OSCR

A pre-trained foundation model framework for multiplanar MRI classification of extramural vascular invasion and mesorectal fascia invasion in rectal cancer.

Code ↔ Paper

12 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.

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 12 matches
  1. [1] § Methods › Evaluation › Evaluation metrics ↔ notebooks/compute_AUC_CI.ipynb, lines 513 to 584 · score 0.83 · confidence intervals, binary predictions, predicted probabilities, balanced accuracy, F1 score, CI · Report a mismatch
  2. [2] § Methods › Model development › Training strategy ↔ othercode/classification_model/FMmodel.py, lines 231 to 269 · score 0.76 · Cosine annealing, AdamW, decay, UMedPt, scheduling, optimized · block oscr:b:4DMKBT36HBXEY-M · Report a mismatch
  3. [3] § Methods › Data curation › Dataset ↔ notebooks/export_patient_information.ipynb, lines 87 to 153 · score 0.76 · La Fe, CHU Angers, Centre, Siemens, ULS, manufacturers · Report a mismatch
  4. [4] § Methods › Model development › Training strategy ↔ othercode/classification_model/segresnet192.py, lines 185 to 229 · score 0.74 · focal loss, Cosine annealing, SGD, decay, scheduling, batch · block oscr:b:GKPT0FS2D3VZZ-0 · Report a mismatch
  5. [5] § Results › Classification results ↔ notebooks/draw_ROC.ipynb, lines 145 to 274 · score 0.74 · ROC curves, SeResnet, axial original, UMedPT_LR, MFI classification, AUC · Report a mismatch
  6. [6] § Results › Classification results ↔ notebooks/draw_ROC.ipynb, lines 145 to 274 · score 0.64 · axial_harmo, ROC curves, UMedPT_LR, AUC, sagittal, EVI · Report a mismatch
  7. [7] § Results › Patient characteristics ↔ notebooks/export_patient_information.ipynb, lines 87 to 153 · score 0.61 · CHU Angers, train_val, Siemens, ULS, manufacturers, patient · Report a mismatch
  8. [8] § Methods › Data curation › Image preprocessing and rectum localization ↔ notebooks/resample_totalmask3.ipynb, lines 83 to 172 · score 0.61 · NIfTI, colon mask, resampled, spacing, TotalSegmentator, rectum · Report a mismatch
  9. [9] § Results › Classification results ↔ notebooks/draw_ROC.ipynb, lines 1 to 139 · score 0.55 · UMedPT_LR, EVI classification, ROC, curves, AUC, score · Report a mismatch
  10. [10] § Methods › Data curation › Image preprocessing and rectum localization ↔ othercode/classification_model/centrecrop_correct2.ipynb, lines 26 to 111 · score 0.54 · center crop, voxel, intensity, spacing, TotalSegmentator, mask · Report a mismatch
  11. [11] § Methods › Model development › Training strategy ↔ othercode/classification_model/FMmodel.py, lines 289 to 345 · score 0.54 · Gaussian noise, affine, intensity, transforms, patch, Training · block oscr:b:CW10P6FPZGHF1-L · Report a mismatch
  12. [12] § Methods › Model development › Training strategy ↔ othercode/classification_model/embedding_LR.py, lines 277 to 333 · score 0.54 · Gaussian noise, affine, intensity, transforms, patch, Training · block oscr:b:PW99ZHBJBFPH7-9 · 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

