OSCR

BraMARS: An Interpretable Histopathology-Driven Deep Learning Model for Brain Metastasis Risk Stratification in Surgically Resected Limited-Stage SCLC.

Code ↔ Paper

3 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 3 matches
  1. [1] § Materials and Methods › Implementation Details ↔ train.py, lines 144–267 · score 0.90 · cosine annealing, AdamW, BCEWithLogitsLoss, weight decay, schedule, optimization
  2. [2] § Results › Performance of BraMARS for BM Risk Prediction ↔ train.py, lines 144–267 · score 0.62 · internal validation, external validation, AUC, trained, curve, threshold
  3. [3] § Materials and Methods › Feature Encoding With S4 ↔ S4MIL.py, lines 94–142 · score 0.59 · state space, FFT, convolutions, Kernel, S4D, SSM

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 · 284 lines · 12 KB · no license · 2 matches

  1. import torch
  2. import sys
  3. import numpy as np
  4. import os
  5. import pandas as pd
  6. from datasets import FeatureDataset
  7. from torch.optim.lr_scheduler import CosineAnnealingLR
  8. import warnings
  9. import random
  10. from torch.utils.data import DataLoader
  11. from torch import nn
  12. from pathlib import Path
  13. from tqdm import tqdm
  14. from warmup_scheduler import GradualWarmupScheduler
  15. import torch.backends.cudnn as cudnn
  16. from sklearn.metrics import roc_auc_score, roc_curve
  17. import argparse
  18. from sklearn.model_selection import StratifiedKFold
  19. from lifelines.statistics import multivariate_logrank_test
  20. from lifelines import CoxPHFitter
  21. import lifelines
  22. from S4MIL import S4Model
  24. warnings.filterwarnings("ignore")
  25. os.environ['CUDA_VISIBLE_DEVICES'] = '0'
  28. def calculate_acc(data_loader):
  29. pred_list = data_loader['PREDS'].tolist()
  30. label_list = data_loader['LABELS'].tolist()
  31. acc = 0
  32. for idx_ in range(len(pred_list)):
  33. if pred_list[idx_] == label_list[idx_]:
  34. acc += 1
  35. acc = acc / len(pred_list)
  36. return acc
  39. def setup_seed(seed):
  40. torch.manual_seed(seed)
  41. os.environ['PYTHONHASHSEED'] = str(seed)
  42. torch.cuda.manual_seed_all(seed)
  43. torch.cuda.manual_seed(seed)
  44. np.random.seed(seed)
  45. random.seed(seed)
  46. cudnn.deterministic = True
  47. cudnn.benchmark = False
  48. cudnn.enabled = False
  51. def get_args(lr, wd):
  52. parser = argparse.ArgumentParser(description='BM invasion prediction')
  53. parser.add_argument('--workers', default=4, type=int, metavar='N',
  54. help='number of data loader workers')
  55. parser.add_argument('--epochs', default=200, type=int, metavar='N',
  56. help='number of total epochs to run')
  57. parser.add_argument('--batch_size', default=64, type=int, metavar='N',
  58. help='mini-batch size')
  59. parser.add_argument('--checkpoint-dir', default='', type=Path,
  60. metavar='DIR', help='path to checkpoint directory')
  61. parser.add_argument('--lr', default=lr)
  62. parser.add_argument('--wd', default=wd)
  63. parser.add_argument('--T_max', default=10)
  64. args = parser.parse_args()
  65. return args
  68. def calculate_metrics(model, data_loader, thresholds):
  69. with torch.no_grad():
  70. sigmoid = nn.Sigmoid()
  71. data = pd.DataFrame()
  72. model.eval()
  73. score = np.array([])
  74. label = []
  75. slides = []
  76. for step, (slide, slide_property) in enumerate(data_loader):
  77. slide = slide.cuda()
  78. slides = slides + slide_property['slide_name']
  79. pred_ = model(slide)
  80. score = np.append(score, (sigmoid(pred_).detach().cpu().numpy()))
  81. label = label + list(slide_property['label'].detach().cpu().numpy())
  83. auc = roc_auc_score(label, score)
  84. dfs_ = []
  85. os_ = []
  86. dfs_state = []
  87. os_tate = []
  88. for ik in slides:
  89. dfs_.append(dfs_os[ik]['DFS'])
  90. os_.append(dfs_os[ik]['OS'])
  91. dfs_state.append(dfs_os[ik]['DFS State'])
  92. os_tate.append(dfs_os[ik]['OS State'])
  94. preds = (score > thresholds).astype(float)
  95. Surival_Data = pd.DataFrame()
  96. Surival_Data['DFS'] = dfs_
