OSCR

OpenMAP-BrainAge: generalizable and interpretable brain age predictor from MRI.

Code ↔ Paper

7 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 7 matches
  1. [1] § Materials and methods › OpenMAP-BrainAge ↔ run_full_pipeline.py, lines 254–344 · score 0.62 · brain age prediction, OpenMAP T1, parcellation, encoders, model
  2. [2] § Materials and methods › Model training and evaluation ↔ train_ADNI_multiview.py, lines 313–363 · score 0.59 · squared error, absolute error, MSE, MAE, trained, model
  3. [3] § Materials and methods › Dataset ↔ train_ADNI_multiview.py, lines 98–138 · score 0.59 · min max, augmentation, intensity, cropping, resolution, weighted
  4. [4] § Materials and methods › OpenMAP-BrainAge ↔ run_full_pipeline.py, lines 254–344 · score 0.58 · shared image encoder, OpenMAP T1, BrainAge, parcellation, tokens, predicts
  5. [5] § Materials and methods › Model training and evaluation ↔ modelADNI.py, lines 65–144 · score 0.58 · batch normalization, backbone, hidden, MLP, embedding, layer
  6. [6] § Materials and methods › Model training and evaluation ↔ Inference.ipynb, lines 177–244 · score 0.58 · squared error, absolute error, MSE, MAE, prediction, age
  7. [7] § Materials and methods › Model training and evaluation ↔ hpt/models/policy_stem.py, lines 307–321 · score 0.58 · Vision Transformer, patch, ViT, MLP, layer, pretrained

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Python · 348 lines · 11 KB · no license · 2 matches