Jupyter notebook · 278 lines · 9.9 KB · Apache-2.0 · 3 matches

  1. # %%
  2. import matplotlib.pyplot as plt
  3. from sklearn.metrics import roc_curve, auc, roc_auc_score
  4. from sklearn.utils import resample
  5. import numpy as np
  6. import matplotlib as mpl
  7. import pandas as pd
  8. #----for evi -----
  9. df1 = pd.read_csv(r"/path/to/workspace/Complete_set/Experiments/Results/UMedPT_LR/combine_origin.csv")
  10. df2 = pd.read_csv(r"/path/to/workspace/Complete_set/Experiments/Results/UMedPT_LR/axial_original.csv")
  11. df3 = pd.read_csv(r"/path/to/workspace/Complete_set/Experiments/Results/UMedPT_LR/sagittal_original.csv")
  12. df4 = pd.read_csv(r"/path/to/workspace/Complete_set/Experiments/Results/FMmodel192/test/best_FM_192.csv")
  13. # Extract ground truth and predicted probabilities for EVI and MFI
  14. y_true = df1['y_test_evi'].values
  15. y_pred_model1 = df1['y_pred_prob_evi'].values
  16. y_pred_model2 = df2['y_pred_prob_evi'].values
  17. y_pred_model3 = df3['y_pred_prob_evi'].values
  18. y_pred_model4 = df4['predicted_probability_evi'].values
  19. # Model names and placeholder for AUC formatting
  20. models = {
  21. 'UMedPT_LR axial+sagittal': y_pred_model1,
  22. 'UMedPT_LR axial': y_pred_model2,
  23. 'UMedPT_LR sagittal': y_pred_model3,
  24. 'UMedPT axial': y_pred_model4,
  25. }
  26. # Soft, elegant colors: light blue, light yellow, light green, light red
  27. # colors = ['#d62728','#1f77b4', '#ffbb00', '#2ca02c'] # soft red blue, yellow, green
  28. # colors = ['#e41a1c', '#377eb8', '#4daf4a', '#984ea3']
  29. # colors = ['#FBDD85', '#80A6E2', '#F46F43', '#403990']
  30. # colors = ['#403990', '#F46F43','#80A6E2','#FBDD85']
  31. colors = ['#403990', '#F46F43','#80A6E2','#FBDD85']
  32. # Set plot style to match high-quality publication standards (e.g., Nature)
  33. mpl.rcParams['font.family'] = 'sans-serif'
  34. mpl.rcParams['font.size'] = 10
  35. #bootstrap compute CI
  36. def bootstrap_roc_ci(y_true, y_pred, n_bootstraps=1000, alpha=0.95):
  37. rng = np.random.RandomState(42)
  38. tprs = []
  39. base_fpr = np.linspace(0, 1, 101)
  40. for _ in range(n_bootstraps):
  41. indices = rng.randint(0, len(y_pred), len(y_pred))
  42. if len(np.unique(y_true[indices])) < 2:
  43. continue
  44. fpr, tpr, _ = roc_curve(y_true[indices], y_pred[indices])
  45. tpr_interp = np.interp(base_fpr, fpr, tpr)
  46. tpr_interp[0] = 0.0
  47. tprs.append(tpr_interp)
  48. tprs = np.array(tprs)
  49. mean_tpr = tprs.mean(axis=0)
  50. std_tpr = tprs.std(axis=0)
  51. tpr_upper = np.minimum(mean_tpr + 1.96 * std_tpr, 1)
  52. tpr_lower = np.maximum(mean_tpr - 1.96 * std_tpr, 0)
  53. return base_fpr, mean_tpr, tpr_lower, tpr_upper
  54. def bootstrap_auc_ci(y_true, y_pred, n_bootstraps=1000, seed=42, alpha=0.95):
  55. rng = np.random.RandomState(seed)
  56. stats = []
  57. n = len(y_pred)
  58. y_true = np.asarray(y_true)
  59. y_pred = np.asarray(y_pred)
  60. for _ in range(n_bootstraps):
  61. idx = rng.randint(0, n, n)
  62. if len(np.unique(y_true[idx])) < 2:
  63. continue
  64. stats.append(roc_auc_score(y_true[idx], y_pred[idx]))
  65. lower = np.percentile(stats, (1 - alpha) / 2 * 100)
  66. upper = np.percentile(stats, (1 + alpha) / 2 * 100)
  67. return lower, upper
  68. # Create the figure
  69. plt.figure(figsize=(6, 6))
  70. # Plot ROC curves for each model
  71. # for (label, y_pred), color in zip(models.items(), colors):
  72. # fpr, mean_tpr, lower_tpr, upper_tpr = bootstrap_roc_ci(y_true, y_pred)
  73. # auc_score = auc(fpr, mean_tpr)
  74. # plt.plot(fpr, mean_tpr, lw=2, label=f"{label} (AUC: {auc_score:.2f})", color=color)