  97. Surival_Data['Label'] = preds
  98. Surival_Data['DFS State'] = dfs_state
  99. Surival_Data['OS'] = os_
  100. Surival_Data['OS State'] = os_tate
  102. ##
  103. result0 = multivariate_logrank_test(Surival_Data['DFS'], Surival_Data['Label'], Surival_Data['DFS State'])
  104. logrank_p0_2ways = result0.p_value
  105. Surival_Data_High_Lows = Surival_Data.dropna(axis=0)
  106. try:
  107. cph = CoxPHFitter()
  108. cph.fit(Surival_Data_High_Lows[['DFS', 'DFS State', 'Label']], 'DFS', event_col='DFS State')
  109. except lifelines.exceptions.ConvergenceError:
  110. hr_values = 100
  112. data['SLIDES'] = list(slides)
  113. data['LABELS'] = list(label)
  114. data['SCORES'] = list(score)
  115. data['PREDS'] = list(preds)
  117. return auc, data, logrank_p0_2ways
  120. def collatte_fn(batch):
  121. max_len = max(len(features) for features, slide in batch)
  122. batch_features = []
  123. batch_labels = []
  124. batch_name = []
  126. for features, slide in batch:
  127. padded_features = torch.zeros((max_len, 768), dtype=torch.float32)
  128. padded_features[:len(features), :] = features
  129. name = slide['slide_name']
  130. label = slide['label']
  132. batch_features.append(padded_features)
  133. batch_labels.append(label)
  134. batch_name.append(name)
  136. batch_features = torch.stack(batch_features)
  137. slide_property = {}
  138. slide_property['slide_name'] = batch_name
  139. slide_property['label'] = torch.tensor(batch_labels)
  141. return batch_features, slide_property
  144. def train(lr, wd, warmup, seed):
  145. args = get_args(lr, wd)
  146. seed = seed
  147. setup_seed(seed)
  149. args.checkpoint_dir.mkdir(parents=True, exist_ok=True)
  150. '''读取数据集路径和构建dataloader'''
  151. # External validation set
  152. External_val_root = '' # External_val特征存放地址
  153. External_val_csv = pd.read_csv('') # 需要用到的External_val患者数据
  154. External_val_path = []
  155. External_val_label_path = []
  156. for i in range(len(External_val_csv)):
  157. External_val_path.append(External_val_root + str(External_val_csv['Name'][i]))
  158. External_val_label_path.append(External_val_csv['Label'][i])
  159. data_External_val = FeatureDataset(External_val_path, External_val_label_path, mode='test')
  160. data_External_val_loader = DataLoader(data_External_val, batch_size=1, shuffle=True, collate_fn=collatte_fn)
  161. # Train set and Internal validation set
  162. label_csv = pd.read_csv('') # 需要用到的Train_set患者数据
  163. root = '' # Train_set特征存放地址
  164. list_train_path = []
  165. label_train = []
  166. for i in range(len(label_csv)):
  167. list_train_path.append(root + str(label_csv['Name'][i]))
  168. label_train.append(label_csv['Label'][i])
  170. setup_seed(seed)
  171. skf = StratifiedKFold(n_splits=3, shuffle=True, random_state=seed)
  172. a, b, c = enumerate(skf.split(list_train_path, label_train))
  173. train_idx, val_idx = b[1][0], b[1][1]
  174. setup_seed(seed)
  175. fold_train, fold_val = [list_train_path[i] for i in train_idx], [list_train_path[i] for i in val_idx]
  176. fold_train_label, fold_val_label = [label_train[i] for i in train_idx], [label_train[i] for i in val_idx]
  178. model = S4Model(in_dim=768, n_classes=1, act='gelu', dropout=0).cuda()
  180. l_bce = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([6]).cuda())
  181. optimizer = torch.optim.AdamW(model.parameters(), lr=args.lr, weight_decay=args.wd)
  182. scheduler = CosineAnnealingLR(optimizer, T_max=args.epochs - warmup)
  183. scheduler = GradualWarmupScheduler(optimizer, multiplier=1, total_epoch=warmup, after_scheduler=scheduler)
  184. data_train = FeatureDataset(fold_train, fold_train_label, mode='train')
  185. data_train_loader = torch.utils.data.DataLoader(data_train, batch_size=1, shuffle=True, collate_fn=collatte_fn)
  186. data_validation = FeatureDataset(fold_val, fold_val_label, mode='val')
  187. data_validation_loader = torch.utils.data.DataLoader(data_validation, batch_size=1, shuffle=False,
  188. collate_fn=collatte_fn)
  190. early_stop = 0
  191. auc_validation = 0
