Pith. sign in

REVIEW 2 major objections 2 minor 1 cited by

NEXUS deploys specialist agents to build, execute, and adapt neuroimaging analysis programs that respond to runtime evidence.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-06-30 22:42 UTC pith:ZQROUJKI

load-bearing objection NEXUS puts multi-agent code synthesis and hierarchical checks into neuroimaging pipelines with public code available, but the abstract gives no numbers or stats to back the performance claims. the 2 major comments →

arxiv 2605.09366 v3 pith:ZQROUJKI submitted 2026-05-10 cs.AI

Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration

Keqi Han , Songlin Zhao , Yao Su , Xiang Li , Yixuan Yuan , Lifang He , Carl Yang This is my paper
classification cs.AI
keywords neuroimaging analysismulti-agent systemsautonomous workflowsADHD-200ADNIworkflow adaptationhierarchical verificationcode-centric execution
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Standard workflows such as fMRIPrep run on fixed configurations and cannot adjust strategies when intermediate results suggest better paths or when failures appear. NEXUS fills the gap by letting multiple agents jointly write and refine executable code that incorporates domain primitives and reacts to what the code actually produces during runs. A layered verification step checks both summary metrics across a cohort and visual details to decide whether and how to revise the workflow. On the ADHD-200 and ADNI collections the resulting pipelines reach higher predictive accuracy than fixed baselines while showing behaviors such as trying alternate analysis routes and correcting course mid-process.

Core claim

The paper introduces NEXUS, an autonomous multi-agent framework that merges neuroimaging workflow execution with scientific-objective understanding. Specialist agents collaborate to synthesize and optimize executable programs over composable domain-specific primitives, supporting long-horizon construction that adapts to runtime observations. A hierarchical verification framework combines cohort-level metric screening with agentic visual inspection to produce evidence-grounded workflow remediation.

What carries the argument

The code-centric multi-agent execution paradigm in which specialist agents collaboratively synthesize executable programs, paired with hierarchical verification that links metric screening to visual inspection for remediation.

Load-bearing premise

The multi-agent system can reliably translate runtime observations into correct workflow changes without creating new undetected errors or biases that static pipelines already avoid.

What would settle it

Run NEXUS on a fresh neuroimaging cohort and compare its final predictive performance and error-remediation success rate against the same static baseline pipelines; if the multi-agent version shows lower accuracy or leaves more undetected failures, the central claim is falsified.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Analysis pipelines can change their own steps mid-process instead of requiring external manual edits.
  • The labor of repeated trial-and-error parameter tuning and failure fixes shrinks because agents close the observation-to-remediation loop.
  • Predictive models trained on the output of these adaptive workflows reach higher accuracy on ADHD-200 and ADNI than models from fixed pipelines.
  • Agent behaviors such as exploring alternative strategies and performing adaptive refinement become reproducible parts of the analysis record.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same agentic code-synthesis pattern could be tested on other high-dimensional scientific data streams that currently rely on static preprocessing pipelines.
  • If verification agents can be trained on larger archives of past neuroimaging failures, the remediation step might become more robust across institutions.
  • Over repeated runs the system could accumulate reusable program fragments that shorten construction time for similar future studies.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

2 major / 2 minor

Summary. The manuscript introduces NEXUS, a multi-agent framework for autonomous neuroimaging analysis. It uses a code-centric paradigm where specialist agents collaboratively synthesize and optimize executable programs over domain-specific primitives, combined with a hierarchical verification framework that integrates cohort-level metric screening and agentic visual inspection. Experiments on the ADHD-200 and ADNI datasets are reported to show that NEXUS outperforms standard workflow-based baselines (such as fMRIPrep) in predictive performance while demonstrating agentic behaviors including strategy exploration and adaptive refinement. Public code is provided.

