OSCR

MIND versus MSN: A systematic evaluation of test-retest reliability and age sensitivity for T1-weighted structural similarity networks.

Code ↔ Paper

5 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.

The 5 matches · 2 of them tie a paragraph to a whole file, not to given lines: weak matches, whose lines are not tinted
  1. [1] § METHODS › Age Sensitivity Analysis ↔ Gao2025_MINDvsMSN/AGE/SVR_func.R, lines 1–28 · score 0.96 · support vector regression, partial Spearman correlation, doRNG, partial Pearson correlation, absolute error, cross validation
  2. [2] § RESULTS ↔ Gao2025_MINDvsMSN/AGE/SVR_func.R, lines 1–28 · score 0.77 · partial Spearman correlation, partial Pearson correlation, absolute error, accuracy metrics, prediction, age
  3. [3] § METHODS › Age Sensitivity Analysis ↔ Gao2025_MINDvsMSN/AGE/calc_CohenD_boot.R, lines 1–60 · score 0.64 · emmeans, bootstrap sample, eNKI, Cohen, variable, sex
  4. [4] § METHODS › Age Sensitivity Analysis ↔ Gao2025_MINDvsMSN/AGE/calc_edge_Sig_CohenD.R, the whole file · a weak match · score 0.58 · emmeans, eNKI, Cohen, FDR, variable, sex
  5. [5] § METHODS › Network Construction ↔ Gao2025_MINDvsMSN/PREPROC/get_Schaefer_label.sh, the whole file · a weak match · score 0.51 · cortical parcellation, FreeSurfer, cortex, Schaefer300, networks, atlas

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

R · 83 lines · 3.6 KB · MIT · 2 matches

  1. ## Custom functions to perform Repeated K-fold Cross-Validated Support Vector Regression
  2. ## Version 1.0.10 / 2025-11-22
  3. ## This version ensures the reproducibility of parallel processing using doRNG package
  4. ## ---------------------------------------------------------------------
  5. ## Function to calculate accuracy metrics
  6. calc_ACC <- function(y_real, y_predict, cov_dat){
  7. ## y_real is the real value of target variable
  8. ## y_predict is the predicted value of target variable
  9. ## cov_dat is the data.frame of covariate variables
  10. ## Partial Pearson correlation
  11. y_real_resid <- resid(lm(y_real ~ ., data = cov_dat))
  12. y_predict_resid <- resid(lm(y_predict ~ ., data = cov_dat))
  13. PPC_dat <- cor(y_real_resid, y_predict_resid)
  14. ## Partial Spearman correlation
  15. cov_dat_rank <- as.data.frame(apply(cov_dat, 2, rank))
  16. y_real_resid <- resid(lm(rank(y_real) ~ ., data = cov_dat_rank))
  17. y_predict_resid <- resid(lm(rank(y_predict) ~ ., data = cov_dat_rank))
  18. PSC_dat <- cor(y_real_resid, y_predict_resid)
  19. ## Mean absolute error
  20. curr_lm_mod <- lm(y_real ~ ., data = cov_dat)
  21. y_real_adjust <- resid(curr_lm_mod) + coef(curr_lm_mod)[1]
  22. curr_lm_mod <- lm(y_predict ~ ., data = cov_dat)
  23. y_predict_adjust <- resid(curr_lm_mod) + coef(curr_lm_mod)[1]
  24. MAE_dat <- mean(abs(y_real_adjust - y_predict_adjust))
  25. ## Combine all metrics
  26. ACC_dat <- c(PPC_dat, PSC_dat, MAE_dat)
  27. return(ACC_dat)
  28. }
  29. ## Evaluate prediction accuracy using all samples or female/male samples
  30. SVR_ACC <- function(y_real, y_predict, cov_dat){
  31. ## Using all samples
  32. all_ACC <- calc_ACC(y_real, y_predict, cov_dat)
  33. ## Using female samples
  34. female_idx <- cov_dat$Sex == 'F'
  35. female_ACC <- calc_ACC(y_real[female_idx], y_predict[female_idx], cov_dat[female_idx, -1])
  36. ## Using male samples
  37. male_idx <- cov_dat$Sex == 'M'
  38. male_ACC <- calc_ACC(y_real[male_idx], y_predict[male_idx], cov_dat[male_idx, -1])
  39. ## Combine all metrics
  40. ACC_dat <- c(all_ACC, female_ACC, male_ACC)
  41. return(ACC_dat)
  42. }
  43. ## ---------------------------------------------------------------------
  44. ## Repeated K-fold CV
  45. SVR_CV <- function(x, y, z, K=5, N=4, myseed=1){
  46. ## x is a matrix or dataframe of predictors, in which row means observation and column means variable
  47. ## y is a vector of target variable
  48. ## z is a dataframe of covariates, in which row means observation and column means variable
  49. ## K means K-fold CV
  50. ## N means the N repetitions of K-fold CV
  51. ## myseed means the random seed
  52. ## Set random seed to ensure reproducibility
  53. set.seed(myseed)
  54. ## Randomly split the data into K folds and repeat N times
  55. all_folds <- matrix(0, nrow=length(y), ncol=N)
  56. for (col_idx in c(1:N)){
  57. all_folds[,col_idx] <- createFolds(y, k=K, list = FALSE)
  58. }
  59. ## Loop each run of train-test procedure
  60. M <- N * K
  61. output <- foreach(curr_run = 1:M, .combine='rbind') %dorng% {
  62. curr_rep <- (curr_run - 1) %/% K + 1
  63. curr_fold <- (curr_run - 1) %% K + 1
  64. ## sub_idx means the subject position index of the current fold
  65. sub_idx <- which(all_folds[, curr_rep] == curr_fold)
  66. x_train <- x[-sub_idx,]
  67. y_train <- y[-sub_idx]
  68. x_test <- x[sub_idx,,drop=FALSE]
  69. y_test <- y[sub_idx]
  70. z_test <- z[sub_idx,,drop=FALSE]
  71. ## Fit SVR model with hyper-parameter tuning
  72. model_tune <- tune(svm, x_train, y_train, kernel='linear',
  73. ranges = list(epsilon = c(0.01, 0.1, 0.5, 1), cost = c(0.1, 1, 10, 100, 1000)),
  74. tunecontrol = tune.control(nrepeat = 1, sampling = "cross", cross=K))
  75. model_train <- model_tune$best.model
  76. ## Predict
  77. y_predict <- predict(model_train, x_test)
  78. ## Evaluate performance
  79. SVR_ACC(y_test, y_predict, z_test)
  80. }
  81. return(output)
  82. }