  1. import argparse
  2. import csv
  3. import subprocess
  4. import sys
  5. from pathlib import Path
  7. import torch
  8. import torchio as tio
  9. from hydra import compose, initialize_config_dir
  11. from dataADNI_multiview import ADNIDataset
  12. from hpt.models.policy import Policy
  13. from modelADNI import ADNIModel
  16. def parse_args():
  17. parser = argparse.ArgumentParser(
  18. description=(
  19. "Run the full OpenMAP-BrainAge inference pipeline: "
  20. "skull removal + rigid registration, 280-region parcellation, "
  21. "demo-style CSV generation, and final brain-age prediction."
  22. )
  23. )
  24. parser.add_argument(
  25. "--input_dir",
  26. required=True,
  27. help="Folder containing raw T1 MRI scans (.nii or .nii.gz).",
  28. )
  29. parser.add_argument(
  30. "--output_dir",
  31. required=True,
  32. help="Folder where all intermediate and final outputs will be written.",
  33. )
  34. parser.add_argument(
  35. "--openmap_t1_model_dir",
  36. required=True,
  37. help="Folder containing the OpenMAP-T1 preprocessing checkpoints.",
  38. )
  39. parser.add_argument(
  40. "--mni_path",
  41. required=True,
  42. help="Path to the MNI template used by skull_removal.py.",
  43. )
  44. parser.add_argument(
  45. "--age_model_checkpoint",
  46. required=True,
  47. help="Path to the trained OpenMAP-BrainAge checkpoint (.pth).",
  48. )
  49. parser.add_argument(
  50. "--device",
  51. default="cuda" if torch.cuda.is_available() else "cpu",
  52. help="Torch device for age prediction. Defaults to cuda if available, else cpu.",
  53. )
  54. parser.add_argument(
  55. "--img_size",
  56. default=(128, 128, 30),
  57. type=int,
  58. nargs=3,
  59. help="Input crop size used by the age model, as in the inference notebook.",
  60. )
  61. parser.add_argument(
  62. "--down_resolution",
  63. default=1,
  64. type=int,
  65. help="Whether to resample to 2mm isotropic before age prediction. 1=true, 0=false.",
  66. )
  67. parser.add_argument(
  68. "--share_image_encoder",
  69. default=1,
  70. type=int,
  71. help="Whether to share the image encoder across views. 1=true, 0=false.",
  72. )
  73. parser.add_argument(
  74. "--use_modality_tokens",
  75. default=0,
  76. type=int,
  77. help="Whether to use modality tokens. Must match the trained checkpoint.",
  78. )
  79. parser.add_argument(
  80. "--domain",
  81. default="mujoco_metaworld",
  82. help="HPT domain prefix used to initialize the pretrained image stem.",
  83. )
  84. return parser.parse_args()
  87. def ensure_exists(path: Path, description: str):
  88. if not path.exists():
  89. raise FileNotFoundError(f"Missing {description}: {path}")
  92. def ensure_openmap_t1_model_files(model_dir: Path):
  93. required_files = [
  94. "CNet/CNet.pth",
  95. "SSNet/SSNet.pth",
  96. "PNet/coronal.pth",
  97. "PNet/sagittal.pth",
  98. "PNet/axial.pth",
  99. "HNet/coronal.pth",
  100. "HNet/axial.pth",
  101. ]
  102. for relative_path in required_files:
  103. ensure_exists(model_dir / relative_path, f"OpenMAP-T1 checkpoint file {relative_path}")
  106. def run_script(command, working_directory: Path):
  107. subprocess.run(command, cwd=working_directory, check=True)
  110. def build_demo_style_csv(skull_removed_dir: Path, parcellation_dir: Path, csv_path: Path):
  111. skull_removed_paths = sorted(skull_removed_dir.glob("*.nii"))
  112. if not skull_removed_paths:
  113. raise FileNotFoundError(
  114. f"No skull-removed .nii files were produced in {skull_removed_dir}"
  115. )
  117. rows = []
  118. for skull_removed_path in skull_removed_paths:
  119. subject_id = skull_removed_path.stem
  120. volume_csv = parcellation_dir / subject_id / f"{subject_id}_volume.csv"
  121. ensure_exists(volume_csv, f"parcellation volume csv for {subject_id}")
  122. rows.append(
  123. {
  124. "path_full": str(skull_removed_path.resolve()),
  125. "age": "",
  126. "path_rigid_parcellation_volume": str(volume_csv.resolve()),
  127. }
  128. )
  130. csv_path.parent.mkdir(parents=True, exist_ok=True)
  131. with csv_path.open("w", newline="") as handle:
  132. writer = csv.DictWriter(
  133. handle,
  134. fieldnames=["path_full", "age", "path_rigid_parcellation_volume"],
  135. )
  136. writer.writeheader()
  137. writer.writerows(rows)
  139. return rows
  142. def build_inference_transform(down_resolution: bool):
  143. return tio.Compose(
  144. [
  145. tio.ToCanonical(),
  146. tio.RescaleIntensity(out_min_max=(0, 1)),
  147. tio.Resample((2, 2, 2), p=1 if down_resolution else 0),
  148. ]
  149. )
  152. def build_age_model(
  153. repo_root: Path,
  154. device: torch.device,
  155. checkpoint_path: Path,
  156. domain: str,
  157. share_image_encoder: bool,
  158. use_modality_tokens: bool,
  159. ):
  160. policy = Policy.from_pretrained("hf://liruiw/hpt-base")
  162. with initialize_config_dir(
  163. version_base="1.2",
  164. config_dir=str((repo_root / "hpt_pretrained_model").resolve()),
  165. ):
  166. cfg = compose(config_name="config_modify", overrides=[])
  168. policy.init_domain_stem(domain, cfg.stem)
  169. policy.finalize_modules()
  171. model = ADNIModel(
  172. trunk=policy.trunk["trunk"],
  173. image_stem=policy.stems[f"{domain}_image"],
  174. image_encoder_depth=18,
  175. image_encoder_pretrained_path=None,
  176. share_image_encoder=share_image_encoder,
  177. state_input_dim=280,
  178. modality_embed_dim=256,
  179. modality_names_types={