Significance. If the empirical claims hold with rigorous quantification, the work could advance automated, closed-loop neuroimaging pipelines that adapt to runtime observations and downstream objectives, addressing limitations of static workflows. The code-centric multi-agent design and public repository are strengths for reproducibility and extension.

major comments (2)
  1. [Abstract, Experiments] Abstract and Experiments section: The central claim that NEXUS 'outperforms standard workflow-based baselines in predictive performance' is stated without any reported metrics (accuracy, AUC, effect sizes), error bars, dataset sizes, statistical tests, or baseline configuration details. This absence prevents evaluation of the magnitude, reliability, or statistical significance of the reported gains and is load-bearing for the primary empirical contribution.
  2. [NEXUS design, hierarchical verification framework] NEXUS design and hierarchical verification: The description of how the multi-agent code synthesis closes the loop between runtime observations and workflow remediation (including failure modes or bias introduction) remains at a high level without concrete algorithms, pseudocode, or ablation studies showing that the agentic loop improves upon static pipelines rather than introducing undetected errors.
minor comments (2)
  1. [Abstract] The abstract mentions 'sophisticated agentic behaviors' but provides no examples or quantification of strategy exploration or adaptive refinement; adding a brief illustrative case from the results would improve clarity.
  2. [Methods] Notation for agent roles and verification stages could be formalized with a diagram or table to aid readability, as the current prose description of the multi-agent hierarchy is dense.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive comments, which highlight important areas for improving the clarity and rigor of our empirical claims and framework description. We will revise the manuscript to incorporate quantitative details and additional technical specifications as outlined below.

read point-by-point responses

  1. Referee: [Abstract, Experiments] Abstract and Experiments section: The central claim that NEXUS 'outperforms standard workflow-based baselines in predictive performance' is stated without any reported metrics (accuracy, AUC, effect sizes), error bars, dataset sizes, statistical tests, or baseline configuration details. This absence prevents evaluation of the magnitude, reliability, or statistical significance of the reported gains and is load-bearing for the primary empirical contribution.

    Authors: We agree that the abstract and the high-level experiments summary lack the specific quantitative details needed for rigorous evaluation. The full manuscript includes performance tables comparing NEXUS against fMRIPrep and other baselines on ADHD-200 and ADNI, but these are not sufficiently highlighted or quantified in the abstract and introductory results paragraphs. In the revision, we will expand the abstract to include key metrics (e.g., accuracy, AUC with standard deviations), report dataset sizes explicitly, include statistical tests (such as paired t-tests with p-values), effect sizes, and detailed baseline configurations (e.g., default fMRIPrep parameters and preprocessing steps). This will enable direct assessment of the gains' magnitude and reliability. revision: yes

  2. Referee: [NEXUS design, hierarchical verification framework] NEXUS design and hierarchical verification: The description of how the multi-agent code synthesis closes the loop between runtime observations and workflow remediation (including failure modes or bias introduction) remains at a high level without concrete algorithms, pseudocode, or ablation studies showing that the agentic loop improves upon static pipelines rather than introducing undetected errors.

    Authors: We acknowledge that the current description of the code-centric multi-agent synthesis and hierarchical verification (cohort-level metric screening combined with agentic visual inspection) is primarily at a conceptual level. To address this, the revised manuscript will include pseudocode for the specialist agent collaboration and remediation loop, explicit algorithms detailing how runtime observations trigger workflow adjustments, and ablation studies comparing the full NEXUS system against ablated versions (e.g., without the verification framework or without adaptive strategy exploration). These will quantify improvements in predictive performance and error remediation while addressing potential bias introduction. The public code repository already contains the implementations, which we will reference with specific file paths and module descriptions in the revision. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper presents an empirical framework (NEXUS) whose central claim rests on reported performance comparisons against baselines on the public ADHD-200 and ADNI datasets. No equations, fitted parameters, uniqueness theorems, or self-citations appear in the abstract or description; the validation is framed as external experimental results rather than any internal reduction of predictions to inputs by construction. The derivation chain is therefore self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract provides no explicit free parameters, axioms, or invented entities; the framework is described at the level of high-level design choices whose concrete realizations are not detailed.

pith-pipeline@v0.9.1-grok · 5788 in / 1094 out tokens · 21931 ms · 2026-06-30T22:42:51.790291+00:00 · methodology