  192. epoch_validation = 0
  193. m = t = 0
  194. for epoch in range(args.epochs):
  195. early_stop = early_stop + 1
  196. if early_stop > 20:
  197. print('Early stop!')
  198. break
  199. LOSS = []
  200. score_ = np.array([])
  201. LABEL_ = []
  202. model.train()
  203. progress_bar = tqdm(total=len(data_train_loader), desc=" BM_invasion training")
  204. for step, (slide, slide_property) in enumerate(data_train_loader, start=epoch * len(data_train_loader)):
  205. optimizer.zero_grad()
  206. slide = slide.cuda()
  207. label = slide_property['label'].cuda().to(torch.float64)
  208. pred = model(slide)
  209. pred = pred.reshape(-1)
  210. sigmoid = nn.Sigmoid()
  211. score_ = np.append(score_, (sigmoid(pred).detach().cpu().numpy()))
  212. LABEL_ = LABEL_ + list(slide_property['label'].detach().cpu().numpy())
  213. loss1 = l_bce(pred, label)
  214. loss = loss1
  215. loss.backward()
  216. LOSS.append(loss.item())
  217. optimizer.step()
  218. progress_bar.update()
  220. progress_bar.close()
  221. train_auc = roc_auc_score(LABEL_, score_)
  222. fpr, tpr, thresholds = roc_curve(LABEL_, score_)
  224. for idx in range(len(thresholds)):
  225. if tpr[idx] - fpr[idx] > m:
  226. m = abs(-fpr[idx] + tpr[idx])
  227. t = thresholds[idx]
  229. print(f'thresholds:{t}')
  231. train_acc_list = (score_ > t).astype(float)
  232. acc_sum = 0
  233. for q in range(len(train_acc_list)):
  234. if train_acc_list[q] == LABEL_[q]:
  235. acc_sum += 1
  236. train_acc = acc_sum / len(train_acc_list)
  237. auc_validation_, data_validation, p_value = calculate_metrics(model, data_validation_loader, t)
  239. if auc_validation_ > auc_validation:
  240. auc_validation = auc_validation_
  241. epoch_validation = epoch
  242. early_stop = 0
  243. state = dict(epoch=epoch + 1, model=model.state_dict(), optimizer=optimizer.state_dict(), threshold=t)
  244. torch.save(state, args.checkpoint_dir / 'checkpoint_max_validation_auc.pth')
  245. data_validation.to_csv(args.checkpoint_dir / 'temp_report_validation.csv')
  246. print('Epoch: ' + str(epoch) + ' loss: ' + str(np.mean(LOSS)))
  247. print(f'Epoch: {epoch} train AUC: {train_auc} train ACC: {train_acc}')
  248. print(f'Epoch: {epoch} validation AUC: {auc_validation_} validation P: {p_value}')
  249. print(f'Current best validation AUC: {auc_validation} at epoch {epoch_validation}')
  250. auc_External_val, data_External_val, p_External_val = calculate_metrics(model, data_External_val_loader, t)
  251. print(f'Epoch: {epoch}, External_val AUC: {auc_External_val}, External_val P: {p_External_val}')
  252. print('-------------------------------------------------------------------------------------------')
  253. scheduler.step()
  255. model = S4Model(in_dim=768, n_classes=1, act='gelu', dropout=0).cuda()
  257. ckpt = torch.load(args.checkpoint_dir / f'checkpoint_max_validation_auc.pth', map_location='cuda:0')
  258. model.load_state_dict(ckpt['model'])
  259. auc_validation, data_validation, p_validation = calculate_metrics(model, data_validation_loader, ckpt['threshold'])
  260. auc_External_val, data_External_val, p_External_val = calculate_metrics(model, data_External_val_loader,
  261. ckpt['threshold'])
  262. th = ckpt['threshold']
  264. print(f'Epoch: {epoch} Validation AUC: {auc_validation}, External_val AUC: {auc_External_val}, threshold: {th}')
  265. data_validation.to_csv(args.checkpoint_dir / f'seed={seed}/temp_report_validation.csv')
  266. data_External_val.to_csv(args.checkpoint_dir / f'seed={seed}/temp_report_External_val.csv')
  267. print('Finish!')
  270. if __name__ == '__main__':
  271. survival = pd.read_csv('') # 患者临床信息
  272. dfs_os = {}
  273. for i in range(survival.shape[0]):
  274. row_data = survival.loc[i]
  275. dfs_os[str(row_data['Name'])] = row_data
  277. lrs = 1e-5
  278. wds = 1e-4
  279. warmups = 40
  280. seeds = 9197
  281. sys.stdout = open('log_root', 'w') # 日志存放地址
  282. print(f'lr {lrs}, wd {wds} , warmup {warmups} , seed {seeds} begin')
  283. train(lrs, wds, warmups, seeds)
  284. sys.stdout.close()

