Generating synthetic tau-PET scans in Alzheimer’s disease from MRI, blood biomarkers and demographics with deep learning
4 blocks of code here have a permanent identifier (oscr:b:…), listed with the matches below: citable for good, with a page of its own. Select a match and press Cite to copy it. What a block identifier is.
The 7 matches
- [1] § Methods › Model development and training › U-Net blocks ↔ src/models/unet3d.py, lines 158 to 183 · score 0.73 · transposed convolutions, decoder blocks, deeper, stride, upsampling, connection · block
oscr:b:J3GGF0JG3KB0H-W· Report a mismatch - [2] § Methods › Participants ↔ notebooks/tau_load_plots.ipynb, lines 19 to 52 · score 0.70 · PREVENT AD, BACS, LLCF, LZAX, OASIS, UCSF · Report a mismatch
- [3] § Methods › Model development and training › U-Net architecture ↔ src/models/unet3d.py, lines 158 to 183 · score 0.64 · skip connections, decoder block, upsamples, layers, convolutional, encoder · block
oscr:b:J3GGF0JG3KB0H-W· Report a mismatch - [4] § Methods › Model development and training › Loss function ↔ src/models/loss.py, lines 7 to 38 · score 0.61 · masked L1 loss, absolute, error, scalar, voxels, brain · block
oscr:b:GWRM9C8KC9535-T· Report a mismatch - [5] § Methods › Participants ↔ notebooks/tau_spat_sim_plots.ipynb, lines 20 to 41 · score 0.60 · Berkeley, LLCF, LZAX, OASIS, UCSF, subset · Report a mismatch
- [6] § Methods › Training ↔ src/models/train.py, lines 116 to 221 · score 0.53 · validation loss, model weights, optimization, batch, training · block
oscr:b:FZ9K3HM7DB69P-5· Report a mismatch - [7] § Methods › Model development and training › Loss function ↔ src/models/train.py, lines 12 to 68 · score 0.50 · masked L1 loss, scalar, brain, weight, predicted, model · block
oscr:b:86S4YCYPXMFG5-O· Report a mismatch
Paper
Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC
The paper is loaded when this pane is shown.
The authors' code
Python · 318 lines · 9 KB · CC-BY-NC-4.0 · 2 matches
- """
- 3D U-Net architecture for synthetic tau-PET generation.
- """
- import numpy as np
- import tensorflow as tf
- from keras import Model
- from keras.layers import (
- Activation,
- BatchNormalization,
- Conv3D,
- Conv3DTranspose,
- Cropping3D,
- Dense,
- Input,
- LeakyReLU,
- MaxPooling3D,
- Reshape,
- ZeroPadding3D,
- add,
- concatenate,
- )
- def conv_block(inputs, num_filters, kernel_size=(3, 3, 3), activation=None, padding="same"):
- """
- Apply 3D convolution, batch normalization, and activation.
- Parameters
- ----------
- inputs : tf.Tensor
- Input tensor.
- num_filters : int
- Number of convolutional filters.
- kernel_size : tuple of int, optional
- Convolution kernel size. Default is (3, 3, 3).
- activation : keras.layers.Layer or None, optional
- Activation layer. Default is LeakyReLU().
- padding : str, optional
- Padding mode for convolution. Default is "same".
- Returns
- -------
- x : tf.Tensor
- Output tensor after convolution, batch norm, and activation.
- """
- if activation is None:
- activation = LeakyReLU()
- x = Conv3D(num_filters, kernel_size, padding=padding)(inputs)
- x = BatchNormalization(fused=False)(x)
- x = Activation(activation)(x)
- return x
- def residual_block(inputs, num_filters):
- """
- Residual 3D convolutional block with skip connection.
- Two convolutions with batch normalization and LeakyReLU activations,
- with a skip connection adding the input to the output.
- Parameters
- ----------
- inputs : tf.Tensor
- Input tensor with number of channels matching num_filters.
- num_filters : int
- Number of convolutional filters.
