Physics-informed multi-encoder adaptive optics enables rapid aberration correction for intravital microscopy of deep complex tissue.
3 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 4 matches
- [1] § Results › Fast and structure-independent aberration estimation via multi-encoder networks ↔ utils/zernike.py, lines 130 to 238 · score 0.90 · horizontal coma, vertical trefoil, oblique trefoil, vertical coma, vertical astigmatism, oblique astigmatism · block
oscr:b:325735Z6VA508-5· Report a mismatch - [2] § Methods › MeNet architecture and network training ↔ model/model.py, lines 63 to 126 · score 0.69 · PReLU, batch normalization, single encoder, kernel, blocks, activation · block
oscr:b:GJNG8QPNB8X9W-6· Report a mismatch - [3] § Methods › MeNet-AO and DWS-AO correction › MeNet-AO ↔ utils/zernike.py, lines 130 to 238 · score 0.69 · vertical astigmatism, oblique astigmatism, primary spherical, Zernike · block
oscr:b:325735Z6VA508-5· Report a mismatch - [4] § Methods › MeNet architecture and network training ↔ .history/model/MultiEncoder_20250913205642.py, lines 12 to 92 · score 0.68 · PReLU, batch normalization, multi encoder, kernel, blocks, model · block
oscr:b:JX9C38E9JA1NB-B· 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 · 310 lines · 12 KB · MIT · 2 matches
- import numpy as np
- from scipy.special import binom
- from csbdeep.utils import _raise
- from functools import lru_cache
- """
- Part of this file is adapted from:
- Project: phasenet
- Author: DEBAYAN SAHA, UWE SCHMIDT,
- URL: https://github.com/mpicbg-csbd/phasenet
- """
- def nm_to_noll(n, m):
- j = (n*(n+1))//2 + abs(m)
- if m> 0 and n%4 in (0,1): return j
- if m< 0 and n%4 in (2,3): return j
- if m>=0 and n%4 in (2,3): return j+1
- if m<=0 and n%4 in (0,1): return j+1
- assert False
- def nm_to_ansi(n, m):
- return (n*(n+2) + m) // 2
- def nm_normalization(n, m):
- """the norm of the zernike mode n,m in born/wolf convetion
- i.e. sqrt( \int | z_nm |^2 )
- """
- return np.sqrt((1.+(m==0))/(2.*n+2))
- def nm_polynomial(n, m, rho, theta, normed=True):
- """returns the zernike polyonimal by classical n,m enumeration
- if normed=True, then they form an orthonormal system
- \int z_nm z_n'm' = delta_nn' delta_mm'
- and the first modes are
- z_nm(0,0) = 1/sqrt(pi)*
- z_nm(1,-1) = 1/sqrt(pi)* 2r cos(phi)
- z_nm(1,1) = 1/sqrt(pi)* 2r sin(phi)
- z_nm(2,0) = 1/sqrt(pi)* sqrt(3)(2 r^2 - 1)
- ...
- z_nm(4,0) = 1/sqrt(pi)* sqrt(5)(6 r^4 - 6 r^2 +1)
- ...
- if normed =False, then they follow the Born/Wolf convention
- (i.e. min/max is always -1/1)
- \int z_nm z_n'm' = (1.+(m==0))/(2*n+2) delta_nn' delta_mm'
- z_nm(0,0) = 1
- z_nm(1,-1) = r cos(phi)
- z_nm(1,1) = r sin(phi)
- z_nm(2,0) = (2 r^2 - 1)
- ...
- z_nm(4,0) = (6 r^4 - 6 r^2 +1)
- """
- if abs(m) > n:
- raise ValueError(" |m| <= n ! ( %s <= %s)" % (m, n))
- if (n - m) % 2 == 1:
- return 0 * rho + 0 * theta
- radial = 0
- m0 = abs(m)
- for k in range((n - m0) // 2 + 1):
- radial += (-1.) ** k * binom(n - k, k) * binom(n - 2 * k, (n - m0) // 2 - k) * rho ** (n - 2 * k)
- radial *= (rho <= 1.)
- if normed:
- prefac = 1. / nm_normalization(n, m)
- else:
- prefac = 1.