0 comments
read the original abstract

Transforming neuroimaging data into clinically actionable biomarkers is a knowledge-intensive and labor-intensive process. Standardized workflows such as fMRIPrep have improved robustness and efficiency, but they are statically configured and cannot reason about downstream objectives, deliberate over alternative strategies, or close the loop between intermediate evidence and subsequent decisions in the way a human researcher would. This lack of closed-loop adaptation often leaves domain experts trapped in a cycle of manual trial-and-error to tune parameters and remediate pipeline failures, severely constraining the scalability of clinical biomarker development. To bridge this gap, we introduce NEXUS, an autonomous multi-agent framework that integrates neuroimaging workflow execution with scientific-objective understanding. Unlike conventional flat toolcalling agents, NEXUS adopts a code-centric execution paradigm where specialist agents collaboratively synthesize and optimize executable programs over composable domain-specific primitives. This design enables robust, long-horizon workflow construction that adapts dynamically to runtime observations. Furthermore, we propose a hierarchical verification framework for autonomous quality control, integrating cohort-level metric screening with agentic visual inspection to drive evidence-grounded workflow remediation. Experiments on ADHD-200 and ADNI demonstrate that NEXUS outperforms standard workflow-based baselines in predictive performance while exhibiting sophisticated agentic behaviors, including strategy exploration and adaptive refinement. The code is available at https://github.com/LearningKeqi/Virtual-Neuroscientist-NEXUS.

Figures

Figures reproduced from arXiv: 2605.09366 by Carl Yang, Keqi Han, Lifang He, Songlin Zhao, Xiang Li, Yao Su, Yixuan Yuan.

Figure 1
Figure 1. Figure 1: Overview of the NIAgent framework. LLM Agents for Scientific Workflows. Recent work has increasingly explored LLM agents not only for general tool use, but also for scientific discovery and domain-specialized research automation. For example, ReAct [11] established a general reasoning-and-acting paradigm, while subsequent systems explored multi-agent collaboration and executable-code-based action spaces su… view at source ↗
Figure 2
Figure 2. Figure 2: Ablation study results. Stacked bars show total execution errors across five independent [PITH_FULL_IMAGE:figures/full_fig_p008_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Evaluation of the closed loop autonomous QC module. [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Example questionnaire page used for human evaluation in the QC agreement study, shown [PITH_FULL_IMAGE:figures/full_fig_p024_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Example visualization used for raw T1w visual QC. The figure is a mosaic view from the [PITH_FULL_IMAGE:figures/full_fig_p034_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Example visualization used for T1w skull-stripping QC. The red contour shows the extracted [PITH_FULL_IMAGE:figures/full_fig_p035_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Example visualization used for T1w tissue-segmentation QC. Red indicates the brain mask, [PITH_FULL_IMAGE:figures/full_fig_p036_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Example visualization used for T1w-to-MNI normalization QC. The red outlines correspond [PITH_FULL_IMAGE:figures/full_fig_p037_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Example visualization used for raw fMRI visual QC. The figure shows the MRIQC mosaic [PITH_FULL_IMAGE:figures/full_fig_p037_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Example visualization used for fMRI-to-T1w co-registration QC. The red contours [PITH_FULL_IMAGE:figures/full_fig_p038_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Example visualization used for fMRI-to-MNI normalization QC. The red contours [PITH_FULL_IMAGE:figures/full_fig_p039_11.png] view at source ↗

Review history (3 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs

    cs.AI 2026-05 unverdicted novelty 6.0

    EHRBench uses an EHR-LLM-KB pipeline to automatically create 960,067 reliable QA items spanning diagnosis, treatment, and prognosis for large-scale LLM evaluation in clinical decision making.

Reference graph

Works this paper leans on

55 extracted references · 5 canonical work pages · cited by 1 Pith paper · 4 internal anchors

  1. [1]

    The brain imaging data structure, a format for organizing and describing outputs of neuroimaging experiments.Scientific data, 3(1):1–9, 2016

    Krzysztof J Gorgolewski, Tibor Auer, Vince D Calhoun, R Cameron Craddock, Samir Das, Eugene P Duff, Guillaume Flandin, Satrajit S Ghosh, Tristan Glatard, Yaroslav O Halchenko, et al. The brain imaging data structure, a format for organizing and describing outputs of neuroimaging experiments.Scientific data, 3(1):1–9, 2016

    2016

  2. [2]

    fmriprep: a robust preprocessing pipeline for functional mri.Nature methods, 16(1):111–116, 2019