- Returns
- -------
- x : tf.Tensor
- Output tensor after residual connection.
- """
- x = Conv3D(num_filters, (3, 3, 3), padding="same")(inputs)
- x = BatchNormalization(fused=False)(x)
- x = Activation(LeakyReLU())(x)
- x = Conv3D(num_filters, (3, 3, 3), padding="same")(x)
- x = BatchNormalization(fused=False)(x)
- x = add([x, inputs])
- x = Activation(LeakyReLU())(x)
- return x
- def attention_block(inputs):
- """
- Self-attention block for spatial features.
- Computes scaled dot-product attention over spatial voxels, designed for
- bottleneck feature maps with small spatial dimensions.
- Parameters
- ----------
- inputs : tf.Tensor
- Input feature map.
- Returns
- -------
- output : tf.Tensor
- Output tensor after attention mechanism and skip connection.
- """
- query = Conv3D(filters=inputs.shape[-1] // 8, kernel_size=1)(inputs)
- key = Conv3D(filters=inputs.shape[-1] // 8, kernel_size=1)(inputs)
- value = Conv3D(filters=inputs.shape[-1], kernel_size=1)(inputs)
- attention_weights = tf.nn.softmax(tf.matmul(query, key, transpose_b=True) / tf.sqrt(tf.cast(inputs.shape[-1] // 8, dtype=tf.float32)))
- output = tf.matmul(attention_weights, value)
- output = add([output, inputs])
- return output
- def down_block(inputs, num_filters):
- """
- Encoder block combining convolution and residual connection.
- Parameters
- ----------
- inputs : tf.Tensor
- Input tensor.
- num_filters : int
- Number of convolutional filters.
- Returns
- -------
- x : tf.Tensor
- Output tensor after conv and residual blocks.
- """
- x = conv_block(inputs, num_filters)
- x = residual_block(x, num_filters)
- return x
- def bottleneck_block(inputs, num_filters):
- """
- Bottleneck block with attention.
- Parameters
- ----------
- inputs : tf.Tensor
- Input tensor.
- num_filters : int
- Number of convolutional filters.
- Returns
- -------
- x : tf.Tensor
- Output tensor after conv, attention, and conv blocks.
- """
- x = conv_block(inputs, num_filters)
- x = attention_block(x)
- x = conv_block(x, num_filters)
- return x
- def up_block(inputs, skip_connection, num_filters):
- """
- Decoder block with transposed convolution and skip connection.
- Applies transposed convolution to upsample, concatenates with skip connection,
- and applies conv and residual blocks.
- Parameters
- ----------
- inputs : tf.Tensor
- Input tensor (features from deeper layer).
- skip_connection : tf.Tensor
- Encoder feature map from corresponding down_block.
- num_filters : int
- Number of convolutional filters.
- Returns
- -------
- x : tf.Tensor
- Output tensor after upsampling, concatenation, and residual blocks.
- """
- x = Conv3DTranspose(num_filters, (2, 2, 2), strides=(2, 2, 2), padding="same")(inputs)
- x = concatenate([x, skip_connection], axis=4)
- x = conv_block(x, num_filters)
- x = residual_block(x, num_filters)
- return x
- def covariate_bottleneck_layer(covariate_input, spatial_shape=(4, 4, 4), hidden_units=1024, name="covariate"):
- """
- Project scalar covariates into a 3D spatial feature map.
- Passes the input through dense layers and reshapes the output to match
- the specified spatial dimensions for concatenation with CNN features.
- Parameters
- ----------
- covariate_input : tf.Tensor, shape (batch, 1)
- Scalar covariate value (e.g., plasma, age).
- spatial_shape : tuple of int, optional
- Spatial dimensions of the output feature map. Default is (4, 4, 4).
- hidden_units : int, optional
- Number of units in the hidden dense layer. Default is 1024.
- name : str, optional
- Name prefix for the layers. Default is "covariate".