  180. "sag": "image",
  181. "cor": "image",
  182. "axi": "image",
  183. "volume": "state",
  184. },
  185. use_modality_tokens=use_modality_tokens,
  186. )
  187. model.to(device)
  189. checkpoint = torch.load(checkpoint_path, map_location="cpu")
  190. model.load_state_dict(checkpoint["model"], strict=False)
  191. model.eval()
  192. return model
  195. def format_model_input(sag, cor, axi, vol, device):
  196. sag = sag.to(device).float().unsqueeze(0)
  197. cor = cor.to(device).float().unsqueeze(0)
  198. axi = axi.to(device).float().unsqueeze(0)
  199. vol = torch.tensor(vol).to(device).float().unsqueeze(0)
  201. return {
  202. "sag": sag.repeat([1, 3, 1, 1, 1]).permute([0, 1, -1, -3, -2]),
  203. "cor": cor.repeat([1, 3, 1, 1, 1]).permute([0, 1, -1, -3, -2]),
  204. "axi": axi.repeat([1, 3, 1, 1, 1]).permute([0, 1, -1, -3, -2]),
  205. "volume": vol,
  206. }
  209. def predict_ages(dataset_csv: Path, output_csv: Path, model, device, img_size, down_resolution):
  210. transform = build_inference_transform(bool(down_resolution))
  211. dataset = ADNIDataset(
  212. str(dataset_csv),
  213. volume=True,
  214. transform=transform,
  215. img_size=img_size,
  216. gt_age=False,
  217. )
  219. predictions = []
  220. with torch.no_grad():
  221. for idx in range(len(dataset)):
  222. sag, cor, axi, vol = dataset[idx]
  223. data = format_model_input(sag, cor, axi, vol, device)
  224. predicted_age = model(data).item()
  226. row = dataset.data.iloc[idx]
  227. predictions.append(
  228. {
  229. "uid": Path(row["path_full"]).stem,
  230. "path_full": row["path_full"],
  231. "age": row.get("age", ""),
  232. "path_rigid_parcellation_volume": row["path_rigid_parcellation_volume"],
  233. "predicted_age": predicted_age,
  234. }
  235. )
  237. with output_csv.open("w", newline="") as handle:
  238. writer = csv.DictWriter(
  239. handle,
  240. fieldnames=[
  241. "uid",
  242. "path_full",
  243. "age",
  244. "path_rigid_parcellation_volume",
  245. "predicted_age",
  246. ],
  247. )
  248. writer.writeheader()
  249. writer.writerows(predictions)
  251. return predictions
  254. def main():
  255. args = parse_args()
  257. repo_root = Path(__file__).resolve().parent
  258. data_processing_dir = repo_root / "data_processing"
  259. output_dir = Path(args.output_dir).resolve()
  260. output_dir.mkdir(parents=True, exist_ok=True)
  262. skull_removed_dir = output_dir / "01_skull_removed"
  263. parcellation_dir = output_dir / "02_parcellation"
  264. metadata_dir = output_dir / "03_metadata"
  265. prediction_dir = output_dir / "04_predictions"
  266. metadata_dir.mkdir(parents=True, exist_ok=True)
  267. prediction_dir.mkdir(parents=True, exist_ok=True)
  269. input_dir = Path(args.input_dir).resolve()
  270. openmap_t1_model_dir = Path(args.openmap_t1_model_dir).resolve()
  271. mni_path = Path(args.mni_path).resolve()
  272. age_model_checkpoint = Path(args.age_model_checkpoint).resolve()
  274. ensure_exists(input_dir, "input directory")
  275. ensure_exists(openmap_t1_model_dir, "OpenMAP-T1 model directory")
  276. ensure_exists(mni_path, "MNI template")
  277. ensure_exists(age_model_checkpoint, "age model checkpoint")
  278. ensure_openmap_t1_model_files(openmap_t1_model_dir)
  280. raw_input_paths = sorted(input_dir.rglob("*.nii")) + sorted(input_dir.rglob("*.nii.gz"))
  281. if not raw_input_paths:
  282. raise FileNotFoundError(f"No .nii or .nii.gz files found under {input_dir}")
  284. print("Step 1/4: skull removal and rigid registration", flush=True)
  285. run_script(
  286. [
  287. sys.executable,
  288. "skull_removal.py",
  289. "-i",
  290. str(input_dir),
  291. "-o",
  292. str(skull_removed_dir),
  293. "-m",
  294. str(openmap_t1_model_dir),
  295. "--MNI_PATH",
  296. str(mni_path),
  297. ],
  298. data_processing_dir,
  299. )
  301. print("Step 2/4: parcellation and volume CSV export", flush=True)
  302. run_script(
  303. [
  304. sys.executable,
  305. "parcellation_from_skull_removed_img.py",
  306. "-i",
  307. str(skull_removed_dir),
  308. "-o",
  309. str(parcellation_dir),
  310. "-m",
  311. str(openmap_t1_model_dir),
  312. ],
  313. data_processing_dir,
  314. )
  316. demo_csv_path = metadata_dir / "full_pipeline_demo_data.csv"
  317. print("Step 3/4: generate demo-style metadata CSV", flush=True)
  318. rows = build_demo_style_csv(skull_removed_dir, parcellation_dir, demo_csv_path)
  319. print(f"Generated metadata CSV for {len(rows)} subjects: {demo_csv_path}", flush=True)
  321. print("Step 4/4: run OpenMAP-BrainAge inference", flush=True)
  322. device = torch.device(args.device)
  323. model = build_age_model(
  324. repo_root=repo_root,
  325. device=device,
  326. checkpoint_path=age_model_checkpoint,
  327. domain=args.domain,
  328. share_image_encoder=bool(args.share_image_encoder),
  329. use_modality_tokens=bool(args.use_modality_tokens),
  330. )
  332. predictions_csv = prediction_dir / "age_predictions.csv"
  333. predictions = predict_ages(
  334. dataset_csv=demo_csv_path,
  335. output_csv=predictions_csv,
  336. model=model,
  337. device=device,
  338. img_size=tuple(args.img_size),
  339. down_resolution=args.down_resolution,
  340. )
  342. print(f"Wrote {len(predictions)} predictions to {predictions_csv}", flush=True)
  343. for prediction in predictions:
  344. print(f"{prediction['uid']}: {prediction['predicted_age']:.4f}", flush=True)
  347. if __name__ == "__main__":
  348. main()