  75. # # plt.plot(fpr, lower_tpr, color=color, linestyle='--', alpha=0.6, linewidth=1)
  76. # # plt.plot(fpr, upper_tpr, color=color, linestyle='--', alpha=0.6, linewidth=1)
  77. # plt.fill_between(fpr, lower_tpr, upper_tpr, color=color, alpha=0.12)
  78. shade_first_n = 2
  79. for i, ((model_name, y_pred), color) in enumerate(zip(models.items(), colors)):
  80. fpr_raw, tpr_raw, _ = roc_curve(y_true, y_pred)
  81. auc_raw = roc_auc_score(y_true, y_pred)
  82. # --- AUC bootstrap CI ?? ---
  83. auc_lo, auc_hi = bootstrap_auc_ci(y_true, y_pred)
  84. # Legend ??????? or en-dash?
  85. label_text = f"{model_name} (AUC: {auc_raw:.2f} [{auc_lo:.2f}-{auc_hi:.2f}])"
  86. # ?????? or ?? plt.plot ???????
  87. plt.step(fpr_raw, tpr_raw, where='post', lw=2.2, color=color, label=label_text)
  88. # --- bootstrap CI for shading / dashed lines ---
  89. # fpr_ci, mean_tpr, lower_tpr, upper_tpr = bootstrap_roc_ci(y_true, y_pred)
  90. # if i < shade_first_n:
  91. # plt.fill_between(fpr, lower_tpr, upper_tpr, color=color, alpha=0.1, linewidth=0)
  92. # else:
  93. # plt.plot(fpr, lower_tpr, color=color, linestyle='--', linewidth=1.1, alpha=0.7)
  94. # plt.plot(fpr, upper_tpr, color=color, linestyle='--', linewidth=1.1, alpha=0.7)
  95. # Plot diagonal line representing random guess
  96. plt.plot([0, 1], [0, 1], 'k--', lw=1, label='Random Guess')
  97. # Set titles and labels
  98. plt.title('Best 4 Models for EVI Classification', fontsize=12, weight='normal')
  99. plt.xlabel('False Positive Rate', fontsize=12)
  100. plt.ylabel('True Positive Rate', fontsize=12)
  101. plt.legend(loc='lower right', frameon=False, fontsize=9)
  102. plt.grid(True, linestyle='--', alpha=0.3)
  103. plt.xticks(np.linspace(0, 1, 6))
  104. plt.yticks(np.linspace(0, 1, 6))
  105. # Thicker border lines
  106. for spine in plt.gca().spines.values():
  107. spine.set_linewidth(1.2)
  108. output_dir = "/path/to/workspace/Complete_set/Experiments/Results/ROC PHOTO/"
  109. filename = "roc_curve_evi_new3.png"
  110. # Optimize layout
  111. plt.tight_layout()
  112. plt.savefig(output_dir + filename, dpi=600, bbox_inches='tight')
  113. plt.show()
  114. # %%
  115. # %%
  116. import matplotlib.pyplot as plt
  117. from sklearn.metrics import roc_curve, auc
  118. import numpy as np
  119. import matplotlib as mpl
  120. import pandas as pd
  121. #----for MFI-----
  122. df1 = pd.read_csv(r"/path/to/workspace/Complete_set/Experiments/Results/axial_harmo_FM192/best_FM_axial_harmo.csv")
  123. df2 = pd.read_csv(r"/path/to/workspace/Complete_set/Experiments/Results/UMedPT_LR/axial_original.csv")
  124. df3 = pd.read_csv(r"/path/to/workspace/Complete_set/Experiments/Results/sagittal_harmo/best_scr_segresnet_sagittalharmo.csv")
  125. df4 = pd.read_csv(r"/path/to/workspace/Complete_set/Experiments/Results/Segresnet/best_segresnet_axial_original.csv")
  126. # Extract ground truth and predicted probabilities for EVI and MFI
  127. y_true = df1['ground_truth_mfi'].values
  128. y_pred_model1 = df1['predicted_probability_mfi'].values
  129. y_pred_model2 = df2['y_pred_prob_mfi'].values
  130. y_pred_model3 = df3['predicted_probability_mfi'].values
  131. y_pred_model4 = df4['predicted_probability_mfi'].values
  132. # Model names and placeholder for AUC formatting
  133. models = {
  134. 'UMedPT axial_harmo': y_pred_model1,
  135. 'UMedPT_LR axial': y_pred_model2,
  136. 'SeResnet axial': y_pred_model4,
  137. 'SeResnet sagittal_harmo': y_pred_model3
  138. }
  139. # Soft, elegant colors: light blue, light yellow, light green, light red
  140. # colors = ['#d62728','#1f77b4', '#ffbb00', '#2ca02c'] # soft red blue, yellow, green