- Returns
- -------
- x : tf.Tensor, shape (batch, *spatial_shape, 1)
- Reshaped feature map ready for concatenation.
- """
- num_voxels = int(np.prod(spatial_shape))
- if name == "plasma":
- dense1_name, dense2_name = "data1", "data2"
- elif name == "age":
- dense1_name, dense2_name = "data3", "data4"
- else:
- dense1_name, dense2_name = f"{name}_dense1", f"{name}_dense2"
- x = Dense(hidden_units, activation="relu", name=f"{name}_dense1")(covariate_input)
- x = Dense(num_voxels, activation="relu", name=f"{name}_dense2")(x)
- x = Reshape((*spatial_shape, 1), name=f"{name}_reshape")(x)
- return x
- def build_tau_pet_unet(
- image_shape=(72, 90, 76, 1),
- padding=(28, 19, 26),
- encoder_filters=(32, 64, 128, 256, 512),
- bottleneck_filters=1024,
- covariate_shape=(4, 4, 4),
- output_activation=None,
- verbose=False,
- ):
- """
- Build a multimodal 3D U-Net for synthetic tau-PET generation.
- Constructs a U-Net encoder-decoder architecture with residual and attention
- blocks. Takes MRI and scalar covariates (plasma, age) as inputs and outputs
- synthetic tau-PET images. Covariates are projected into 3D bottleneck features
- and concatenated with CNN features.
- Parameters
- ----------
- image_shape : tuple of int, optional
- Input MRI image shape (H, W, D, channels). Default is (72, 90, 76, 1).
- padding : tuple of int, optional
- Zero padding applied to MRI input (H_pad, W_pad, D_pad). Default is (28, 19, 26).
- encoder_filters : tuple of int, optional
- Number of filters at each encoder level. Default is (32, 64, 128, 256, 512).
- bottleneck_filters : int, optional
- Number of filters in the bottleneck. Default is 1024.
- covariate_shape : tuple of int, optional
- Spatial shape of covariate bottleneck features. Default is (4, 4, 4).
- output_activation : keras.layers.Layer or None, optional
- Output activation layer. Default is LeakyReLU().
- verbose : bool, optional
- If True, print model summary. Default is False.
- Returns
- -------
- model : keras.Model
- Compiled U-Net model with inputs [mri, plasma, age] and output tau-PET.
- """
- if output_activation is None:
- output_activation = LeakyReLU()
- mri_input = Input(shape=image_shape, name="mri_input")
- plasma_input = Input(shape=(1,), name="plasma_input")
- age_input = Input(shape=(1,), name="age_input")
- x = ZeroPadding3D(padding=padding)(mri_input)
- skips = []
- for num_filters in encoder_filters:
- x = down_block(x, num_filters)
- skips.append(x)
- x = MaxPooling3D((2, 2, 2))(x)
- x = bottleneck_block(x, bottleneck_filters)
- plasma_features = covariate_bottleneck_layer(
- plasma_input,
- spatial_shape=covariate_shape,
- hidden_units=bottleneck_filters,
- name="plasma",
- )
- age_features = covariate_bottleneck_layer(
- age_input,
- spatial_shape=covariate_shape,
- hidden_units=bottleneck_filters,
- name="age",
- )
- x = concatenate([x, plasma_features], axis=4)
- x = concatenate([x, age_features], axis=4)
- for skip_connection, num_filters in zip(reversed(skips), reversed(encoder_filters)):
- x = up_block(x, skip_connection, num_filters)
- x = Conv3D(
- 1,
- (1, 1, 1),
- activation=output_activation,
- bias_initializer="zeros",
- )(x)
- output = Cropping3D(cropping=padding)(x)
- model = Model(
- inputs=[mri_input, plasma_input, age_input],
- outputs=output,
- name="tau_pet_unet",
- )
- if verbose:
- model.summary()
- return model
unet3d.py at commit 4226694, under CC-BY-NC-4.0 · at the source
Overview
- Clinical Memory Research Unit, Department of Clinical Sciences in Malmö, Lund University, Lund, Sweden
- Memory Clinic, Skåne University Hospital, Malmö, Sweden