run_full_pipeline.py at commit a998e96, no license · at the source

Overview

Authors: Pengyu Kan1, Craig Jones1, Kenichi Oishi2,3, Alzheimer’s Disease Neuroimaging Initiative and the Australian Imaging Biomarkers and Lifestyle Flagship Study of Aging
ORCID iDs: Pengyu Kan, Craig Jones, Kenichi Oishi
  1. Department of Computer Science, Johns Hopkins University, Baltimore, MD, United States
  2. The Russell H. Morgan Department of Radiology and Radiological Science, The Johns Hopkins University School of Medicine, Baltimore, MD 21205, United States
  3. Department of Neurology, The Johns Hopkins University School of Medicine, Baltimore, MD, United States
Institutions: Johns Hopkins University (United States); Johns Hopkins Medicine (United States)
Journal: Radiology advances, volume 3, issue 4, article umag025
Dates: received 17 July 2025; accepted 16 April 2026; published online 29 May 2026
Type: Research article · Language: English
License: CC BY-NC
Identifiers: DOI 10.1093/radadv/umag025 · PMID 42482983 · PMCID PMC13387714 · OpenAlex W7162767077
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: structural MRI / diffusion (modality), human (organism), Alzheimer's / dementia (population)
Methods: Connectivity, Statistics, Machine learning
Keywords: brain age prediction, deep learning, transformer, neurodegeneration, dementia
Topic: Dementia and Cognitive Impairment Research (Psychiatry and Mental health, Medicine), according to OpenAlex
Funding: NIA NIH HHS (P01 AG026276, U01 AG024904, P01 AG003991, R01 AG043434, P30 AG066444); NCATS NIH HHS (UL1 TR000448); NIBIB NIH HHS (R01 EB009352)
Citations: not cited yet (Europe PMC); 35 references in the paper

Abstract

Background: Accurately estimating brain age can help identify deviations linked to neurodegenerative diseases, underscoring the need for robust models that accurately perform across heterogenous cohorts.

Purpose: To develop an age prediction model that is interpretable and robust to demographic and technological variations in brain MRI.

Materials and Methods: We propose a transformer-based brain age model that analyzes 3D T1-weighted MRI. Model performance was assessed using mean absolute error (MAE). Associations between brain age gap (BAG, ie, predicted minus chronological age) and chronological age were evaluated in cognitive normal (CN) participants. Clinical relevance was assessed by examining BAG differences across cognitive groups and correlations with Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA).

