OSCR

Segmentation and classification of hippocampal subregions using multi-task generative adversarial networks.

Code ↔ Paper

6 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.

6 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 6 matches
  1. [1] § Methodology › Benchmark dataset ↔ mtugan/dataset.py, lines 9 to 105 · score 0.73 · horizontal flipping, brightness, elastic, nearest, resized, augmentation · block oscr:b:V046MM5KKJ34C-P · Report a mismatch
  2. [2] § Methodology › Model architecture › Loss functions › Generator loss ↔ mtugan/losses.py, lines 25 to 30 · score 0.69 · focal loss, segmentation loss, Dice loss, generator loss, weighted, class · block oscr:b:DCJPNF2H50JQ8-E · Report a mismatch
  3. [3] § Methodology › Model architecture › Loss functions › Discriminator loss ↔ mtugan/losses.py, lines 32 to 38 · score 0.66 · gradient penalty, discriminator loss, Dice loss, fake · block oscr:b:WKQBT1TZJYXF0-V · Report a mismatch
  4. [4] § Methodology › Evaluation metrics ↔ main.py, lines 30 to 98 · score 0.56 · class metrics, F1 score, hippocampal subregions, Precision, Recall, CA1 · block oscr:b:GQSQAD36VTY38-T · Report a mismatch
  5. [5] § Methodology › Model architecture › The generator ↔ mtugan/gan.py, lines 7 to 66 · score 0.56 · LeakyReLU, padding, Max, stride, blocks, bottleneck · block oscr:b:FAAJA7D5MH12H-3 · Report a mismatch
  6. [6] § Methodology › Training protocol ↔ mtugan/train.py, lines 34 to 119 · score 0.51 · Adam, warm, phase, optimizers, trained, discriminator · block oscr:b:NSSHKQHBSGKE5-T · Report a mismatch

Paper

Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Python · 39 lines · 1.9 KB · MIT · 2 matches

  1. import torch
  2. import torch.nn as nn
  3. import torch.nn.functional as F
  4. from mtugan.utils import gradient_penalty
  5. # Loss Functions
  6. def dice_loss(y_true, y_pred, epsilon=1e-8):
  7. numerator = 2 * torch.sum(y_true * y_pred, dim=(1, 2, 3))
  8. denominator = torch.sum(y_true + y_pred, dim=(1, 2, 3)) + epsilon
  9. return 1 - (numerator / denominator).mean()
  10. def focal_loss(y_pred, y_true, gamma=2.0, alpha=None, reduction='mean'):
  11. log_pt = F.log_softmax(y_pred, dim=1)
  12. pt = torch.exp(log_pt)
  13. y_true_onehot = F.one_hot(y_true, num_classes=3).float()
  14. if alpha is not None:
  15. focal_weight = alpha[y_true] * (1 - pt[range(len(y_true)), y_true]) ** gamma
  16. else:
  17. focal_weight = (1 - pt[range(len(y_true)), y_true]) ** gamma
  18. loss = -focal_weight * log_pt[range(len(y_true)), y_true]
  19. return loss.mean() if reduction == 'mean' else loss.sum()
  20. def generator_loss(y_true_seg, y_pred_seg, fake_output, y_true_cls, y_pred_cls, class_weights,
  21. lambda_dice=2.0, lambda_adv=0.1, lambda_cls=0.3): # Adjusted to prioritize segmentation
  22. seg_loss = dice_loss(y_true_seg, y_pred_seg)
  23. adv_loss = nn.BCELoss()(fake_output, torch.ones_like(fake_output))
  24. cls_loss = focal_loss(y_pred_cls, y_true_cls, alpha=class_weights)
  25. return lambda_dice * seg_loss + lambda_adv * adv_loss + lambda_cls * cls_loss
  26. def discriminator_loss(discriminator, real_output, fake_output, ground_truth, lambda_dice=0.5, lambda_bce=0.5, lambda_gp=1.0, device='cuda'):
  27. dice_real = dice_loss(ground_truth, real_output)
  28. bce_real = nn.BCELoss()(real_output, torch.ones_like(real_output))
  29. dice_fake = dice_loss(ground_truth, fake_output)
  30. bce_fake = nn.BCELoss()(fake_output, torch.zeros_like(fake_output))
  31. gp = gradient_penalty(discriminator, ground_truth, fake_output.detach(), device)
  32. return lambda_dice * (dice_real + dice_fake) / 2 + lambda_bce * (bce_real + bce_fake) / 2 + lambda_gp * gp

