class=StreamHandler +level=INFO +formatter=fullFormatter +args=(sys.stdout,) + +[formatter_fullFormatter] +format=%(asctime)s - %(name)s - %(levelname)s - %(message)s diff --git a/model-zoo/models/brain_image_synthesis_latent_diffusion_model/configs/metadata.json b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/configs/metadata.json new file mode 100644 index 00000000..4310640e --- /dev/null +++ b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/configs/metadata.json @@ -0,0 +1,72 @@ +{ + "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json", + "version": "1.0.0", + "changelog": { + "1.0.8": "Initial release" + }, + "monai_version": "1.1.0", + "pytorch_version": "1.13.0", + "numpy_version": "1.22.4", + "optional_packages_version": { + "nibabel": "4.0.1", + "generative": "0.1.0" + }, + "task": "Brain image synthesis", + "description": "A generative model for creating high-resolution 3D brain MRI based on UK Biobank", + "authors": "Walter H. L. Pinaya, Petru-Daniel Tudosiu, Jessica Dafflon, Pedro F Da Costa, Virginia Fernandez, Parashkev Nachev, Sebastien Ourselin, and M. Jorge Cardoso", + "copyright": "Copyright (c) MONAI Consortium", + "data_source": "https://www.ukbiobank.ac.uk/", + "data_type": "nibabel", + "image_classes": "T1w head MRI with 1x1x1 mm voxel size", + "eval_metrics": { + "fid": 0.0076, + "msssim": 0.6555, + "4gmsssim": 0.3883 + }, + "intended_use": "This is a research tool/prototype and not to be used clinically", + "references": [ + "Pinaya, Walter HL, et al. \"Brain imaging generation with latent diffusion models.\" MICCAI Workshop on Deep Generative Models. Springer, Cham, 2022." + ], + "network_data_format": { + "inputs": { + "image": { + "type": "tabular", + "num_channels": 1, + "dtype": "float32", + "value_range": [ + 0, + 1 + ], + "is_patch_data": false, + "channel_def": { + "0": "Gender", + "1": "Age", + "2": "Ventricular volume", + "3": "Brain volume" + } + } + }, + "outputs": { + "pred": { + "type": "image", + "format": "magnitude", + "modality": "MR", + "num_channels": 1, + "spatial_shape": [ + 160, + 224, + 160 + ], + "dtype": "float32", + "value_range": [ + 0, + 1 + ], + "is_patch_data": false, + "channel_def": { + "0": "T1w" + } + } + } + } +} diff --git a/model-zoo/models/brain_image_synthesis_latent_diffusion_model/docs/README.md b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/docs/README.md new file mode 100644 index 00000000..8a2dded6 --- /dev/null +++ b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/docs/README.md @@ -0,0 +1,58 @@ +# Brain Imaging Generation with Latent Diffusion Models + +### **Authors** + +Walter H. L. Pinaya, Petru-Daniel Tudosiu, Jessica Dafflon, Pedro F Da Costa, Virginia Fernandez, Parashkev Nachev, +Sebastien Ourselin, and M. Jorge Cardoso + +### **Tags** +Synthetic data, Latent Diffusion Model, Generative model, Brain Imaging + +## **Model Description** +This model is trained using the Latent Diffusion Model architecture [1] and is used for the synthesis of conditioned 3D +brain MRI data. The model is divided into two parts: an autoencoder with a KL-regularisation model that compresses data +into a latent space and a diffusion model that learns to generate conditioned synthetic latent representations. This +model is conditioned on age, sex, the volume of ventricular cerebrospinal fluid, and brain volume normalised for head size. + +## **Data** +The model was trained on brain data from 31,740 participants from the UK Biobank [2]. We used high-resolution 3D T1w MRI with voxel size of 1mm3, resulting in volumes with 160 x 224 x 160 voxels + +#### **Preprocessing** +We used UniRes [3] to perform a rigid body registration to a common MNI space for image pre-processing. The voxel intensity was normalised to be between [0, 1]. + +## **Performance** +This model achieves the following results on UK Biobank: an FID of 0.0076, an MS-SSIM of 0.6555, and a 4-G-R-SSIM of 0.3883. + +Please, check Table 1 of the original paper for more details regarding evaluation results. + + +## **commands example** +Execute sampling: +``` +export PYTHONPATH=$PYTHONPATH:"" +$ python -m monai.bundle run save_nii --config_file configs/inference.json --gender 1.0 --age 0.7 --ventricular_vol 0.7 --brain_vol 0.5 +``` +All conditioning are expected to have values between 0 and 1 + +## **Citation Info** + +``` +@inproceedings{pinaya2022brain, + title={Brain