- Centre for Mathematical Sciences, Lund University, Lund, Sweden
- C2N Diagnostics LLC, St Louis, MO, USA
- Pharma Research and Early Development, F Hoffmann-La Roche Ltd., Basel, Switzerland
- Eli Lilly and Company, Indianapolis, Indiana, USA
- Department of Neuroscience, University of California, Berkeley, California,USA
- Centre for Studies in the Prevention of Alzheimer’s Disease, Douglas Mental Health Institute, McGill University, Montreal, QC, Canada
- Department of Neurology, Edward and Pearl Fein Memory and Aging Center, Weill Institute for Neurosciences, University of California, San Francisco, California, USA
- Department of Radiology and Biomedical Imaging, Edward and Pearl Fein Memory and Aging Center, Weill Institute for Neurosciences, University of California, San Francisco, California, USA
- Clinical Memory Research Unit, SciLifeLab, Department of Clinical Sciences in Malmö, Lund University, Lund, Sweden
Abstract
Tau protein aggregation in the brain is a hallmark of Alzheimer’s disease (AD). Positron emission tomography (PET) is the only in vivo method to visualize tau pathology and estimate both its burden and regional distribution, but the use of tau-PET is constrained by high cost and limited accessibility. Here, we develop a deep learning model to synthesize tau-PET scans from more accessible data: structural magnetic resonance imaging (MRI), demographics, and when available, blood biomarkers. We included 5,191 participants across the AD continuum or with another neurological disorder from 13 cohorts (mean age 70 years, 51% female) and optimized a 3D U-Net neural network with residual and attention units for this task. In held-out test data, synthetic tau-PET reliably modeled tau burden, with correlations of R=
Reproduced under the paper's license (CC BY), from the paper cited above.
Repository
Its files are read in the Code ↔ Paper reader above, with 7 matches between paragraphs and lines of code.
DeMONLab-BioFINDER/karlsson_synthetic_taupet
4226694b0d3ca9d15e3a427f1f0bc49d0259a05e, 29 June 2026Availability: 1 check, the latest on 28 September 2026: the link answers
- 28 September 2026: the link answers
22 files
- examples/
evaluate_unet.py , Python, 229 lines - examples/
start_unet.sh , Shell, 14 lines - examples/
train_new_unet.py , Python, 182 lines - notebooks/
example_cases_plots.ipyn , Jupyter, 76 linesb - notebooks/
tau_load_plots.ipynb , Jupyter, 98 lines, 1 match - notebooks/
tau_spat_sim_plots.ipynb , Jupyter, 303 lines, 1 match - pretrained_models/
__init__.py , Python, 1 line - pretrained_models/
unet_taupet_v1/ , Python, 1 line__init__.py - pretrained_models/
unet_taupet_v1/ , Python, 148 linesgenerate_multiple_taupet .py - pretrained_models/
unet_taupet_v1/ , Jupyter, 138 linesgenerate_single_taupet.i pynb - pretrained_models/
unet_taupet_v1/ , Python, 186 linesunet3d_v1.py - src/
__init__.py , Python, 1 line - src/
models/ , Python, 1 line__init__.py - src/
models/ , Python, 38 lines, 1 matchloss.py - src/
models/ , Python, 221 lines, 2 matchestrain.py - src/
models/ , Python, 105 linestraining_visualization.p y - src/
models/ , Python, 318 lines, 2 matchesunet3d.py - src/
utils/ , Python, 1 line__init__.py - src/
utils/ , Python, 307 linesimage_helpers.py - src/
utils/ , Python, 48 linesplot_helpers.py - LICENSE, License, 358 lines
- README.md, Text, 125 lines
Code availability
The code and model will be made available at https://
Reproduced under the paper's license (CC BY), from the paper cited above.
Tracing map
Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.