train.py at commit 14fc0c7, no license · at the source

Overview

Authors: Zijian Yang1, Taolue Wang1, Shilong Liu2, Zicheng Zhang1, Yibo Zhang1, Fan Yang3, Bo Yu4, Shuaishuai Gao1, Yu Chen1, Lin Yang3, Meng Zhou1
ORCID iDs: Shilong Liu, Yibo Zhang, Bo Yu, Meng Zhou
  1. Institute of Genomic Medicine School of Biomedical Engineering Wenzhou Medical University Wenzhou People's Republic of China
  2. Department of Thoracic Radiation Oncology Harbin Medical University Cancer Hospital Harbin People's Republic of China
  3. Department of Pathology National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing People's Republic of China
  4. AMG Nephrology Avera McKennan Hospital Sioux Falls South Dakota USA
Institutions: Wenzhou Medical University (China); Third Affiliated Hospital of Harbin Medical University (China); Chinese Academy of Medical Sciences & Peking Union Medical College (China); Cancer Hospital of Chinese Academy of Medical Sciences (China); Avera McKennan Hospital & University Health Center (United States)
Journal: Advanced science (Weinheim, Baden-Wurttemberg, Germany), article e77075
Dates: received 20 January 2026; accepted 31 July 2026; published online 14 August 2026; in print August 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1002/advs.77075 · PMID 42598747 · PMCID PMC13474182 · OpenAlex W7203499714
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: histology / microscopy (modality), human (organism), other condition (population), clinical / translational (subfield)
Methods: Statistics, Spectral & time-frequency, Connectivity, Machine learning
Keywords: brain metastasis, deep learning, prophylactic cranial irradiation, small cell lung cancer
Topic: Lung Cancer Research Studies (Oncology, Medicine), according to OpenAlex
Funding: CAMS Innovation Fund for Medical Sciences (CIFMS 2024‐I2M‐C&T‐A‐005); National High Level Hospital Clinical Research Funding (LC2024L01)
Citations: not cited yet (Europe PMC); 43 references in the paper

Abstract

Brain metastasis (BM) is a major cause of mortality in limited‐stage small‐cell lung cancer (LS‐SCLC). Prophylactic cranial irradiation (PCI) reduces BM incidence but carries neurotoxicity and lacks individualized risk assessment. Here, we developed BraMARS, an explainable deep learning model that estimates future BM risk from routine H&E‐stained whole‐slide images of resected LS‐SCLC. BraMARS demonstrates robust discriminatory performance across independent cohorts, with AUCs ranging from 0.738 to 0.944, and stratifies patients into high‐risk and low‐risk groups with significantly different disease‐free survival, overall survival, and brain metastasis‐free survival. Retrospective simulation shows BraMARS‐guided risk stratification could reduce PCI exposure in 19.3% of low‐risk predicted patients while improving identification of high‐risk‐predicted patients by 84.4%. Histopathologic attribution and proteomic analyses linked higher scores to distinct tissue patterns and programs involving mitochondrial metabolism, reactive‐oxygen‐species detoxification, and DNA repair. Overall, BraMARS provides a biologically interpretable histopathology‐based framework for estimating subsequent BM risk in resected LS‐SCLC, with potential to support individualized intracranial risk assessment, intensified MRI surveillance, and hypothesis generation for prospective BM‐prevention strategies.