    Oscar Esteban, Christopher J Markiewicz, Ross W Blair, Craig A Moodie, A Ilkay Isik, Asier Erramuzpe, James D Kent, Mathias Goncalves, Elizabeth DuPre, Madeleine Snyder, et al. fmriprep: a robust preprocessing pipeline for functional mri.Nature methods, 16(1):111–116, 2019

    2019

  3. [3]

    A comprehensive overview of large language models.ACM Transactions on Intelligent Systems and Technology, 16(5):1–72, 2025

    Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Naveed Akhtar, Nick Barnes, and Ajmal Mian. A comprehensive overview of large language models.ACM Transactions on Intelligent Systems and Technology, 16(5):1–72, 2025

    2025

  4. [4]

    arXiv preprint arXiv:2503.08979 , year=

    Mourad Gridach, Jay Nanavati, Khaldoun Zine El Abidine, Lenon Mendes, and Christina Mack. Agentic ai for scientific discovery: A survey of progress, challenges, and future directions. arXiv preprint arXiv:2503.08979, 2025

    work page arXiv 2025

  5. [5]

    The adhd-200 consortium: a model to advance the translational potential of neuroimaging in clinical neuroscience.Frontiers in systems neuroscience, 6:62, 2012

    ADHD-200 consortium. The adhd-200 consortium: a model to advance the translational potential of neuroimaging in clinical neuroscience.Frontiers in systems neuroscience, 6:62, 2012

    2012

  6. [6]

    Alzheimer’s disease neuroimaging initiative (adni) clinical characterization.Neurology, 74(3):201–209, 2010

    Ronald Carl Petersen, Paul S Aisen, Laurel A Beckett, Michael C Donohue, Anthony Collins Gamst, Danielle J Harvey, Clifford R Jack Jr, William J Jagust, Leslie M Shaw, Arthur W Toga, et al. Alzheimer’s disease neuroimaging initiative (adni) clinical characterization.Neurology, 74(3):201–209, 2010

    2010

  7. [7]

    Freesurfer.Neuroimage, 62(2):774–781, 2012

    Bruce Fischl. Freesurfer.Neuroimage, 62(2):774–781, 2012

    2012

  8. [8]

    Brainsuite: an automated cortical surface identification tool.Medical image analysis, 6(2):129–142, 2002

    David W Shattuck and Richard M Leahy. Brainsuite: an automated cortical surface identification tool.Medical image analysis, 6(2):129–142, 2002

    2002

  9. [9]

    Nipype: a flexible, lightweight and extensible neuroimaging data processing framework in python.Frontiers in neuroinformatics, 5:13, 2011

    Krzysztof Gorgolewski, Christopher D Burns, Cindee Madison, Dav Clark, Yaroslav O Halchenko, Michael L Waskom, and Satrajit S Ghosh. Nipype: a flexible, lightweight and extensible neuroimaging data processing framework in python.Frontiers in neuroinformatics, 5:13, 2011

    2011

  10. [10]

    Mriqc: Advancing the automatic prediction of image quality in mri from unseen sites.PloS one, 12(9):e0184661, 2017

    Oscar Esteban, Daniel Birman, Marie Schaer, Oluwasanmi O Koyejo, Russell A Poldrack, and Krzysztof J Gorgolewski. Mriqc: Advancing the automatic prediction of image quality in mri from unseen sites.PloS one, 12(9):e0184661, 2017

    2017

  11. [11]

    React: Synergizing reasoning and acting in language models

    Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. React: Synergizing reasoning and acting in language models. InInternational Conference on Learning Representations (ICLR), 2023

    2023

  12. [12]

    Executable code actions elicit better llm agents

    Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, and Heng Ji. Executable code actions elicit better llm agents. InForty-first International Conference on Machine Learning, 2024

    2024

  13. [13]

    The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

    Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, and David Ha. The ai scien- tist: Towards fully automated open-ended scientific discovery.arXiv preprint arXiv:2408.06292, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  14. [14]

    ChemCrow: Augmenting large-language models with chemistry tools

    Andres M Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D White, and Philippe Schwaller. Chemcrow: Augmenting large-language models with chemistry tools.arXiv preprint arXiv:2304.05376, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  15. [15]