  141. colors = ['#403990', '#F46F43','#80A6E2','#FBDD85']
  142. # Set plot style to match high-quality publication standards (e.g., Nature)
  143. mpl.rcParams['font.family'] = 'sans-serif'
  144. mpl.rcParams['font.size'] = 10
  145. def bootstrap_roc_ci(y_true, y_pred, n_bootstraps=1000, alpha=0.95):
  146. rng = np.random.RandomState(42)
  147. tprs = []
  148. base_fpr = np.linspace(0, 1, 101)
  149. for _ in range(n_bootstraps):
  150. indices = rng.randint(0, len(y_pred), len(y_pred))
  151. if len(np.unique(y_true[indices])) < 2:
  152. continue
  153. fpr, tpr, _ = roc_curve(y_true[indices], y_pred[indices])
  154. tpr_interp = np.interp(base_fpr, fpr, tpr)
  155. tpr_interp[0] = 0.0
  156. tprs.append(tpr_interp)
  157. tprs = np.array(tprs)
  158. mean_tpr = tprs.mean(axis=0)
  159. std_tpr = tprs.std(axis=0)
  160. tpr_upper = np.minimum(mean_tpr + 1.96 * std_tpr, 1)
  161. tpr_lower = np.maximum(mean_tpr - 1.96 * std_tpr, 0)
  162. return base_fpr, mean_tpr, tpr_lower, tpr_upper
  163. def bootstrap_auc_ci(y_true, y_pred, n_bootstraps=1000, seed=42, alpha=0.95):
  164. rng = np.random.RandomState(seed)
  165. stats = []
  166. n = len(y_pred)
  167. y_true = np.asarray(y_true)
  168. y_pred = np.asarray(y_pred)
  169. for _ in range(n_bootstraps):
  170. idx = rng.randint(0, n, n)
  171. if len(np.unique(y_true[idx])) < 2:
  172. continue
  173. stats.append(roc_auc_score(y_true[idx], y_pred[idx]))
  174. lower = np.percentile(stats, (1 - alpha) / 2 * 100)
  175. upper = np.percentile(stats, (1 + alpha) / 2 * 100)
  176. return lower, upper
  177. # Create the figure
  178. plt.figure(figsize=(6, 6))
  179. shade_first_n = 2
  180. for i, ((model_name, y_pred), color) in enumerate(zip(models.items(), colors)):
  181. fpr_raw, tpr_raw, _ = roc_curve(y_true, y_pred)
  182. auc_raw = roc_auc_score(y_true, y_pred)
  183. # --- AUC bootstrap CI ?? ---
  184. auc_lo, auc_hi = bootstrap_auc_ci(y_true, y_pred)
  185. # Legend ??????? or en-dash?
  186. label_text = f"{model_name} (AUC: {auc_raw:.2f} [{auc_lo:.2f}-{auc_hi:.2f}])"
  187. # ?????? or ?? plt.plot ???????
  188. plt.step(fpr_raw, tpr_raw, where='post', lw=2.2, color=color, label=label_text)
  189. # # --- bootstrap CI for shading / dashed lines ---
  190. # fpr_ci, mean_tpr, lower_tpr, upper_tpr = bootstrap_roc_ci(y_true, y_pred)
  191. # if i < shade_first_n:
  192. # plt.fill_between(fpr, lower_tpr, upper_tpr, color=color, alpha=0.1, linewidth=0)
  193. # else:
  194. # plt.plot(fpr, lower_tpr, color=color, linestyle='--', linewidth=1.1, alpha=0.7)
  195. # plt.plot(fpr, upper_tpr, color=color, linestyle='--', linewidth=1.1, alpha=0.7)
  196. # Plot diagonal line representing random guess
  197. plt.plot([0, 1], [0, 1], 'k--', lw=1, label='Random Guess')
  198. # Set titles and labels
  199. plt.title('Best 4 Models for MFI Classification', fontsize=12, weight='normal')
  200. plt.xlabel('False Positive Rate', fontsize=12)
  201. plt.ylabel('True Positive Rate', fontsize=12)
  202. # Add legend in bottom right, no frame
  203. plt.legend(loc='lower right', frameon=False, fontsize=9)
  204. # Add light grid lines
  205. plt.grid(True, linestyle='--', alpha=0.3)
  206. # Customize ticks
  207. plt.xticks(np.linspace(0, 1, 6))
  208. plt.yticks(np.linspace(0, 1, 6))
  209. # Thicker border lines
  210. for spine in plt.gca().spines.values():
  211. spine.set_linewidth(1.2)
  212. output_dir = "/path/to/workspace/Complete_set/Experiments/Results/ROC PHOTO/"
  213. filename = "roc_curve_mfi_new3.png"
  214. # Optimize layout
  215. plt.tight_layout()
  216. plt.savefig(output_dir + filename, dpi=300, bbox_inches='tight')
  217. plt.show()
  218. # %%