Results: We achieved an MAE 3.65 years on ADNI2 & 3 and OASIS3 test sets, and a high generalizability of MAE of 3.54 years on AIBL. In dementia, a notable increase in brain age gap (BAG) along with cognitive decline, with a mean of 0.15 years (95% CI: [−0.22, 0.51]) in CN, 2.55 years ([2.40, 2.70]) in mild cognitive impairment (MCI), and 6.12 years ([5.82, 6.43]) is noted. Negative correlation between BAG and cognitive scores was observed after adjustment for covariates, with r = −0.397 (P < 0.001) for MMSE and −0.393 (P < 0.001) for MoCA, where declining scores generally signify worsening cognitive performance. The saliency map highlighted white and deep gray matter structures as key regions influenced by brain aging.

Conclusion: Our model effectively integrated multiview and volumetric information to achieve state-of-the-art brain age prediction, with improved generalizability, interpretability, and association with cognitive function.

Reproduced under the paper's license (CC BY-NC), 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.

OishiLab/OpenMAP-BrainAge

License: none: the authors keep all their rights
State: the link answers, verified on 28 September 2026
Evidence: files inventoried
Commit: a998e9666808e4e95880f581c41f02b741355fe1, 26 May 2026
Languages: Python (39), Jupyter (1), Shell (1)
Size: 62 files, 41 scripts
Software Heritage: not archived
Found in: the text, “OpenMAP-BrainAge”
Holds: README, environment (environment.yml), 1 notebook
Not found: license file, CITATION.cff, tests, continuous integration, documentation
Tools: PyTorch (33 files), NumPy (24 files), SciPy (5 files), OpenCV (4 files), NiBabel (3 files), Matplotlib (2 files), pandas (2 files), ANTs (1 file), Numba (1 file), Pillow (1 file), SimpleITK (1 file), Hugging Face Transformers (1 file)
Availability: 1 check, the latest on 28 September 2026: the link answers
  • 28 September 2026: the link answers
42 files
At the source: github.com/OishiLab/OpenMAP-BrainAge

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;
  • 41 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

Data used in preparation of this article were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf

Data used in the preparation of this article was obtained from the Australian Imaging Biomarkers and Lifestyle flagship study of ageing (AIBL) funded by the Commonwealth Scientific and Industrial Research Organisation (CSIRO) which was made available at the ADNI database (www.loni.usc.edu/ADNI). The AIBL researchers contributed data but did not participate in analysis or writing of this report. AIBL researchers are listed at data.aibl.org.au/adni/.

Reproduced under the paper's license (CC BY-NC), 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 1, 28 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 5 keywords, 3 funders, 23 references.

Cite

This paper

Kan, P., Jones, C., Oishi, K., & Alzheimer’s Disease Neuroimaging Initiative and the Australian Imaging Biomarkers and Lifestyle Flagship Study of Aging. (2026). OpenMAP-BrainAge: generalizable and interpretable brain age predictor from MRI. Radiology advances, 3(4), umag025. https://doi.org/10.1093/radadv/umag025

BibTeX

@article{kan2026openmap,
author = {Kan, Pengyu and Jones, Craig and Oishi, Kenichi and {Alzheimer’s Disease Neuroimaging Initiative and the Australian Imaging Biomarkers and Lifestyle Flagship Study of Aging}},
title = {{OpenMAP-BrainAge: generalizable and interpretable brain age predictor from MRI}},
journal = {Radiology advances},
year = {2026},
month = may,
volume = {3},
number = {4},
pages = {umag025},
publisher = {Oxford University Press},
issn = {2976-9337},
doi = {10.1093/radadv/umag025},
url = {https://doi.org/10.1093/radadv/umag025},
pmid = {42482983},
pmcid = {PMC13387714}
}

RIS

TY - JOUR
AU - Kan, Pengyu
AU - Jones, Craig
AU - Oishi, Kenichi
AU - Alzheimer’s Disease Neuroimaging Initiative and the Australian Imaging Biomarkers and Lifestyle Flagship Study of Aging
TI - OpenMAP-BrainAge: generalizable and interpretable brain age predictor from MRI
T2 - Radiology advances
J2 - Radiol Adv
PY - 2026
DA - 2026/05/29
VL - 3
IS - 4
SP - umag025
SN - 2976-9337
PB - Oxford University Press
DO - 10.1093/radadv/umag025
UR - https://doi.org/10.1093/radadv/umag025
LA - en
ER -