losses.py at commit bc6784d, under MIT · at the source

Overview

Authors: Sayed Mehedi Azim1, Renuka Kumar2, Brian Corbett1,2, Iman Dehzangi1,3,4
  1. Center for Computational and Integrative Biology, Rutgers University,Camden, NJ 08103 USA
  2. Department of Biology, Rutgers University,Camden, NJ 08103 USA
  3. Department of Computer Science, Rutgers University,Camden, NJ 08103 USA
  4. Rutgers Cancer Institute, Rutgers University,New Brunswick, NJ 08901 USA
Institutions: Rutgers, The State University of New Jersey (United States)
Journal: Scientific reports, volume 16, issue 1, article 24430
Dates: received 11 November 2025; accepted 21 April 2026; published online 28 May 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.1038/s41598-026-50475-5 · PMID 42209557 · PMCID PMC13448715 · OpenAlex W7162671199
Open access: gold, a free copy (OpenAlex)
Status: code verified (how the code is found and verified)
Categories: histology / microscopy (modality), mouse (organism), methods / tools (subfield)
Methods: Connectivity, Machine learning
Keywords: Multi-task learning, Generative adversarial networks, Hippocampal region segmentation, Subregion classification, Computational biology and bioinformatics, Neuroscience
MeSH: Hippocampus*, Image Processing, Computer-Assisted*, Animals, Generative Adversarial Networks, Generative Artificial Intelligence, Glutamate Decarboxylase, Mice, Proto-Oncogene Proteins c-fos (* major topic)
Topic: Cell Image Analysis Techniques (Biophysics, Biochemistry, Genetics and Molecular Biology), according to OpenAlex
Funding: NRT-NSF (2152059)
Citations: not cited yet (Europe PMC); 47 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 6 matches between paragraphs and lines of code.

MLBC-lab/MT-UGAN

License: MIT
State: the link answers, verified on 28 September 2026
Evidence: files inventoried
Commit: bc6784dc81deabf722a4a2416c3decd040511e82, 3 October 2025
Languages: Python (8)
Size: 12 files, 8 scripts
Software Heritage: not archived
Found in: the text, “Introduction”
Holds: README, license file
Not found: CITATION.cff, environment file, tests, continuous integration, documentation
Tools: PyTorch (7 files), NumPy (3 files), OpenCV (2 files), scikit-learn (2 files), Matplotlib (1 file), Pillow (1 file), SciPy (1 file)
Availability: 1 check, the latest on 28 September 2026: the link answers
  • 28 September 2026: the link answers
10 files

The paper's code and data availability statement is in the Data section.

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;
  • 8 scripts, each with its path and the digest of its content;
  • 6 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.

Code and data availability statement

The paper has a code and 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/10.1038/s41598-026-50475-5.

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, 6 keywords, 8 MeSH terms, 1 funder, 25 references.

Cite

This paper

Azim, S. M., Kumar, R., Corbett, B., & Dehzangi, I. (2026). Segmentation and classification of hippocampal subregions using multi-task generative adversarial networks. Scientific reports, 16(1), 24430. https://doi.org/10.1038/s41598-026-50475-5

BibTeX

@article{azim2026segmentation,
author = {Azim, Sayed Mehedi and Kumar, Renuka and Corbett, Brian and Dehzangi, Iman},
title = {{Segmentation and classification of hippocampal subregions using multi-task generative adversarial networks}},
journal = {Scientific reports},
year = {2026},
month = may,
volume = {16},
number = {1},
pages = {24430},
publisher = {Nature Publishing Group},
issn = {2045-2322},
doi = {10.1038/s41598-026-50475-5},
url = {https://doi.org/10.1038/s41598-026-50475-5},
pmid = {42209557},
pmcid = {PMC13448715}
}