draw_ROC.ipynb at commit fa683ec, under Apache-2.0 · at the source

Overview

Authors: Yumeng Zhang1, Shruti Atul Mali1, Danial Khan1, Sina Amirrajab1, Eduardo Ibor-Crespo2, Ana Jimenez-Pastor2, Gloria Ribas3, Silvia Flor-Arnal3, Marta Zerunian4, Christophe Aubé5,6, Luis Martí-Bonmatí3,7, Zohaib Salahuddin1, Philippe Lambin1,8
ORCID iDs: Philippe Lambin
  1. The D-Lab, Department of Precision Medicine, GROW - Research Institute for Oncology and Reproduction, Maastricht University,Maastricht, The Netherlands
  2. Research & Frontiers in AI Department, Quantitative Imaging Biomarkers in Medicine, Quibim SL, Valencia, Spain
  3. Biomedical Imaging Research Group, La Fe Health Research Institute, Valencia, Spain
  4. Radiology Unit, Department of Surgical and Medical Sciences and Translational Medicine, Sapienza University of Rome, Sant’Andrea Hospital,Rome, Italy
  5. Laboratoire HIFIH, Université d’Angers, SFR ICAT 4208,Angers, France
  6. Department of Radiology, CHU Angers,Angers, France
  7. Medical Imaging Department, La Fe University and Polytechnic Hospital,Valencia, Spain
  8. Department of Radiology and Nuclear Medicine, GROW - Research Institute for Oncology and Reproduction, Maastricht University Medical Center+,Maastricht, The Netherlands
Journal: Insights into imaging, volume 17, issue 1, article 141
Dates: received 2 December 2025; accepted 19 April 2026; published online 22 May 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1186/s13244-026-02296-3 · PMID 42171860 · PMCID PMC13197564 · OpenAlex W7162068795
Open access: gold, a free copy (OpenAlex)
Status: code verified (how the code is found and verified)
Categories: structural MRI / diffusion (modality), other condition (population)
Methods: Connectivity, Smoothing, state filtering, decompositions, Machine learning, Preprocessing, Statistics
Keywords: Rectal neoplasms, Magnetic resonance imaging, Extramural vascular invasion, Mesorectal fascia, Deep learning
Topic: Colorectal Cancer Surgical Treatments (Oncology, Medicine), according to OpenAlex
Funding: AIDAVA (101057062); EUCAIM (101100633); EuCanImage (952103); GLIOMATCH (101136670); IMI-OPTIMA (101034347); ImmunoSABR (733008); REALM (101095435); RADIOVAL (101057699); CHAIMELEON (952172); China Scholarship Council (202208110055); HYPOXIMMUNO (694812); AUTO.DISTINCT (957565); JTC2016 CLEARLY (UM 2017-8295)
Citations: not cited yet (Europe PMC); 44 references in the paper