CSL-JSON

{
"id": "10.1093/radadv/umag025",
"type": "article-journal",
"title": "OpenMAP-BrainAge: generalizable and interpretable brain age predictor from MRI",
"container-title": "Radiology advances",
"author": [
{
"family": "Kan",
"given": "Pengyu"
},
{
"family": "Jones",
"given": "Craig"
},
{
"family": "Oishi",
"given": "Kenichi"
},
{
"literal": "Alzheimer’s Disease Neuroimaging Initiative and the Australian Imaging Biomarkers and Lifestyle Flagship Study of Aging"
}
],
"container-title-short": "Radiol Adv",
"volume": "3",
"issue": "4",
"page": "umag025",
"DOI": "10.1093/radadv/umag025",
"PMID": "42482983",
"PMCID": "PMC13387714",
"ISSN": "2976-9337",
"publisher": "Oxford University Press",
"URL": "https://doi.org/10.1093/radadv/umag025",
"language": "en",
"issued": {
"date-parts": [
[
2026,
5,
29
]
]
}
}

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:10.1162/imag.a.1164 [code]
Bias and generalizability of brain age prediction models: A multi-cohort evaluation with anatomical and interpretability insights.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: ANTs, Pillow, NiBabel, 5 other tools, Alzheimer's / dementia, structural MRI / diffusion, 3 references
[2] doi:10.1002/alz.71649 [code]
Postmortem brain MRI reveals differential associations of subcortical and limbic volumes with cortical thinning and neurodegenerative pathologies.
Journal: Alzheimer's & dementia : the journal of the Alzheimer's Association
In common: SimpleITK, ANTs, OpenCV, 7 other tools, Alzheimer's / dementia, structural MRI / diffusion
[3] doi:10.1162/imag.a.1326 [code]
RAVEN: Robust, generalizable, multi-resolution structural MRI upsampling using autoencoders.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: Hugging Face Transformers, SimpleITK, OpenCV, 7 other tools, structural MRI / diffusion
[4] doi:10.1111/joa.70203 [code]
Two-step workflow integrating automatic registration and manual refinement for the accurate alignment of serial histological sections in 3D reconstruction.
Journal: Journal of anatomy
In common: Hugging Face Transformers, SimpleITK, OpenCV, 7 other tools
[5] doi:10.1016/j.patter.2026.101538 [code]
A multi-modal foundation model for brain disease diagnosis and medical imaging.
Journal: Patterns (New York, N.Y.)
In common: Hugging Face Transformers, OpenCV, Pillow, 6 other tools, 1 reference
[6] doi:10.1038/s41467-026-73373-w [code]
Mapping neuro-vascular unit communications reveals distinct angiogenic programs across developing mouse brain regions.
Journal: Nature communications
In common: SimpleITK, ANTs, OpenCV, 7 other tools
[7] doi:10.1016/j.crmeth.2026.101473 [code]
AmygdalaGo-BOLT for boundary-aware segmentation of the human amygdala.
Journal: Cell reports methods
In common: SimpleITK, ANTs, OpenCV, 6 other tools, structural MRI / diffusion
[8] doi:10.1038/s43856-026-01722-3 [code]
Local and global patterns support medical imaging as a biomarker of ageing.
Journal: Communications medicine
In common: SimpleITK, NiBabel, PyTorch, 4 other tools, 3 references
[9] doi:10.1162/imag.a.1352 [code]
Brain-age in ultra-low-field MRI: How well does it work?
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: ANTs, NiBabel, PyTorch, 3 other tools, structural MRI / diffusion, 3 references
[10] doi:10.1038/s41467-026-76011-7 [code]
Human cortex organizes dynamic co-fluctuations along the sensorimotor-association axis.
Journal: Nature communications
In common: SimpleITK, ANTs, OpenCV, 6 other tools

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.

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: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.