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 3 matches between paragraphs and lines of code.

ZhoulabCPH/BraMARS

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 14fc0c761c03ae2cc94f875ead8d67da15b6f956, 2 December 2025
Languages: Python (7)
Size: 10 files, 7 scripts
Software Heritage: not archived
Found in: “Code Availability Statement”
Holds: README, environment (requirements.txt)
Not found: license file, CITATION.cff, tests, continuous integration, documentation
Tools: PyTorch (6 files), NumPy (3 files), pandas (2 files), Pillow (1 file), scikit-learn (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
8 files
At the source: github.com/ZhoulabCPH/BraMARS

Code Availability Statement

The code of this work is available at https://github.com/ZhoulabCPH/BraMARS.

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;
  • 7 scripts, each with its path and the digest of its content;
  • 3 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

Datasets cited

Data Availability Statement

The whole‐slide histopathology images and associated clinical data generated and analyzed during this study are not publicly available due to patient privacy concerns and institutional data protection policies. These data may be made available to qualified researchers for non‐commercial research purposes upon reasonable request to the corresponding author, Dr. Lin Yang and Dr. Shilong Liu, subject to institutional data transfer agreement and ethical approval. The mass spectrometry proteomics data have been deposited in the OMIX database (https://ngdc.cncb.ac.cn/omix/) under accession code OMIX007230.

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 1, 27 September 2026: the first record

Recorded: type, language, journal, pages, dates, 11 authors, 4 keywords, 2 funders, 41 references.

Cite

This paper

Yang, Z., Wang, T., Liu, S., Zhang, Z., Zhang, Y., Yang, F., Yu, B., Gao, S., Chen, Y., Yang, L., & Zhou, M. (2026). BraMARS: An Interpretable Histopathology-Driven Deep Learning Model for Brain Metastasis Risk Stratification in Surgically Resected Limited-Stage SCLC. Advanced science (Weinheim, Baden-Wurttemberg, Germany), e77075. https://doi.org/10.1002/advs.77075

BibTeX

@article{yang2026bramars,
author = {Yang, Zijian and Wang, Taolue and Liu, Shilong and Zhang, Zicheng and Zhang, Yibo and Yang, Fan and Yu, Bo and Gao, Shuaishuai and Chen, Yu and Yang, Lin and Zhou, Meng},
title = {{BraMARS: An Interpretable Histopathology-Driven Deep Learning Model for Brain Metastasis Risk Stratification in Surgically Resected Limited-Stage SCLC}},
journal = {Advanced science (Weinheim, Baden-Wurttemberg, Germany)},
year = {2026},
month = aug,
pages = {e77075},
publisher = {Wiley},
issn = {2198-3844},
doi = {10.1002/advs.77075},
url = {https://doi.org/10.1002/advs.77075},
pmid = {42598747},
pmcid = {PMC13474182}
}

RIS

TY - JOUR
AU - Yang, Zijian
AU - Wang, Taolue
AU - Liu, Shilong
AU - Zhang, Zicheng
AU - Zhang, Yibo
AU - Yang, Fan
AU - Yu, Bo
AU - Gao, Shuaishuai
AU - Chen, Yu
AU - Yang, Lin
AU - Zhou, Meng
TI - BraMARS: An Interpretable Histopathology-Driven Deep Learning Model for Brain Metastasis Risk Stratification in Surgically Resected Limited-Stage SCLC
T2 - Advanced science (Weinheim, Baden-Wurttemberg, Germany)
J2 - Adv Sci (Weinh)
PY - 2026
DA - 2026/08/14
SP - e77075
SN - 2198-3844
PB - Wiley
DO - 10.1002/advs.77075
UR - https://doi.org/10.1002/advs.77075
LA - en
ER -

