Accelerating Whole-Sample Polarization-Resolved Second Harmonic Generation imaging in Mammary Gland Tissue via Generative Adversarial Networks
Bibliographic record
Abstract
Authors: Arash Aghigh, Jysiane Cardot, Melika Saadat Mohammadi, Gaëtan Jargot, Heide Ibrahim, Isabelle Plante, François Légaré Affiliations: 1. Centre Énergie Matériaux Télécommunications, Institut National de la Recherche Scientifique, Varennes, Québec, Canada. 2. Centre Armand-Frappier Santé Biotechnologie, Institut National de la Recherche Scientifique, Laval, Québec, Canada. Corresponding Author: Arash Aghigh, arash.aghigh@inrs.ca Description: This dataset accompanies the research on improving whole-sample Polarization-Resolved Second Harmonic Generation (P-SHG) imaging in mammary gland tissue using Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN). The novel approach significantly reduces imaging time while maintaining high image quality and analytical accuracy, demonstrating a reduction in imaging time by more than 95%. This method also minimizes laser-induced photodamage, lowers costs of optical components, and increases the accessibility and applicability of P-SHG imaging in various fields. Keywords: Polarization-Resolved Second Harmonic Generation, P-SHG, Generative Adversarial Networks, GAN, ESRGAN, Mammary Gland Imaging, Super-Resolution, Image Upscaling, Deep Learning, Biomedical Imaging Funding Information: • Canada Foundation for Innovation • Fonds de recherche du Québec–Nature et technologies • Natural Sciences and Engineering Research Council of Canada • New Frontiers Research Fund • NSERC CREATE program (scholarship for Arash Aghigh) Related Identifiers: • GitHub repository for ChaiNNer program: https://github.com/chaiNNer-org/chaiNNer • Download links for models used: https://openmodeldb.info Additional Information: Animal studies were conducted according to the procedures provided by the Canadian Council on Animal Care. The protocol (2005-02) was reviewed and approved by the Institutional Committee for Animal Protection of the Laboratoire National de Biologie Expérimentale (LNBE), the animal facilities based at the Institut National de Recherche Scientifique (INRS).
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".