- if m >= 0:
- return prefac * radial * np.cos(m0 * theta)
- else:
- return prefac * radial * np.sin(m0 * theta)
- @lru_cache(maxsize=32)
- def rho_theta(size):
- r = np.linspace(-1,1,size)
- X,Y = np.meshgrid(r,r, indexing='ij')
- rho = np.hypot(X,Y)
- theta = np.arctan2(Y,X)
- return rho, theta
- @lru_cache(maxsize=32)
- def outside_mask(size):
- rho, theta = rho_theta(size)
- return nm_polynomial(0, 0, rho, theta, normed=False) < 1
- def dict_to_list(kv):
- max_key = max(kv.keys())
- out = [0]*(max_key+1)
- for k,v in kv.items():
- out[k] = v
- return out
- def ensure_dict(values, order):
- if isinstance(values,dict):
- return values
- if isinstance(values,np.ndarray):
- values = tuple(values.ravel())
- if isinstance(values,(tuple,list)):
- order = str(order).lower()
- order in ('noll','ansi') or _raise(ValueError("Could not identify the Zernike nomenclature/order"))
- offset = 1 if order=='noll' else 0
- indices = range(offset,offset+len(values))
- return dict(zip(indices,values))
- raise ValueError("Could not identify the data type for dictionary formation")
- class Zernike:
- """
- Encapsulates Zernike polynomials
- :param index: string, integer or tuple, index of Zernike polynomial e.g. 'defocus', 4, (2,2)
- :param oder: string, defines the Zernike nomenclature if index is an integer, eg noll or ansi, default is noll
- """
- _ansi_names = ['piston', 'tilt', 'tip', 'oblique astigmatism', 'defocus',
- 'vertical astigmatism', 'vertical trefoil', 'vertical coma',
- 'horizontal coma', 'oblique trefoil', 'oblique quadrafoil',
- 'oblique secondary astigmatism', 'primary spherical',
- 'vertical secondary astigmatism', 'vertical quadrafoil']
- _nm_pairs = set((n,m) for n in range(200) for m in range(-n,n+1,2))
- _noll_to_nm = dict(zip((nm_to_noll(*nm) for nm in _nm_pairs),_nm_pairs))
- _ansi_to_nm = dict(zip((nm_to_ansi(*nm) for nm in _nm_pairs),_nm_pairs))
- def __init__(self, index, order='noll'):
- super().__setattr__('_mutable', True)
- if isinstance(index,str):
- if index.isdigit():
- index = int(index)
- else:
- name = index.lower()
- name in self._ansi_names or _raise(ValueError("Your input for index is string : Could not identify the name of Zernike polynomial"))
- index = self._ansi_names.index(name)
- order = 'ansi'
- if isinstance(index,(list,tuple)) and len(index)==2:
- self.n, self.m = int(index[0]), int(index[1])
- (self.n, self.m) in self._nm_pairs or _raise(ValueError("Your input for index is list/tuple : Could not identify the n,m order of Zernike polynomial"))
- elif isinstance(index,int):
- order = str(order).lower()
- order in ('noll','ansi') or _raise(ValueError("Your input for index is int : Could not identify the Zernike nomenclature/order"))
- if order == 'noll':
- index in self._noll_to_nm or _raise(ValueError("Your input for index is int and input for Zernike nomenclature is Noll: Could not identify the Zernike polynomial with this index"))
- self.n, self.m = self._noll_to_nm[index]
- elif order == 'ansi':
- index in self._ansi_to_nm or _raise(ValueError("Your input for index is int and input for Zernike nomenclature is ANSI: Could not identify the Zernike polynomial with this index"))
- self.n, self.m = self._ansi_to_nm[index]
- else:
- raise ValueError("Could not identify your index input, we accept strings, lists and tuples only")
- self.index_noll = nm_to_noll(self.n, self.m)
- self.index_ansi = nm_to_ansi(self.n, self.m)
- self.name = self._ansi_names[self.index_ansi] if self.index_ansi < len(self._ansi_names) else None
- self._mutable = False
- def polynomial(self, size, normed=True, outside=np.nan):
- """
- For visualization of Zernike polynomial on a disc of unit radius
- :param size: integer, Defines the shape of square grid, e.g. 256 or 512
- :param normed: boolen, Whether the Zernike polynomials are normalized, default is True
- :param outside: scalar, Outside padding of the spherical disc defined within a square grid, default is np.nan