Abstract

Objectives: Accurate MRI-based identification of extramural vascular invasion (EVI) and mesorectal fascia invasion (MFI) is crucial for risk-stratified rectal cancer treatment. However, subjective visual assessment and inter-institutional variability limit diagnostic consistency. This study developed and evaluated a multi-center, foundation model-driven framework that automatically classifies EVI and MFI on axial and sagittal MRI.

Materials and methods: A total of 331 pre-treatment rectal cancer T2-weighted MRI scans from three European hospitals were retrospectively recruited. A self-supervised frequency domain harmonization strategy was applied to reduce scanner variability. Three classifiers, SeResNet, the universal biomedical pretrained model (UMedPT) with a multilayer perceptron head, and a logistic-regression variant using frozen UMedPT features (UMedPT_LR), were trained (n = 265) and tested (n = 66). Gradient-weighted class activation mapping (Grad-CAM) visualized model predictions.

Results: UMedPT_LR achieved the best EVI performance with multiplanar fusion (AUC = 0.82, test set). For MFI, UMedPT trained on axial harmonized images yielded the highest performance (AUC = 0.77). Both tasks outperformed the CHAIMELEON 2024 benchmark (EVI: 0.82 vs 0.74; MFI: 0.77 vs 0.75). Harmonization enhanced MFI classification, and multiplanar fusion further boosted EVI performance. Grad-CAM confirmed biologically plausible attention on peritumoral regions (EVI) and mesorectal fascia margins (MFI).

Conclusion: The proposed foundation model-driven framework, leveraging frequency domain harmonization and multiplanar fusion, achieves state-of-the-art performance for automated EVI and MFI classification on MRI, demonstrating strong generalizability across multiple centers.

Critical relevance statement: Addressing inter-center inconsistencies in rectal cancer MRI, a multiplanar foundation model with cross-scanner harmonization significantly improves the detection of EVI and MFI, potentially standardizing staging and guiding therapy.

Key Points: Among the first studies to investigate automated classification of both EVI and MFI using axial and sagittal T2-weighted MRI. Foundation model-derived features outperform conventional convolutional neural networks (CNNs) for EVI and MFI classification. Frequency domain harmonization and multiplanar fusion selectively enhance diagnostic performance. Automated prediction of EVI and MFI may support more consistent staging and clinical decision-making across institutions.

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 12 matches between paragraphs and lines of code.

yumengzhang97/foundation-model-rectal-mri

License: Apache-2.0
State: the link answers, verified on 28 September 2026
Evidence: files inventoried
Commit: fa683ec2c4c201aca83cb7070eda9863bbf589d8, 6 July 2026
Languages: Jupyter (46), Python (11)
Size: 61 files, 57 scripts
Software Heritage: not archived
Found in: “Code availability”
Holds: README, license file, environment (requirements.txt), 46 notebooks
Not found: CITATION.cff, tests, continuous integration, documentation
Tools: NumPy (36 files), SimpleITK (31 files), pandas (24 files), scikit-learn (12 files), PyTorch (8 files), MONAI (7 files), Matplotlib (6 files), NiBabel (4 files), nnU-Net (2 files), pydicom (2 files), SciPy (2 files), OpenCV (1 file)
Availability: 1 check, the latest on 28 September 2026: the link answers
  • 28 September 2026: the link answers
59 files

Code availability

The code will be made publicly available at https://github.com/yumengzhang97/foundation-model-rectal-mri upon publication.