SVR_func.R at commit 3dc9bdd, under MIT · at the source

Overview

Authors: Jiaqi Gao1,2, Yang Hu3
ORCID iDs: Yang Hu
  1. Faculty of Psychology, Shandong Normal University, Jinan, China
  2. Shandong Provincial Key Laboratory of Brain Science and Mental Health, Jinan, China
  3. Independent Researcher
Institutions: Shandong Normal University (China)
Journal: Network neuroscience (Cambridge, Mass.), volume 10, issue 3, pages 613-629
Dates: received 15 October 2025; accepted 12 February 2026; published online 20 July 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1162/netn.a.553 · PMID 42529723 · PMCID PMC13418519 · OpenAlex W7131659985
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: structural MRI / diffusion (modality), human (organism)
Methods: Connectivity, Statistics, Machine learning, fMRI & imaging, Physiology & signal measures
Keywords: MSN, MIND, Test–retest reliability, Age sensitivity, Structural similarity network, T1-weighted MRI
Topic: Functional Brain Connectivity Studies (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Funding: Shandong Provincial Natural Science Foundation (Youth Program ZR2023QC226); Youth Innovation Team Program of Shandong Universities (2022KJ252)
Citations: not cited yet (Europe PMC); 44 references in the paper

Abstract

Constructing structural similarity networks from T1-weighted MRI offers a powerful means to characterize brain organization. Two prominent methods for constructing such networks, Morphometric Similarity Network (MSN) and Morphometric INverse Divergence (MIND), have been proposed. However, a systematic evaluation of the test–retest reliability and age sensitivity of both MIND and MSN is still lacking. The present study comprehensively assessed these properties to inform the reliability and validity of both approaches. Test–retest reliability was evaluated by the intraclass correlation coefficient (ICC) using two public datasets containing repeated MRI scans. Age sensitivity was examined by conducting edge-wise comparisons between younger and older age groups, as well as by training machine learning models to predict individual age, using two public lifespan datasets. Additionally, several practical variants of MIND and MSN were explored by constructing networks with different morphological feature sets. Results demonstrated that MSN exhibited higher test–retest reliability, whereas MIND showed greater age sensitivity when both methods employed the same five features. Both methods revealed distinct spatial patterns that differentiate older from younger adults. Notably, the choice of feature sets substantially influenced reliability and age sensitivity. These findings offer empirical guidance for methodological selection and highlight the importance of feature optimization in future studies.

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 5 matches between paragraphs and lines of code.

younghoo/paper-scripts

License: MIT
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 3dc9bdda513647d6be374701efc10d79ecf15da2, 5 March 2026
Languages: R (20), Shell (11), Python (1)
Size: 34 files, 32 scripts
Software Heritage: not archived
Found in: “DATA AND CODE AVAILABILITY”
Holds: license file
Not found: README, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: FreeSurfer (5 files), tidyverse (5 files), emmeans (2 files), caret (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
33 files
At the source: github.com/younghoo/paper-scripts/tree/main/Gao2025_MINDvsMSN

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;
  • 32 scripts, each with its path and the digest of its content;
  • 5 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 and code availability

All MRI datasets are publicly available. The BNU1 and HNU1 datasets are available at https://fcon_1000.projects.nitrc.org/indi/CoRR/html/index.html, the eNKI dataset is available at https://fcon_1000.projects.nitrc.org/indi/enhanced/index.html, and the Cam-CAN dataset is available at https://cam-can.mrc-cbu.cam.ac.uk/dataset/.