- :return: 2D array, Zernike polynomial computed on a disc of unit radius defined within a square grid
- """
- np.isscalar(size) and int(size) > 0 or _raise(ValueError())
- return self.phase(*rho_theta(int(size)), normed=normed, outside=outside)
- def phase(self, rho, theta, normed=True, outside=None):
- """
- For creation of a Zernike polynomial with a given polar co-ordinate system
- :param rho: 2D square array, radial axis
- :param theta: 2D square array, azimuthal axis
- :param normed: boolen, whether the Zernike polynomials are normalized, default is True
- :param outside: scalar, outside padding of the spherical disc defined within a square grid, default is None
- :return: 2D array, Zernike polynomial computed for rho and theta
- """
- (isinstance(rho,np.ndarray) and rho.ndim==2 and rho.shape[0]==rho.shape[1]) or _raise(ValueError('Only 2D square array for radial co-ordinate is accepted'))
- (isinstance(theta,np.ndarray) and theta.shape==rho.shape) or _raise(ValueError('Only 2D square array for azimutha co-ordinate is accepted'))
- size = rho.shape[0]
- np.isscalar(normed) or _raise(ValueError())
- outside is None or np.isscalar(outside) or _raise(ValueError("Only scalar constant value for outside is accepted"))
- w = nm_polynomial(self.n, self.m, rho, theta, normed=bool(normed))
- if outside is not None:
- w[nm_polynomial(0, 0, rho, theta, normed=False) < 1] = outside
- return w
- def __hash__(self):
- return hash((self.n,self.m))
- def __eq__(self, other):
- return isinstance(other,Zernike) and (self.n,self.m) == (other.n,other.m)
- def __lt__(self, other):
- # return self.index_ansi < other.index_ansi
- return self.index_noll < other.index_noll
- def __setattr__(self, *args):
- if self._mutable:
- super().__setattr__(*args)
- else:
- raise AttributeError('Zernike is immutable')
- def __repr__(self):
- return f'Zernike(n={self.n}, m={self.m: 1}, noll={self.index_noll:2}, ansi={self.index_ansi:2}' + (f", name='{self.name}')" if self.name is not None else ")")
- class ZernikeWavefront:
- """
- Encapsulates the wavefront defined by Zernike polynomials
- :param amplitudes: dictionary, nd array, tuple or list, Amplitudes of Zernike polynomials
- :param oder: string, Zernike nomenclature, eg noll or ansi, default is noll
- """
- def __init__(self, amplitudes, order='noll'):
- amplitudes = ensure_dict(amplitudes, order)
- all(np.isscalar(a) for a in amplitudes.values()) or _raise(ValueError("Could not identify scalar value for amplitudes after making a dictionary"))
- self.zernikes = {Zernike(j,order=order):a for j,a in amplitudes.items()}
- self.amplitudes_noll = tuple(dict_to_list({z.index_noll:a for z,a in self.zernikes.items()})[1:])
- self.amplitudes_ansi = tuple(dict_to_list({z.index_ansi:a for z,a in self.zernikes.items()}))
- self.amplitudes_requested = tuple(self.zernikes[k] for k in sorted(self.zernikes.keys()))
- def __len__(self):
- return len(self.zernikes)
- def polynomial(self, size, normed=True, outside=np.nan):
- """
- For visualization of weighted sum of Zernike polynomials on a disc of unit radius
- :param size: integer, Defines the shape of square grid, e.g. 256 or 512
- :param normed: boolen, Whether the Zernike polynomials are normalized, default is True
- :param outside: scalar, Outside padding of the spherical disc defined within a square grid, default is np.nan
- :return: 2D array, weighted sums of Zernike polynomials computed on a disc of unit radius defined within a square grid
- """
- return np.sum([a * z.polynomial(size=size, normed=normed, outside=outside) for z,a in self.zernikes.items()], axis=0)
- def phase(self, rho, theta, normed=True, outside=None):
- """
- For creation of phase defined as a weighted sum of Zernike polynomial with a given polar co-ordinate system
- :param rho: 2D square array, radial axis
- :param theta: 2D square array, azimuthal axis
- :param normed: boolen, whether the Zernike polynomials are normalized, default is True