RIS

TY - JOUR
AU - Azim, Sayed Mehedi
AU - Kumar, Renuka
AU - Corbett, Brian
AU - Dehzangi, Iman
TI - Segmentation and classification of hippocampal subregions using multi-task generative adversarial networks
T2 - Scientific reports
J2 - Sci Rep
PY - 2026
DA - 2026/05/28
VL - 16
IS - 1
SP - 24430
SN - 2045-2322
PB - Nature Publishing Group
DO - 10.1038/s41598-026-50475-5
UR - https://doi.org/10.1038/s41598-026-50475-5
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41598-026-50475-5",
"type": "article-journal",
"title": "Segmentation and classification of hippocampal subregions using multi-task generative adversarial networks",
"container-title": "Scientific reports",
"author": [
{
"family": "Azim",
"given": "Sayed Mehedi"
},
{
"family": "Kumar",
"given": "Renuka"
},
{
"family": "Corbett",
"given": "Brian"
},
{
"family": "Dehzangi",
"given": "Iman"
}
],
"container-title-short": "Sci Rep",
"volume": "16",
"issue": "1",
"page": "24430",
"DOI": "10.1038/s41598-026-50475-5",
"PMID": "42209557",
"PMCID": "PMC13448715",
"ISSN": "2045-2322",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41598-026-50475-5",
"language": "en",
"issued": {
"date-parts": [
[
2026,
5,
28
]
]
}
}

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:10.1007/s12021-024-09688-0 [code]
A Deep Learning-based Pipeline for Segmenting the Cerebral Cortex Laminar Structure in Histology Images.
Journal: Neuroinformatics
In common: OpenCV, Pillow, PyTorch, 4 other tools, histology / microscopy, 2 references
[2] doi:10.1093/bib/bbag020 [code]
S2potAE: multimodal spatial spot autoencoder integrating image and transcriptomic features for deconvolution.
Journal: Briefings in bioinformatics
In common: OpenCV, Pillow, PyTorch, 4 other tools, histology / microscopy, mouse, 1 reference
[3] doi:10.3390/children12091127 [code]
The Expanding Frontier: The Role of Artificial Intelligence in Pediatric Neuroradiology.
Journal: Children (Basel, Switzerland)
In common: OpenCV, Pillow, PyTorch, 4 other tools, 2 references
[4] doi:10.3389/fbioe.2024.1411680 [code]
ML-driven segmentation of microvascular features during histological examination of tissue-engineered vascular grafts.
Journal: Frontiers in bioengineering and biotechnology
In common: OpenCV, Pillow, PyTorch, 3 other tools, histology / microscopy, methods / tools, 1 reference
[5] doi:10.1007/s00429-026-03166-w [code]
Autoencoders for unsupervised analysis of rat myeloarchitecture.
Journal: Brain structure & function
In common: OpenCV, Pillow, PyTorch, 4 other tools, histology / microscopy, 1 reference
[6] doi:10.1038/s41698-024-00632-8 [code]
Combination of MRI-based prediction and CRISPR/Cas12a-based detection for IDH genotyping in glioma.
Journal: NPJ precision oncology
In common: OpenCV, Pillow, PyTorch, 4 other tools, 1 reference
[7] 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: OpenCV, Pillow, PyTorch, 4 other tools, 1 reference
[8] doi:10.1093/nar/gkaf1473 [code]
STAN, a computational framework for inferring spatially informed transcription factor activity.
Journal: Nucleic acids research
In common: OpenCV, Pillow, PyTorch, 4 other tools, 1 reference
[9] doi:10.1111/bpa.70029 [code]
Pediatric brain tumor classification using digital pathology and deep learning: Evaluation of SOTA methods on a multi-center Swedish cohort.
Journal: Brain pathology (Zurich, Switzerland)
In common: OpenCV, Pillow, PyTorch, 4 other tools, 1 reference
[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: OpenCV, Pillow, PyTorch, 2 other tools, histology / microscopy, methods / tools, mouse, 1 reference

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/10.1038/s41598-026-50475-5.svg)](https://openscicode.org/badge/doi/10.1038/s41598-026-50475-5)
<!-- oscr-badge:end -->
reStructuredText
.. oscr-badge:start

.. image:: https://openscicode.org/badge/doi/10.1038/s41598-026-50475-5.svg
   :target: https://openscicode.org/badge/doi/10.1038/s41598-026-50475-5
   :alt: OSCR

.. oscr-badge:end
HTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1038/s41598-026-50475-5"><img src="https://openscicode.org/badge/doi/10.1038/s41598-026-50475-5.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.