The core code necessary to replicate the key data analyses is provided in the Supporting Information. The original scripts used to generate the results reported in this study are publicly available in the following GitHub repository: https://github.com/younghoo/paper-scripts/tree/main/Gao2025_MINDvsMSN.

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, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 2 authors, 6 keywords, 2 funders, 44 references.

Cite

This paper

Gao, J., & Hu, Y. (2026). MIND versus MSN: A systematic evaluation of test-retest reliability and age sensitivity for T1-weighted structural similarity networks. Network neuroscience (Cambridge, Mass.), 10(3), 613-629. https://doi.org/10.1162/netn.a.553

BibTeX

@article{gao2026mind,
author = {Gao, Jiaqi and Hu, Yang},
title = {{MIND versus MSN: A systematic evaluation of test-retest reliability and age sensitivity for T1-weighted structural similarity networks}},
journal = {Network neuroscience (Cambridge, Mass.)},
year = {2026},
month = jul,
volume = {10},
number = {3},
pages = {613--629},
publisher = {MIT Press},
issn = {2472-1751},
doi = {10.1162/netn.a.553},
url = {https://doi.org/10.1162/netn.a.553},
pmid = {42529723},
pmcid = {PMC13418519}
}

RIS

TY - JOUR
AU - Gao, Jiaqi
AU - Hu, Yang
TI - MIND versus MSN: A systematic evaluation of test-retest reliability and age sensitivity for T1-weighted structural similarity networks
T2 - Network neuroscience (Cambridge, Mass.)
J2 - Netw Neurosci
PY - 2026
DA - 2026/07/20
VL - 10
IS - 3
SP - 613
EP - 629
SN - 2472-1751
PB - MIT Press
DO - 10.1162/netn.a.553
UR - https://doi.org/10.1162/netn.a.553
LA - en
ER -

CSL-JSON

{
"id": "10.1162/netn.a.553",
"type": "article-journal",
"title": "MIND versus MSN: A systematic evaluation of test-retest reliability and age sensitivity for T1-weighted structural similarity networks",
"container-title": "Network neuroscience (Cambridge, Mass.)",
"author": [
{
"family": "Gao",
"given": "Jiaqi"
},
{
"family": "Hu",
"given": "Yang"
}
],
"container-title-short": "Netw Neurosci",
"volume": "10",
"issue": "3",
"page": "613-629",
"DOI": "10.1162/netn.a.553",
"PMID": "42529723",
"PMCID": "PMC13418519",
"ISSN": "2472-1751",
"publisher": "MIT Press",
"URL": "https://doi.org/10.1162/netn.a.553",
"language": "en",
"issued": {
"date-parts": [
[
2026,
7,
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:10.1038/s42003-026-10276-y [code]
The cellular correlates and adolescent reorganisation of cortical myelination networks in the common marmoset.
Journal: Communications biology
In common: FreeSurfer, tidyverse, structural MRI / diffusion, 8 references
[2] doi:10.1162/netn.a.546 [code]
Cortical similarity networks in the rat brain: Postnatal development and sensitivity to early life stress.
Journal: Network neuroscience (Cambridge, Mass.)
In common: tidyverse, structural MRI / diffusion, 7 references
[3] doi:10.1162/imag.a.1322 [code]
Fine-scale individualized gyral folding-based cortical similarity networks reveal distinct organizational patterns in Alzheimer's disease and Lewy body dementia.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: structural MRI / diffusion, 8 references
[4] doi:10.1038/s42003-026-10237-5 [code]
Shared subcortical-default mode morphological dysconnectivity in adolescent bipolar disorder, major depressive disorder and schizophrenia.
Journal: Communications biology
In common: 7 references
[5] doi:10.1038/s41467-026-73714-9 [code]
The genetic architecture of cortical similarity networks.
Journal: Nature communications
In common: FreeSurfer, tidyverse, structural MRI / diffusion, 5 references
[6] doi:10.1038/s41467-026-74153-2 [code]
Regional, functional and transcriptomic decoding of multidimensional brain structure alterations in obsessive-compulsive disorder.
Journal: Nature communications
In common: FreeSurfer, tidyverse, 5 references
[7] doi:10.1038/s41398-026-04025-2 [code]
Brain energetic landscapes shape state dysregulation in major depressive disorder: a morphological network controllability perspective.
Journal: Translational psychiatry
In common: FreeSurfer, 5 references
[8] doi:10.1126/sciadv.aec2348 [code]
Congenital blindness reduces myelination in human visual cortex.
Journal: Science advances
In common: emmeans, FreeSurfer, tidyverse, structural MRI / diffusion, 2 references
[9] doi:10.1038/s41467-026-74824-0 [code]
Learning regularities in noise engages both neural predictive activity and representational changes.
Journal: Nature communications
In common: emmeans, FreeSurfer, tidyverse, 3 references
[10] doi:10.1002/hbm.70627 [code]
Investigating the Contribution of Molecular-Enriched Functional Connectivity to Brain-Age Analysis.
Journal: Human brain mapping
In common: structural MRI / diffusion, 5 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.

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.