- :param outside: scalar, outside padding of the spherical disc defined within a square grid, default is none
- :return: 2D array, wavefront computed for rho and theta
- """
- return np.sum([a * z.phase(rho=rho, theta=theta, normed=normed, outside=outside) for z,a in self.zernikes.items()], axis=0)
- def random_zernike_wavefront(amplitude_ranges, order='noll', rng=None):
- """
- Creates random Zernike wavefront with random amplitudes drawn from a uniform distibution
- :param aplitude_ranges: dictionary, nd array, tuple or list, amplitude bounds
- :param oder: string, to define the Zernike nomenclature if index is an integer, eg noll or ansi, default is noll
- :param rng:
- :return: Zernike wavefront object
- """
- if rng is None:
- rng = np.random
- amplitude_ranges = ensure_dict(amplitude_ranges, order)
- all((np.isscalar(v) and v>=0) or (isinstance(v,(tuple,list)) and len(v)==2) for v in amplitude_ranges.values()) or _raise(ValueError())
- amplitude_ranges = {k:((-v,v) if np.isscalar(v) else v) for k,v in amplitude_ranges.items()}
- all(v[0]<=v[1] for v in amplitude_ranges.values()) or _raise(ValueError("Lower bound is expected to be less than the upper bound"))
- # return ZernikeWavefront({k:rng.uniform(*v) for k,v in amplitude_ranges.items()}, order=order)
- # return ZernikeWavefront({k: rng.normal(loc=0, scale=(v[1] - v[0]) / 2) for k, v in amplitude_ranges.items()}, order=order)
- return ZernikeWavefront({k: rng.normal(loc=0, scale=(v[1] - v[0]) / 2) if rng.random() < 0.3 else 0 for k, v in amplitude_ranges.items()}, order=order)
zernike.py at commit 81262de, under MIT · at the source
Overview
- Department of Biomedical Engineering, Southern University of Science and Technology,Shenzhen, China
- Department of Immunology and Microbiology, School of Life Sciences, Southern University of Science and Technology,Shenzhen, China
- Division of Life Science, The Hong Kong University of Science and Technology, Clear Water Bay,Kowloon, Hong Kong China
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.
Repositories
Its files are read in the Code ↔ Paper reader above, with 4 matches between paragraphs and lines of code.
Zenodo 17118222
Availability: 1 check, the latest on 28 September 2026: the link answers (HTTP 200)
- 28 September 2026: the link answers (HTTP 200)
lukachan41/MeNet-AO
81262de3bf380b2c947f78ee5e22238baa9028fa, 30 December 2025Availability: 1 check, the latest on 28 September 2026: the link answers
- 28 September 2026: the link answers
26 files
- .history/
model/ , Python, 122 linesGdata_20250913213729.py - .history/
model/ , Python, 122 linesGdata_20250917110854.py - .history/
model/ , Python, 92 lines, 1 matchMultiEncoder_20250913205 642.py - .history/
model/ , Python, 86 linesMultiEncoder_20250917110 844.py - .history/
utils/ , Python, 177 linespseudo_20250913203511.py - .history/
utils/ , Python, 162 linespseudo_20250917110801.py - .history/
utils/ , Python, 162 linespseudo_20250917110805.py - Demo/
Demo_1.ipynb , Jupyter, 132 lines - Demo/
Demo_2.ipynb , Jupyter, 147 lines - Demo/
Demo_3.ipynb , Jupyter, 204 lines - Demo/
Demo_4.ipynb , Jupyter, 208 lines - model/
Gdata.py , Python, 123 lines - model/
MultiEncoder.py , Python, 86 lines - model/
__init__.py , Python, 1 line - model/
config.py , Python, 63 lines - model/
model.py , Python, 208 lines, 1 match - model/
version.py , Python, 1 line - training/
DataGenerator.py , Python, 114 lines - training/
Model_training.ipynb , Jupyter, 204 lines - utils/
__init__.py , Python, 1 line - utils/
pseudo.py , Python, 201 lines - utils/
psf.py , Python, 116 lines - utils/
utils.py , Python, 46 lines - utils/
zernike.py , Python, 310 lines, 2 matches - LICENSE, License, 21 lines
- Readme.md, Text, 50 lines
Zenodo 19315205
Availability: 1 check, the latest on 28 September 2026: the link answers (HTTP 200)
- 28 September 2026: the link answers (HTTP 200)
