OSCR

Outer retinal band segmentation in healthy subjects: comparative study between human grading and deep convolutional neural networks.

Code ↔ Paper

1 match 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 1 match
  1. [1] § Methods ↔ Autoencoder/train.py, lines 20–103 · score 0.58 · Deep learning, Adam, loss, Optimizer, CPU, trained

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 · 106 lines · 3.8 KB · no license · 1 match

  1. # train_mae.py
  3. import os
  4. import yaml
  5. import torch
  6. import torch.nn as nn
  7. import torch.optim as optim
  8. from torch.utils.data import DataLoader
  9. from masked_autoencoder import MAESparK
  10. from Dataset import OCTMaskedDataset
  11. from visualize import save_recon_images
  12. from tqdm import tqdm
  13. import matplotlib.pyplot as plt
  16. def load_config(path):
  17. with open(path, "r") as f:
  18. return yaml.safe_load(f)
  20. def train():
  21. config = load_config("Deep_learning_approach\code\AE\config\config.yaml")
  23. # Device
  24. device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
  26. # Dataset
  27. dataset = OCTMaskedDataset(
  28. root_dir=config["data"]["path"],
  29. patch_size=config["model"]["patch_size"],
  30. masking_ratio=config["model"]["masking_ratio"]
  31. )
  32. dataloader = DataLoader(dataset, batch_size=config["train"]["batch_size"], shuffle=True, num_workers=4)
  34. # Model
  35. model = MAESparK(
  36. encoder_cfg=config["model"]["encoder_cfg"],
  37. input_size=config["model"]["input_size"],
  38. patch_size=config["model"]["patch_size"],
  39. embed_dim=config["model"]["embed_dim"],
  40. masking_ratio=config["model"]["masking_ratio"]
  41. ).to(device)
  43. # Optimizer
  44. optimizer = optim.AdamW(model.parameters(), lr=float(config["train"]["lr"]))
  45. criterion = nn.MSELoss()
  47. # Output dirs
  48. os.makedirs(config["train"]["output_dir"], exist_ok=True)
  49. os.makedirs(os.path.join(config["train"]["output_dir"], "recon"), exist_ok=True)
  50. loss_history = []
  52. # Training loop
  53. for epoch in range(config["train"]["epochs"]):
  54. model.train()
  55. epoch_loss = 0.0
  56. for images, masks in tqdm(dataloader, desc=f"Epoch {epoch+1}/{config['train']['epochs']}"):
  57. images, masks = images.to(device), masks.to(device)
  59. optimizer.zero_grad()
  60. outputs = model(images, masks)
  62. loss = criterion(outputs, images)
  63. loss.backward()
  64. optimizer.step()
  66. epoch_loss += loss.item()
  68. avg_loss = epoch_loss / len(dataloader)
  69. loss_history.append(avg_loss)
  70. print(f"Epoch {epoch+1} Loss: {avg_loss:.6f}")
  71. plt.figure()
  72. plt.plot(loss_history, label="Total Loss")
  73. plt.xlabel("Epoch")
  74. plt.ylabel("Loss")
  75. plt.title("Training Loss Curve")
  76. plt.legend()
  77. plt.grid(True)
  78. plt.savefig(os.path.join(config["train"]["output_dir"], "loss_curve.png"))
  79. plt.close()
  80. # Save checkpoint
  81. if (epoch + 1) % config["train"]["save_every"] == 0:
  82. ckpt_path = os.path.join(config["train"]["output_dir"], f"mae_epoch_{epoch+1}.pth")
  83. torch.save(model.state_dict(), ckpt_path)
  85. # Visualization
  86. if (epoch + 1) % config["train"]["viz_every"] == 0:
  87. print("Before concatenation:")
  88. print(f"images: {images.shape}, outputs: {outputs.shape}, masks: {masks.shape}")
  89. save_recon_images(images, outputs, masks, epoch + 1, config["train"]["output_dir"])
  90. # Plot first sample's patch mask
  91. patch_h = config["model"]["input_size"] // config["model"]["patch_size"]
  92. patch_w = patch_h # assuming square images
  94. mask_sample = masks[0].cpu().numpy().reshape(patch_h, patch_w)
  96. plt.figure(figsize=(4, 4))
  97. plt.imshow(mask_sample, cmap="gray")
  98. plt.title(f"Mask (Epoch {epoch + 1})")
  99. plt.axis("off")
  100. mask_path = os.path.join(config["train"]["output_dir"], f"mask_epoch_{epoch + 1}.png")
  101. plt.savefig(mask_path)
  102. plt.close()
  103. print(f"[✓] Saved mask visualization to: {mask_path}")
  105. if __name__ == "__main__":
  106. train()