CSL-JSON

{
"id": "10.1002/advs.77075",
"type": "article-journal",
"title": "BraMARS: An Interpretable Histopathology-Driven Deep Learning Model for Brain Metastasis Risk Stratification in Surgically Resected Limited-Stage SCLC",
"container-title": "Advanced science (Weinheim, Baden-Wurttemberg, Germany)",
"author": [
{
"family": "Yang",
"given": "Zijian"
},
{
"family": "Wang",
"given": "Taolue"
},
{
"family": "Liu",
"given": "Shilong"
},
{
"family": "Zhang",
"given": "Zicheng"
},
{
"family": "Zhang",
"given": "Yibo"
},
{
"family": "Yang",
"given": "Fan"
},
{
"family": "Yu",
"given": "Bo"
},
{
"family": "Gao",
"given": "Shuaishuai"
},
{
"family": "Chen",
"given": "Yu"
},
{
"family": "Yang",
"given": "Lin"
},
{
"family": "Zhou",
"given": "Meng"
}
],
"container-title-short": "Adv Sci (Weinh)",
"page": "e77075",
"DOI": "10.1002/advs.77075",
"PMID": "42598747",
"PMCID": "PMC13474182",
"ISSN": "2198-3844",
"publisher": "Wiley",
"URL": "https://doi.org/10.1002/advs.77075",
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
14
]
]
}
}

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:10.1186/s11658-026-00957-1
Lactate-activated astrocytes promote NSCLC brain metastasis through extracellular vesicle-mediated miR-8085/TRIM67/ELK1 signaling axis.
Journal: Cellular & molecular biology letters
In common: ngdc.cncb.ac.cn/omix, other condition, 2 references
[2] doi:10.1002/cnr2.70625 [code]
Machine Learning-Based Prediction of Brain Metastasis at Initial Diagnosis in Small-Cell Lung Cancer: Model Development and SHAP Interpretation Study.
Journal: Cancer reports (Hoboken, N.J.)
In common: clinical / translational, other condition, 3 references
[3] doi:10.1038/s41598-026-61605-4 [code]
Learning precise segmentation of neurofibrillary tangles from rapid manual point annotations.
Journal: Scientific reports
In common: Pillow, PyTorch, scikit-learn, 2 other tools, histology / microscopy, other condition
[4] 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: Pillow, PyTorch, scikit-learn, 2 other tools, histology / microscopy, other condition
[5] doi:10.1038/s41398-026-03965-z [code]
Disentangling individual heterogeneity reveals robust network and molecular signatures of major depressive disorder with suicidal ideation.
Journal: Translational psychiatry
In common: Pillow, PyTorch, scikit-learn, 2 other tools, 1 reference
[6] doi:10.1038/s41598-026-57519-w [code]
Automated segmentation of neurons and spinal cord structures in immunofluorescence images using SpineDL.
Journal: Scientific reports
In common: Pillow, PyTorch, scikit-learn, 2 other tools, histology / microscopy, other condition
[7] doi:10.1371/journal.pcbi.1013499 [code]
VesiclePy: A machine learning vesicle analysis toolbox for volume electron microscopy.
Journal: PLoS computational biology
In common: Pillow, PyTorch, scikit-learn, 2 other tools, histology / microscopy
[8] doi:10.1038/s41746-026-02651-0 [code]
AI Augmented Confocal Laser Endomicroscopy for Rapid Intraoperative Diagnosis of Brain Tumors.
Journal: NPJ digital medicine
In common: Pillow, PyTorch, pandas, 1 other tool, histology / microscopy, clinical / translational, other condition
[9] doi:10.1038/s41593-026-02388-9 [code]
Hippocampal CA3 connectomics reveals a gradient of mossy fiber inputs and selective feedforward inhibition onto pyramidal cells.
Journal: Nature neuroscience
In common: Pillow, PyTorch, scikit-learn, 2 other tools, histology / microscopy
[10] doi:10.1038/s41598-026-43798-w [code]
A Machine learning pipeline to investigate tissue ingrowth in cerebral aneurysms using preclinical animal models.
Journal: Scientific reports
In common: Pillow, PyTorch, scikit-learn, 2 other tools, histology / microscopy

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.