26 files
- .history/
model/ , Python, 122 linesGdata_20250913213729.py - .history/
model/ , Python, 122 linesGdata_20250917110854.py - .history/
model/ , Python, 92 linesMultiEncoder_20250913205 642.py - .history/
model/ , Python, 86 linesMultiEncoder_20250917110 844.py - .history/
utils/ , Python, 177 linespseudo_20250913203511.py - .history/
utils/ , Python, 162 linespseudo_20250917110801.py - .history/
utils/ , Python, 162 linespseudo_20250917110805.py - Demo/
Demo_1.ipynb , Jupyter, 132 lines - Demo/
Demo_2.ipynb , Jupyter, 147 lines - Demo/
Demo_3.ipynb , Jupyter, 204 lines - Demo/
Demo_4.ipynb , Jupyter, 208 lines - model/
Gdata.py , Python, 123 lines - model/
MultiEncoder.py , Python, 86 lines - model/
__init__.py , Python, 1 line - model/
config.py , Python, 63 lines - model/
model.py , Python, 208 lines - model/
version.py , Python, 1 line - training/
DataGenerator.py , Python, 114 lines - training/
Model_training.ipynb , Jupyter, 204 lines - utils/
__init__.py , Python, 1 line - utils/
pseudo.py , Python, 201 lines - utils/
psf.py , Python, 116 lines - utils/
utils.py , Python, 46 lines - utils/
zernike.py , Python, 310 lines - LICENSE, License, 21 lines
- Readme.md, Text, 50 lines
Code availability statement
The paper has a code availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:
- it points to the authors' code: lukachan41/
MeNet-AO , Zenodo 17118222, Zenodo 19315205 - it says that the code is available on request
Read it in the paper: doi.org/10.1038/s41467-026-73389-2.
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:
- 3 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
- 48 scripts, each with its path and the digest of its content;
- 4 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:
- it points to the authors' code: lukachan41/
MeNet-AO , Zenodo 17118222, Zenodo 19315205 - it says that the data are available on request
- it says that the code is available on request
Read it in the paper: doi.org/10.1038/s41467-026-73389-2.
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, 5 authors, 2 keywords, 14 MeSH terms, 2 funders, 93 references.
Cite
This paper
Cheng, X., Wang, B., Luo, L., Sun, Z., & He, S. (2026). Physics-informed multi-encoder adaptive optics enables rapid aberration correction for intravital microscopy of deep complex tissue. Nature communications, 17(1), 6651. https://
BibTeX
@article{cheng2026physic
author = {Cheng, Xiangzhang and Wang, Bo and Luo, Li and Sun, Zhaowei and He, Sicong},
title = {{Physics-informed multi-encoder adaptive optics enables rapid aberration correction for intravital microscopy of deep complex tissue}},
journal = {Nature communications},
year = {2026},
month = may,
volume = {17},
number = {1},
pages = {6651},
publisher = {Nature Publishing Group},
issn = {2041-1723},
doi = {10.1038/
url = {https://
pmid = {42161926},
pmcid = {PMC13381939}
}
RIS
TY - JOUR
AU - Cheng, Xiangzhang
AU - Wang, Bo
AU - Luo, Li
AU - Sun, Zhaowei
AU - He, Sicong
TI - Physics-informed multi-encoder adaptive optics enables rapid aberration correction for intravital microscopy of deep complex tissue
T2 - Nature communications
J2 - Nat Commun
PY - 2026
DA - 2026/
VL - 17
IS - 1
SP - 6651
SN - 2041-1723
PB - Nature Publishing Group
DO - 10.1038/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.1038/
"type": "article-journal",
"title": "Physics-informed multi-encoder adaptive optics enables rapid aberration correction for intravital microscopy of deep complex tissue",
"container-title": "Nature communications",
"author": [
{
"family": "Cheng",
"given": "Xiangzhang"
},
{
"family": "Wang",
"given": "Bo"
},
{
"family": "Luo",
"given": "Li"
},
{
"family": "Sun",
"given": "Zhaowei"
},
{
"family": "He",
"given": "Sicong"
}
],
"container-title-short":
"volume": "17",
"issue": "1",
"page": "6651",
"DOI": "10.1038/
"PMID": "42161926",
"PMCID": "PMC13381939",
"ISSN": "2041-1723",