What the map holds:
- 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
- 20 scripts, each with its path and the digest of its content;
- 7 matches between paragraphs of the paper and lines of the code (method lexical-v1);
- neither the text of the paper nor the code itself.
Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.
Data
No dataset and no data link were found in the paper.
Data availability
Participant data from open access cohorts (ADNI, A4, OASIS and PREVENT-AD) can be obtained from http://
Reproduced under the paper's license (CC BY), from the paper cited above.
Versions
The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.
Version 2, 28 September 2026
- Language: n/a → en
- Authors: added Renaud La Joie (0000-0003-2581-8100); removed Renaud La Joie
- Funding: added Michael J. Fox Foundation for Parkinson's Research: MJFF‐025507, 2022-Projekt0107; Alzheimer's Association: ZEN24-1069572, SG-23-1061717; Eli Lilly and Company; Cure Alzheimer's Fund; Australian Government: 2022-Projekt0107, 2022-Projekt0080; GHR Foundation: 2022-00775; Lunds Universitet: AF-980907; Knut och Alice Wallenbergs Stiftelse: KAW 2020.0239, (2022-0231), 2022-Projekt0080, 2022-00775, AF-980907, 2022-1259, FO2021-0293, 2020-O000028, 1412/22, 2020.0239; Vetenskapsrådet: ERAPERMED2021-184, 2024-03642, 2022-00775, 2022-Projekt0080, FO2021-0293, AF-980907, 2018, 1412/22, 2018-02052, 2021-02219, 2020-O000028, 2022-1259; Konung Gustaf V:s och Drottning Victorias Frimurarestiftelse: 2020-O000028, WASP/DDLS22-066; Science for Life Laboratory: KAW 2020.0239; Skånes universitetssjukhus: 2022-1259, 2020-O000028, 2022-Projekt0080; Stiftelsen Bundy Academy; University of California, San Francisco; Parkinsonfonden: 1412/22
Version 1, 28 September 2026: the first record
Recorded: type, journal, dates, 23 authors, 72 references.
Cite
This paper
Karlsson, L., Strandberg, O., Smith, R., Tang, W., Arvidsson, I., Åström, K., Hauer, K. O., Janelidze, S., Stomrud, E., Palmqvist, S., Verghese, P. B., Braunstein, J. B., Alzheimer’s Disease Neuroimaging Initiative, PREVENT-AD Research Group, Klein, G., Shcherbinin, S., Jagust, W. J., Villeneuve, S., La Joie, R., . . . Hansson, O. (2026). Generating synthetic tau-PET scans in Alzheimer’s disease from MRI, blood biomarkers and demographics with deep learning. medRxiv (preprint). https://
BibTeX
@article{karlsson2026gen
author = {Karlsson, Linda and Strandberg, Olof and Smith, Ruben and Tang, Weizhong and Arvidsson, Ida and Åström, Kalle and Hauer, Kevin Oliveira and Janelidze, Shorena and Stomrud, Erik and Palmqvist, Sebastian and Verghese, Philip B. and Braunstein, Joel B. and {Alzheimer’s Disease Neuroimaging Initiative} and {PREVENT-AD Research Group} and Klein, Gregory and Shcherbinin, Sergey and Jagust, William J. and Villeneuve, Sylvia and La Joie, Renaud and Rabinovici, Gil D. and Mattsson-Carlgren, Niklas and Vogel, Jacob W. and Hansson, Oskar},
title = {{Generating synthetic tau-PET scans in Alzheimer’s disease from MRI, blood biomarkers and demographics with deep learning}},
journal = {medRxiv (preprint)},
year = {2026},
month = may,
publisher = {medRxiv},
doi = {10.64898/
url = {https://
}
RIS
TY - JOUR
AU - Karlsson, Linda
AU - Strandberg, Olof
AU - Smith, Ruben
AU - Tang, Weizhong
AU - Arvidsson, Ida
AU - Åström, Kalle
AU - Hauer, Kevin Oliveira
AU - Janelidze, Shorena
AU - Stomrud, Erik
AU - Palmqvist, Sebastian
AU - Verghese, Philip B.