train.py at commit e74770a, no license · at the source

Overview

Authors: João Duarte Afonso1, Pedro Camacho2, Bruno Pereira2,3, João Pedro Marques4, Daniel Simões Lopes1, Diogo Cabral5
ORCID iDs: João Duarte Afonso, Pedro Camacho, Bruno Pereira, João Pedro Marques, Daniel Simões Lopes, Diogo Cabral
  1. ITI/LARSyS, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
  2. H&TRC - Health & Technology Research Center, ESTeSL - Lisbon School of Health, Polytechnic Institute of Lisbon, Lisbon, Portugal
  3. IRL - Instituto de Retina de Lisboa, Lisbon, Portugal
  4. Department of Ophthalmology, Hospitais da Universidade de Coimbra, Local Health Unit of Coimbra, Coimbra, Portugal
  5. Hospital Garcia de Orta, Almada-Seixal Local Health Unit, Almada, Portugal
Institutions: University of Lisbon (Portugal); Instituto Superior Técnico (Portugal); Laboratório de Robótica e Sistemas de Engenharia; Instituto Politécnico de Lisboa (Portugal); Centro de Investigação em Saúde e Tecnologia (Portugal); Hospitais da Universidade de Coimbra (Portugal); Hospital Garcia de Orta (Portugal)
Journal: Quantitative imaging in medicine and surgery, volume 16, issue 5, article 408
Dates: received 1 October 2025; accepted 30 December 2025; published online 13 April 2026; in print 1 May 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.21037/qims-2025-aw-2093 · PMID 42147957 · PMCID PMC13178413 · OpenAlex W7155958315
Open access: diamond, a free copy (OpenAlex)
Status: code verified
Categories: other (modality), human (organism), healthy (population), methods / tools (subfield)
Methods: Connectivity, Statistics
Keywords: Optical coherence tomography (OCT), deep learning, automatic segmentation, intraclass correlation
Topic: Retinal Imaging and Analysis (Radiology, Nuclear Medicine and Imaging, Medicine), according to OpenAlex
Funding: Associação de Oftalmologistas para o Estudo da Retina (Bolsa para Investigação em Retina), Sociedade Portuguesa de Oftalmologia (Bolsa de Investigação Clinica 2023) and the Portuguese Recovery and Resilience Program (PRR) via IAPMEI/ANI/FCT (Agenda C64502239900000057)
Citations: not cited yet (Europe PMC); 63 references in the paper

Abstract

The abstract is not reproduced here: the paper's license (CC BY-NC-ND) does not allow it. Read it in the paper, at the publisher or on Europe PMC.

Repository

Its files are read in the Code ↔ Paper reader above, with 1 match between paragraphs and lines of code.

Joao-afonso11/OCT_segmentation

License: none: the authors keep all their rights
State: the link answers, verified on 29 September 2026
Evidence: files inventoried
Commit: e74770ad0c2267f83dd9312e3b1d2e2578bd5769, 28 November 2025
Languages: Python (16)
Size: 19 files, 16 scripts
Software Heritage: not archived
Found in: the references
Holds: README
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: PyTorch (14 files), Matplotlib (3 files), NumPy (3 files), Pillow (3 files), PyTorch Lightning (1 file), OpenCV (1 file), pandas (1 file)
Availability: 1 check, the latest on 29 September 2026: the link answers
  • 29 September 2026: the link answers
17 files
At the source: github.com/Joao-afonso11/OCT_segmentation

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;
  • 16 scripts, each with its path and the digest of its content;
  • 1 match 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 statement

The paper has a data availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

  • no repository, dataset or request procedure was recognized in it

Read it in the paper: doi.org/10.21037/qims-2025-aw-2093.

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, 29 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 6 authors, 4 keywords, 1 funder, 53 references.

Cite

This paper

Afonso, J. D., Camacho, P., Pereira, B., Marques, J. P., Lopes, D. S., & Cabral, D. (2026). Outer retinal band segmentation in healthy subjects: comparative study between human grading and deep convolutional neural networks. Quantitative imaging in medicine and surgery, 16(5), 408. https://doi.org/10.21037/qims-2025-aw-2093