"publisher": "Nature Publishing Group",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
5,
20
]
]
}
}
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:10.1016/j.isci.2026.116769 [code]
- Graph-based modeling of optical system enables adaptive optics on dynamic samples with self-calibration.Journal: iScienceIn common: SciPy, Matplotlib, NumPy, 18 references
- [2] doi:10.1038/s41467-024-48575-9 [code]
- Zero-shot learning enables instant denoising and super-resolution in optical fluorescence microscopy.Journal: Nature communicationsIn common: Keras, OpenCV, SciPy, 1 other tool, histology / microscopy, mouse, 11 references
- [3] doi:10.1038/s41467-025-64251-y [code]
- Rapid adaptive optics enabling near noninvasive high-resolution brain imaging in awake behaving mice.Journal: Nature communicationsIn common: optical imaging (calcium, voltage, 2-photon), histology / microscopy, mouse, 12 references
- [4] doi:10.1073/pnas.2503576122 [code]
- Descattering and image restoration with a transformer-based neural network in deep tissue imaging.Journal: Proceedings of the National Academy of Sciences of the United States of AmericaIn common: OpenCV, Matplotlib, NumPy, optical imaging (calcium, voltage, 2-photon), histology / microscopy, mouse, 8 references
- [5] doi:10.1038/s41592-023-02029-0 [code]
- Deep learning-driven adaptive optics for single-molecule localization microscopy.Journal: Nature methodsIn common: SciPy, Matplotlib, NumPy, histology / microscopy, 8 references
- [6] doi:10.3390/ijms26188770 [code]
- NeuroDecon: A Neural Network-Based Method for Three-Dimensional Deconvolution of Fluorescent Microscopic Images.Journal: International journal of molecular sciencesIn common: Keras, SciPy, Matplotlib, 1 other tool, histology / microscopy, 7 references
- [7] doi:10.1038/s41467-026-73045-9 [code]
- Aberration-aware 3D localization microscopy via self-supervised neural-physics learning.Journal: Nature communicationsIn common: OpenCV, SciPy, Matplotlib, 1 other tool, histology / microscopy, 6 references
- [8] doi:10.1038/s41467-026-69798-y [code]
- Dual deconvolution in multiphoton structured illumination microscopy for deep-tissue super-resolution imaging.Journal: Nature communicationsIn common: optical imaging (calcium, voltage, 2-photon), histology / microscopy, mouse, 7 references
- [9] doi:10.1038/s41377-022-00768-x [code]
- Deep learning autofluorescence-harmoni
c microscopy. Journal: Light, science & applicationsIn common: OpenCV, SciPy, NumPy, optical imaging (calcium, voltage, 2-photon), histology / microscopy, 6 references - [10] doi:10.7554/elife.84853 [code]
- Retinal microvascular and neuronal pathologies probed in vivo by adaptive optical two-photon fluorescence microscopy.Journal: eLifeIn common: optical imaging (calcium, voltage, 2-photon), histology / microscopy, mouse, 7 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.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Validate its tracing map
You validate the map as this page shows it: 3 repositories of the authors' code, each at its verified commit and with its license, 48 scripts, and 4 matches between paragraphs and code (see the Code and Map sections). It then receives a DOI on Zenodo, with you (your ORCID iD) and OSCR as its creators; the code itself is not deposited.
The map's fingerprint: sha256:997b44460014e5c3…
Add the badge to the code's README
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 -->
[](https://openscicode.org/badge/doi/10.1038/s41467-026-73389-2)
<!-- oscr-badge:end -->reStructuredText
.. oscr-badge:start
.. image:: https://openscicode.org/badge/doi/10.1038/s41467-026-73389-2.svg
:target: https://openscicode.org/badge/doi/10.1038/s41467-026-73389-2
:alt: OSCR
.. oscr-badge:endHTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1038/s41467-026-73389-2"><img src="https://openscicode.org/badge/doi/10.1038/s41467-026-73389-2.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.