imaging generation with latent diffusion models}, + author={Pinaya, Walter HL and Tudosiu, Petru-Daniel and Dafflon, Jessica and Da Costa, Pedro F and Fernandez, Virginia and Nachev, Parashkev and Ourselin, Sebastien and Cardoso, M Jorge}, + booktitle={MICCAI Workshop on Deep Generative Models}, + pages={117--126}, + year={2022}, + organization={Springer} +} +``` + +## **References** + +Example: + +[1] Pinaya, Walter HL, et al. "Brain imaging generation with latent diffusion models." MICCAI Workshop on Deep Generative Models. Springer, Cham, 2022. + +[2] Sudlow, Cathie, et al. "UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age." PLoS medicine 12.3 (2015): e1001779. + +[3] Brudfors, Mikael, et al. "MRI super-resolution using multi-channel total variation." Annual Conference on Medical Image Understanding and Analysis. Springer, Cham, 2018. diff --git a/model-zoo/models/brain_image_synthesis_latent_diffusion_model/large_files.yml b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/large_files.yml new file mode 100644 index 00000000..2083c0d8 --- /dev/null +++ b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/large_files.yml @@ -0,0 +1,9 @@ +large_files: + - path: "models/autoencoder.pth" + url: "https://drive.google.com/uc?export=download&id=1CZHwxHJWybOsDavipD0EorDPOo_mzNeX" + hash_val: "" + hash_type: "" + - path: "models/diffusion_model.pth" + url: "https://drive.google.com/uc?export=download&id=1XO-ak93ZuOcGTCpgRtqgIeZq3dG5ExN6" + hash_val: "" + hash_type: "" diff --git a/model-zoo/models/brain_image_synthesis_latent_diffusion_model/scripts/__init__.py b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/scripts/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/model-zoo/models/brain_image_synthesis_latent_diffusion_model/scripts/sampler.py b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/scripts/sampler.py new file mode 100644 index 00000000..3058c470 --- /dev/null +++ b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/scripts/sampler.py @@ -0,0 +1,45 @@ +from __future__ import annotations + +import torch +import torch.nn as nn +from monai.utils import optional_import +from torch.cuda.amp import autocast + +tqdm, has_tqdm = optional_import("tqdm", name="tqdm") + + +class Sampler: + def __init__(self) -> None: + super().__init__() + + @torch.no_grad() + def sampling_fn( + self, + input_noise: torch.Tensor, + autoencoder_model: nn.Module, + diffusion_model: nn.Module, + scheduler: nn.Module, + conditioning: torch.Tensor, + ) -> torch.Tensor: + if has_tqdm: + progress_bar = tqdm(scheduler.timesteps) + else: + progress_bar = iter(scheduler.timesteps) + + image = input_noise + cond_concat = conditioning.squeeze(1).unsqueeze(-1).unsqueeze(-1).unsqueeze(-1) + cond_concat = cond_concat.expand(list(cond_concat.shape[0:2]) + list(input_noise.shape[2:])) + for t in progress_bar: + with torch.no_grad(): + model_output = diffusion_model( + torch.cat((image, cond_concat), dim=1), + timesteps=torch.Tensor((t,)).to(input_noise.device).long(), + context=conditioning, + ) + image, _ = scheduler.step(model_output, t, image) + + with torch.no_grad(): + with autocast(): + sample = autoencoder_model.decode_stage_2_outputs(image) + + return sample diff --git a/model-zoo/models/brain_image_synthesis_latent_diffusion_model/scripts/saver.py b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/scripts/saver.py new file mode 100644 index 00000000..de882df0 --- /dev/null +++ b/model-zoo/models/brain_image_synthesis_latent_diffusion_model/scripts/saver.py @@ -0,0 +1,29 @@ +from __future__ import annotations + +import nibabel as nib +import numpy as np +import torch + + +class NiftiSaver: + def __init__(self, output_dir: str) -> None: + super().__init__() + self.output_dir = output_dir + self.affine = np.array( + [ + [-1.0, 0.0, 0.0, 96.48149872], + [0.0, 1.0, 0.0, -141.47715759], + [0.0, 0.0, 1.0, -156.55375671], + [0.0, 0.0, 0.0, 1.0], + ] + ) + + def save(self, image_data: torch.Tensor, file_name: str) -> None: + image_data = image_data.cpu().numpy() + image_data = image_data[0, 0, 5:-5, 5:-5, :-15] + image_data = (image_data - image_data.min()) / (image_data.max() - image_data.min()) + image_data = (image_data * 255).astype(np.uint8) + + empty_header = nib.Nifti1Header() + sample_nii = nib.Nifti1Image(image_data, self.affine, empty_header) + nib.save(sample_nii, f"{str(self.output_dir)}/{file_name}.nii.gz")