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;
  • 57 scripts, each with its path and the digest of its content;
  • 12 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

The multicentre MRI datasets used in this study are subject to institutional and EU data protection regulations and therefore cannot be publicly shared. An earlier version of this manuscript was made available as a preprint on arXiv (10.48550/arXiv.2505.18058). The preprint was subsequently updated during the review process.

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, 28 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 13 authors, 5 keywords, 13 funders, 40 references.

Cite

This paper

Zhang, Y., Mali, S. A., Khan, D., Amirrajab, S., Ibor-Crespo, E., Jimenez-Pastor, A., Ribas, G., Flor-Arnal, S., Zerunian, M., Aubé, C., Martí-Bonmatí, L., Salahuddin, Z., & Lambin, P. (2026). A pre-trained foundation model framework for multiplanar MRI classification of extramural vascular invasion and mesorectal fascia invasion in rectal cancer. Insights into imaging, 17(1), 141. https://doi.org/10.1186/s13244-026-02296-3

BibTeX

@article{zhang2026pre,
author = {Zhang, Yumeng and Mali, Shruti Atul and Khan, Danial and Amirrajab, Sina and Ibor-Crespo, Eduardo and Jimenez-Pastor, Ana and Ribas, Gloria and Flor-Arnal, Silvia and Zerunian, Marta and Aubé, Christophe and Martí-Bonmatí, Luis and Salahuddin, Zohaib and Lambin, Philippe},
title = {{A pre-trained foundation model framework for multiplanar MRI classification of extramural vascular invasion and mesorectal fascia invasion in rectal cancer}},
journal = {Insights into imaging},
year = {2026},
month = may,
volume = {17},
number = {1},
pages = {141},
publisher = {Springer},
issn = {1869-4101},
doi = {10.1186/s13244-026-02296-3},
url = {https://doi.org/10.1186/s13244-026-02296-3},
pmid = {42171860},
pmcid = {PMC13197564}
}

RIS

TY - JOUR
AU - Zhang, Yumeng
AU - Mali, Shruti Atul
AU - Khan, Danial
AU - Amirrajab, Sina
AU - Ibor-Crespo, Eduardo
AU - Jimenez-Pastor, Ana
AU - Ribas, Gloria
AU - Flor-Arnal, Silvia
AU - Zerunian, Marta
AU - Aubé, Christophe
AU - Martí-Bonmatí, Luis
AU - Salahuddin, Zohaib
AU - Lambin, Philippe
TI - A pre-trained foundation model framework for multiplanar MRI classification of extramural vascular invasion and mesorectal fascia invasion in rectal cancer
T2 - Insights into imaging
J2 - Insights Imaging
PY - 2026
DA - 2026/05/22
VL - 17
IS - 1
SP - 141
SN - 1869-4101
PB - Springer
DO - 10.1186/s13244-026-02296-3
UR - https://doi.org/10.1186/s13244-026-02296-3
LA - en
ER -

CSL-JSON

{
"id": "10.1186/s13244-026-02296-3",
"type": "article-journal",
"title": "A pre-trained foundation model framework for multiplanar MRI classification of extramural vascular invasion and mesorectal fascia invasion in rectal cancer",
"container-title": "Insights into imaging",
"author": [
{
"family": "Zhang",
"given": "Yumeng"
},
{
"family": "Mali",
"given": "Shruti Atul"
},
{
"family": "Khan",
"given": "Danial"
},
{
"family": "Amirrajab",
"given": "Sina"
},
{
"family": "Ibor-Crespo",
"given": "Eduardo"
},
{
"family": "Jimenez-Pastor",
"given": "Ana"
},
{
"family": "Ribas",
"given": "Gloria"
},
{
"family": "Flor-Arnal",
"given": "Silvia"
},
{
"family": "Zerunian",
"given": "Marta"
},
{
"family": "Aubé",
"given": "Christophe"
},
{
"family": "Martí-Bonmatí",
"given": "Luis"
},
{
"family": "Salahuddin",
"given": "Zohaib"
},
{
"family": "Lambin",
"given": "Philippe"
}
],
"container-title-short": "Insights Imaging",
"volume": "17",
"issue": "1",
"page": "141",
"DOI": "10.1186/s13244-026-02296-3",
"PMID": "42171860",
"PMCID": "PMC13197564",
"ISSN": "1869-4101",
"publisher": "Springer",
"URL": "https://doi.org/10.1186/s13244-026-02296-3",
"language": "en",
"issued": {
"date-parts": [
[
2026,
5,
22
]
]
}
}