BibTeX

@article{afonso2026outer,
author = {Afonso, João Duarte and Camacho, Pedro and Pereira, Bruno and Marques, João Pedro and Lopes, Daniel Simões and Cabral, Diogo},
title = {{Outer retinal band segmentation in healthy subjects: comparative study between human grading and deep convolutional neural networks}},
journal = {Quantitative imaging in medicine and surgery},
year = {2026},
month = apr,
volume = {16},
number = {5},
pages = {408},
publisher = {AME Publications},
issn = {2223-4292},
doi = {10.21037/qims-2025-aw-2093},
url = {https://doi.org/10.21037/qims-2025-aw-2093},
pmid = {42147957},
pmcid = {PMC13178413}
}

RIS

TY - JOUR
AU - Afonso, João Duarte
AU - Camacho, Pedro
AU - Pereira, Bruno
AU - Marques, João Pedro
AU - Lopes, Daniel Simões
AU - Cabral, Diogo
TI - Outer retinal band segmentation in healthy subjects: comparative study between human grading and deep convolutional neural networks
T2 - Quantitative imaging in medicine and surgery
J2 - Quant Imaging Med Surg
PY - 2026
DA - 2026/04/13
VL - 16
IS - 5
SP - 408
SN - 2223-4292
PB - AME Publications
DO - 10.21037/qims-2025-aw-2093
UR - https://doi.org/10.21037/qims-2025-aw-2093
LA - en
ER -

CSL-JSON

{
"id": "10.21037/qims-2025-aw-2093",
"type": "article-journal",
"title": "Outer retinal band segmentation in healthy subjects: comparative study between human grading and deep convolutional neural networks",
"container-title": "Quantitative imaging in medicine and surgery",
"author": [
{
"family": "Afonso",
"given": "João Duarte"
},
{
"family": "Camacho",
"given": "Pedro"
},
{
"family": "Pereira",
"given": "Bruno"
},
{
"family": "Marques",
"given": "João Pedro"
},
{
"family": "Lopes",
"given": "Daniel Simões"
},
{
"family": "Cabral",
"given": "Diogo"
}
],
"container-title-short": "Quant Imaging Med Surg",
"volume": "16",
"issue": "5",
"page": "408",
"DOI": "10.21037/qims-2025-aw-2093",
"PMID": "42147957",
"PMCID": "PMC13178413",
"ISSN": "2223-4292",
"publisher": "AME Publications",
"URL": "https://doi.org/10.21037/qims-2025-aw-2093",
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
13
]
]
}
}

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:10.3389/frai.2026.1841639 [code]
Label tree semantic losses for rich multi-class medical image segmentation.
Journal: Frontiers in artificial intelligence
In common: PyTorch Lightning, OpenCV, Pillow, 4 other tools, 1 reference
[2] doi:10.1364/boe.600665 [code]
NeuroSeg-MF: robust neuron segmentation in two-photon Ca<sup>2+</sup> imaging using multi-feature fusion and detection-guided SAM.
Journal: Biomedical optics express
In common: OpenCV, Pillow, PyTorch, 3 other tools, methods / tools, 2 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: PyTorch Lightning, OpenCV, Pillow, 4 other tools, methods / tools
[4] doi:10.1038/s42003-026-10957-8 [code]
Brain defence by the extracellular matrix protein Cochlin.
Journal: Communications biology
In common: PyTorch Lightning, OpenCV, Pillow, 4 other tools
[5] doi:10.1007/s12021-026-09815-z [code]
BasNet: Attention U-Net-Based Automated Axon Segmentation in Bielschowsky Silver-Stained Histology.
Journal: Neuroinformatics
In common: PyTorch Lightning, OpenCV, Pillow, 4 other tools
[6] doi:10.1371/journal.pcbi.1014263 [code]
MIRAGE: Robust multi-modal architectures translate fMRI-to-image models from vision to mental imagery.
Journal: PLoS computational biology
In common: PyTorch Lightning, OpenCV, Pillow, 4 other tools
[7] doi:10.1162/imag.a.1207 [code]
Investigating the temporal dynamics and modeling of mid-level feature representations in humans.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: PyTorch Lightning, OpenCV, Pillow, 4 other tools
[8] doi:10.1038/s41597-026-07077-7 [code]
Everyday Activity Science and Engineering Table Setting Dataset.
Journal: Scientific data
In common: PyTorch Lightning, OpenCV, PyTorch, 3 other tools, other, methods / tools
[9] doi:10.1162/imag.a.1326 [code]
RAVEN: Robust, generalizable, multi-resolution structural MRI upsampling using autoencoders.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: PyTorch Lightning, OpenCV, Pillow, 4 other tools
[10] doi:10.1016/j.isci.2026.116355 [code]
Tera-MIND: Tera-scale mouse brain simulation via spatial mRNA-guided diffusion.
Journal: iScience
In common: PyTorch Lightning, OpenCV, Pillow, 4 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.