AU - Braunstein, Joel B.
AU - Alzheimer’s Disease Neuroimaging Initiative
AU - PREVENT-AD Research Group
AU - Klein, Gregory
AU - Shcherbinin, Sergey
AU - Jagust, William J.
AU - Villeneuve, Sylvia
AU - La Joie, Renaud
AU - Rabinovici, Gil D.
AU - Mattsson-Carlgren, Niklas
AU - Vogel, Jacob W.
AU - Hansson, Oskar
TI - Generating synthetic tau-PET scans in Alzheimer’s disease from MRI, blood biomarkers and demographics with deep learning
T2 - medRxiv (preprint)
J2 - medRxiv
PY - 2026
DA - 2026/
PB - medRxiv
DO - 10.64898/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.64898/
"type": "article",
"title": "Generating synthetic tau-PET scans in Alzheimer’s disease from MRI, blood biomarkers and demographics with deep learning",
"container-title": "medRxiv (preprint)",
"author": [
{
"family": "Karlsson",
"given": "Linda"
},
{
"family": "Strandberg",
"given": "Olof"
},
{
"family": "Smith",
"given": "Ruben"
},
{
"family": "Tang",
"given": "Weizhong"
},
{
"family": "Arvidsson",
"given": "Ida"
},
{
"family": "Åström",
"given": "Kalle"
},
{
"family": "Hauer",
"given": "Kevin Oliveira"
},
{
"family": "Janelidze",
"given": "Shorena"
},
{
"family": "Stomrud",
"given": "Erik"
},
{
"family": "Palmqvist",
"given": "Sebastian"
},
{
"family": "Verghese",
"given": "Philip B."
},
{
"family": "Braunstein",
"given": "Joel B."
},
{
"literal": "Alzheimer’s Disease Neuroimaging Initiative"
},
{
"literal": "PREVENT-AD Research Group"
},
{
"family": "Klein",
"given": "Gregory"
},
{
"family": "Shcherbinin",
"given": "Sergey"
},
{
"family": "Jagust",
"given": "William J."
},
{
"family": "Villeneuve",
"given": "Sylvia"
},
{
"family": "La Joie",
"given": "Renaud"
},
{
"family": "Rabinovici",
"given": "Gil D."
},
{
"family": "Mattsson-Carlgren",
"given": "Niklas"
},
{
"family": "Vogel",
"given": "Jacob W."
},
{
"family": "Hansson",
"given": "Oskar"
}
],
"container-title-short":
"DOI": "10.64898/
"publisher": "medRxiv",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
5,
7
]
]
}
}
The tracing map gets a citation of its own once an author has validated it and it has a DOI.
Similar papers
The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.
- [1] doi:10.1002/alz.14600 [code]
- Machine learning prediction of tau-PET in Alzheimer's disease using plasma, MRI, and clinical data.Journal: Alzheimer's & dementia : the journal of the Alzheimer's AssociationIn common: seaborn, scikit-learn, pandas, 2 other tools, PET / SPECT, Alzheimer's / dementia, structural MRI / diffusion, 1 other category, 28 references, 2 authors
- [2] doi:10.1038/s41467-025-63564-2 [code]
- Hemispheric asymmetry of tau pathology is related to asymmetric amyloid deposition in Alzheimer's Disease.Journal: Nature communicationsIn common: NiBabel, seaborn, scikit-learn, 4 other tools, PET / SPECT, Alzheimer's / dementia, structural MRI / diffusion, 10 references, 2 authors
- [3] doi:10.1101/2025.04.15.648728 [code]
- Hemispheric Asymmetry of Tau Pathology is Related to Asymmetric Amyloid Deposition in Alzheimer’s DiseaseJournal: bioRxiv (preprint)In common: NiBabel, seaborn, scikit-learn, 4 other tools, PET / SPECT, Alzheimer's / dementia, 10 references, 2 authors
- [4] doi:10.1093/brain/awaf375 [code]
- Reference proteins to improve Core 1 and Core 2 Alzheimer's disease CSF and plasma biomarkers.Journal: Brain : a journal of neurologyIn common: scikit-learn, pandas, Matplotlib, 1 other tool, PET / SPECT, other, Alzheimer's / dementia, 1 other category, 10 references, 2 authors
- [5] doi:10.1038/s44321-025-00348-7 [code]