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:10.1038/s41467-025-64469-w [code]
Modality-projection universal model for comprehensive full-body medical imaging segmentation.
Journal: Nature communications
In common: nnU-Net, MONAI, pydicom, 8 other tools, 1 reference
[2] doi:10.3389/frai.2026.1771088 [code]
Few-shot deployment of pretrained MRI transformers in brain imaging tasks.
Journal: Frontiers in artificial intelligence
In common: nnU-Net, MONAI, pydicom, 9 other tools, structural MRI / diffusion
[3] doi:10.1016/j.neuroimage.2024.120603 [code]
Fetal brain MRI atlases and datasets: A review.
Journal: NeuroImage
In common: nnU-Net, MONAI, pydicom, 9 other tools, structural MRI / diffusion
[4] doi:10.3389/fonc.2022.819673 [code]
Multimodal MRI Image Decision Fusion-Based Network for Glioma Classification.
Journal: Frontiers in oncology
In common: nnU-Net, MONAI, pydicom, 8 other tools, structural MRI / diffusion, other condition, 1 reference
[5] doi:10.1038/s41597-024-03073-x [code]
Brain tumor segmentation using synthetic MR images - A comparison of GANs and diffusion models.
Journal: Scientific data
In common: nnU-Net, MONAI, pydicom, 9 other tools, other condition
[6] doi:10.1007/s00701-024-05973-8 [code]
NnU-Net versus mesh growing algorithm as a tool for the robust and timely segmentation of neurosurgical 3D images in contrast-enhanced T1 MRI scans.
Journal: Acta neurochirurgica
In common: nnU-Net, MONAI, pydicom, 8 other tools, structural MRI / diffusion, other condition
[7] doi:10.1371/journal.pcbi.1014555 [code]
Body surface potential driven personalisation of electrophysiological digital twins in hypertrophic cardiomyopathy.
Journal: PLoS computational biology
In common: nnU-Net, MONAI, pydicom, 8 other tools, structural MRI / diffusion
[8] doi:10.1016/j.isci.2024.109023 [code]
Deep learning aided preoperative diagnosis of primary central nervous system lymphoma.
Journal: iScience
In common: nnU-Net, MONAI, pydicom, 8 other tools, other condition
[9] doi:10.3389/fneur.2025.1620469 [code]
Federated learning for lesion segmentation in multiple sclerosis: a real-world multi-center feasibility study.
Journal: Frontiers in neurology
In common: nnU-Net, MONAI, pydicom, 7 other tools, structural MRI / diffusion
[10] doi:10.1038/s41593-026-02202-6 [code]
A generalizable foundation model for analysis of human brain MRI.
Journal: Nature neuroscience
In common: MONAI, SimpleITK, OpenCV, 6 other tools, structural MRI / diffusion, other condition, 2 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.

Add the badge to the code's README

OSCR: the badge of this paper

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 -->
[![OSCR](https://openscicode.org/badge/doi/10.1186/s13244-026-02296-3.svg)](https://openscicode.org/badge/doi/10.1186/s13244-026-02296-3)
<!-- oscr-badge:end -->
reStructuredText
.. oscr-badge:start

.. image:: https://openscicode.org/badge/doi/10.1186/s13244-026-02296-3.svg
   :target: https://openscicode.org/badge/doi/10.1186/s13244-026-02296-3
   :alt: OSCR

.. oscr-badge:end
HTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1186/s13244-026-02296-3"><img src="https://openscicode.org/badge/doi/10.1186/s13244-026-02296-3.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.