- Prediction of continuous amyloid positron emission tomography with fluid measures of phosphorylated tau and β-amyloid.Journal: EMBO molecular medicineIn common: seaborn, scikit-learn, pandas, 2 other tools, PET / SPECT, other, Alzheimer's / dementia, 7 references, 2 authors
- [6] doi:10.21203/rs.3.rs-8687892/v1 [code]
- Brain network dynamics determine tau presence while regional vulnerability governs tau load in Alzheimer’s diseaseJournal: Research Square (preprint)In common: seaborn, scikit-learn, pandas, 3 other tools, PET / SPECT, Alzheimer's / dementia, 9 references, author O Hansson
- [7] doi:10.1101/2025.04.17.648358 [code]
- Brain network dynamics determine tau presence while regional vulnerability governs tau load in Alzheimer’s diseaseJournal: bioRxiv (preprint)In common: seaborn, scikit-learn, pandas, 3 other tools, PET / SPECT, Alzheimer's / dementia, 9 references, author O Hansson
- [8] doi:10.1038/s41467-024-47971-5 [code]
- Cerebrospinal fluid reference proteins increase accuracy and interpretability of biomarkers for brain diseases.Journal: Nature communicationsIn common: scikit-learn, pandas, Matplotlib, 1 other tool, Alzheimer's / dementia, 7 references, 2 authors
- [9] doi:10.1007/s00259-026-07868-5 [code]
- Bayesian modelling demonstrates clinically relevant heterogeneity in Tau PET patterns in Alzheimer's disease.Journal: European journal of nuclear medicine and molecular imagingIn common: NiBabel, scikit-learn, SciPy, 2 other tools, PET / SPECT, Alzheimer's / dementia, clinical / translational, 10 references
- [10] doi:10.1002/hbm.70508 [code]
- Cyclic 2.5D Perceptual Loss for Cross-Modal 3D Medical Image Synthesis: T1w MRI to Tau PET.Journal: Human brain mappingIn common: NiBabel, NumPy, PET / SPECT, Alzheimer's / dementia, structural MRI / diffusion, 11 references
Contribute
The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.
Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Validate its tracing map
You validate the map as this page shows it: 1 repository of the authors' code, each at its verified commit and with its license, 20 scripts, and 7 matches between paragraphs and code (see the Code and Map sections). It then receives a DOI on Zenodo, with you (your ORCID iD) and OSCR as its creators; the code itself is not deposited.
The map's fingerprint: sha256:9e15f208a4bfd113…
Add the badge to the code's README
If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.
Markdown
<!-- oscr-badge:start -->
[](https://openscicode.org/badge/doi/10.64898/2026.05.06.26352540)
<!-- oscr-badge:end -->reStructuredText
.. oscr-badge:start
.. image:: https://openscicode.org/badge/doi/10.64898/2026.05.06.26352540.svg
:target: https://openscicode.org/badge/doi/10.64898/2026.05.06.26352540
:alt: OSCR
.. oscr-badge:endHTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.64898/2026.05.06.26352540"><img src="https://openscicode.org/badge/doi/10.64898/2026.05.06.26352540.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->On GitHub, open the README, choose Edit (the pencil), paste the snippet under the title, then "Commit changes".
If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge page.
Request its removal
To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).
Discussion, reproductions, activity
Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.
Report a mismatch between the code and the paper · Report a code error (signed in)
Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.
Report a reproduction failure (signed in)
Versions of its code: the releases of its code tied to a version of this paper (the preprint, the accepted manuscript, the version of record…), each with the tracing map versioned with it.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.