    Biomni: A general-purpose biomedical ai agent

    Kexin Huang, Serena Zhang, Hanchen Wang, Yuanhao Qu, Yingzhou Lu, Yusuf Roohani, Ryan Li, Lin Qiu, Gavin Li, Junze Zhang, et al. Biomni: A general-purpose biomedical ai agent. biorxiv, 2025. 10

    2025

  16. [16]

    Medrax: Medical reasoning agent for chest x-ray

    Adibvafa Fallahpour, Jun Ma, Alif Munim, Hongwei Lyu, and Bo Wang. Medrax: Medical reasoning agent for chest x-ray. InInternational Conference on Machine Learning, pages 15661–15676. PMLR, 2025

    2025

  17. [17]

    Neura: An agentic system for autonomous neuroimaging workflows

    Jun Xie, Jing Wang, Xiumei Wu, Xinyuan Liu, Yiqi Mi, Qinjin Liu, Tong Xu, Chen Liu, Huafu Chen, and Jing Guo. Neura: An agentic system for autonomous neuroimaging workflows. bioRxiv, pages 2026–04, 2026

    2026

  18. [18]

    NeuroClaw Technical Report

    Cheng Wang, Zhibin He, Zhihao Peng, Shengyuan Liu, Yufan Hu, Lichao Sun, Xiang Li, and Yixuan Yuan. Neuroclaw technical report.arXiv preprint arXiv:2604.24696, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  19. [19]

    Agentic Large Language Models for Training-Free Neuro-Radiological Image Analysis

    Ayhan Can Erdur, Daniel Scholz, Jiazhen Pan, Benedikt Wiestler, Daniel Rueckert, and Jan C Peeken. Agentic large language models for training-free neuro-radiological image analysis. arXiv preprint arXiv:2604.16729, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  20. [20]

    Afni: software for analysis and visualization of functional magnetic resonance neuroimages.Computers and Biomedical research, 29(3):162–173, 1996

    Robert W Cox. Afni: software for analysis and visualization of functional magnetic resonance neuroimages.Computers and Biomedical research, 29(3):162–173, 1996

    1996

  21. [21]

    FSL.NeuroImage, 62(2):782–790, 2012

    Mark Jenkinson, Christian F Beckmann, Timothy E J Behrens, Mark W Woolrich, and Stephen M Smith. FSL.NeuroImage, 62(2):782–790, 2012

    2012

  22. [22]

    Spm12 manual

    John Ashburner, Gareth Barnes, Chun-Chuan Chen, Jean Daunizeau, Guillaume Flandin, Karl Friston, Stefan Kiebel, James Kilner, Vladimir Litvak, Rosalyn Moran, et al. Spm12 manual. Wellcome Trust Centre for Neuroimaging, London, UK, 2464(4):53, 2014

    2014

  23. [23]

    Advanced normalization tools (ants).Insight j, 2(365):1–35, 2009

    Brian B Avants, Nick Tustison, Gang Song, et al. Advanced normalization tools (ants).Insight j, 2(365):1–35, 2009

    2009

  24. [24]

    Computing inter-rater reliability and its variance in the presence of high agreement.British Journal of Mathematical and Statistical Psychology, 61(1):29–48, 2008

    Kilem Li Gwet. Computing inter-rater reliability and its variance in the presence of high agreement.British Journal of Mathematical and Statistical Psychology, 61(1):29–48, 2008

    2008

  25. [25]

    Improved optimization for the robust and accurate linear registration and motion correction of brain images.NeuroImage, 17(2):825–841, 2002

    Mark Jenkinson, Peter Bannister, Michael Brady, and Stephen Smith. Improved optimization for the robust and accurate linear registration and motion correction of brain images.NeuroImage, 17(2):825–841, 2002

    2002

  26. [26]

    Statistical Parametric Mapping: The Analysis of Functional Brain Images

    William D Penny, Karl J Friston, John T Ashburner, Stefan J Kiebel, and Thomas E Nichols. Statistical Parametric Mapping: The Analysis of Functional Brain Images. Elsevier, 2011

    2011

  27. [27]

    Fast robust automated brain extraction.Human Brain Mapping, 17(3): 143–155, 2002

    Stephen M Smith. Fast robust automated brain extraction.Human Brain Mapping, 17(3): 143–155, 2002

    2002

  28. [28]

    Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm.IEEE Transactions on Medical Imaging, 20(1):45–57, 2001

    Yongyue Zhang, Michael Brady, and Stephen Smith. Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm.IEEE Transactions on Medical Imaging, 20(1):45–57, 2001

    2001

  29. [29]

    Symmetric diffeo- morphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain.Medical Image Analysis, 12(1):26–41, 2008

    Brian B Avants, Charles L Epstein, Murray Grossman, and James C Gee. Symmetric diffeo- morphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain.Medical Image Analysis, 12(1):26–41, 2008

    2008

  30. [30]

    A reproducible evaluation of ANTs similarity metric performance in brain image registration

    Brian B Avants, Nicholas J Tustison, Gang Song, Philip A Cook, Arno Klein, and James C Gee. A reproducible evaluation of ANTs similarity metric performance in brain image registration. NeuroImage, 54(3):2033–2044, 2011

    2033

  31. [31]

    N4ITK: improved N3 bias correction.IEEE Transactions on Medical Imaging, 29(6):1310–1320, 2010

    Nicholas J Tustison, Brian B Avants, Philip A Cook, Yuanjie Zheng, Alexander Egan, Paul A Yushkevich, and James C Gee. N4ITK: improved N3 bias correction.IEEE Transactions on Medical Imaging, 29(6):1310–1320, 2010

    2010

  32. [32]

    An open source multivariate framework for n-tissue segmentation with evaluation on public data.Neuroinfor- matics, 9(4):381–400, 2011

    Brian B Avants, Nicholas J Tustison, Jue Wu, Philip A Cook, and James C Gee. An open source multivariate framework for n-tissue segmentation with evaluation on public data.Neuroinfor- matics, 9(4):381–400, 2011

    2011

  33. [33]

    Automated anatomical labeling of activations in spm using a macroscopic anatomical parcellation of the mni mri single-subject brain.Neuroimage, 2002

    Nathalie Tzourio-Mazoyer, Brigitte Landeau, Dimitri Papathanassiou, Fabrice Crivello, Octave Etard, Nicolas Delcroix, Bernard Mazoyer, and Marc Joliot. Automated anatomical labeling of activations in spm using a macroscopic anatomical parcellation of the mni mri single-subject brain.Neuroimage, 2002. 11

    2002

  34. [34]

    Local-global parcellation of the human cerebral cortex from intrinsic functional connectivity mri.Cerebral Cortex, 2017

    Alexander Schaefer, Ru Kong, Evan Gordon, Timothy Laumann, Xinian Zuo, Avram Holmes, Simon Eickhoff, and T Thomas Yeo. Local-global parcellation of the human cerebral cortex from intrinsic functional connectivity mri.Cerebral Cortex, 2017

    2017

  35. [35]

    A multi-modal parcellation of human cerebral cortex.Nature, 2016

    Matthew F Glasser, Timothy S Coalson, Emma C Robinson, Carl Hacker, John Harwell, Essa Yacoub, Kamil Ugurbil, Jesper Andersson, Christian F Beckmann, Mark Jenkinson, et al. A multi-modal parcellation of human cerebral cortex.Nature, 2016

    2016

  36. [36]

    Brain network transformer

    Xuan Kan, Wei Dai, Hejie Cui, Zilong Zhang, Ying Guo, and Carl Yang. Brain network transformer. InNeurIPS, 2022

    2022

  37. [37]

    Bayrak, Tyler Derr, Mudassir Shabbir, Daniel Moyer, Catie Chang, and Xenofon Koutsoukos

    Anwar Said, Roza G. Bayrak, Tyler Derr, Mudassir Shabbir, Daniel Moyer, Catie Chang, and Xenofon Koutsoukos. Neurograph: benchmarks for graph machine learning in brain connectomics. InNeurIPS, 2023. 12 A End-to-End Autonomous Neuroimaging Analysis Experiments Details A.1 Task Descriptions of the End-to-End Neuroimaging Analysis We evaluate NEXUS in an end...

    2023

  38. [38]

    A complete neuroimaging preprocessing pipeline

  39. [40]

    The provided dataset should be treated as training set

    The corresponding inference script that can load the trained model and produce predictions on the held-out test set. The provided dataset should be treated as training set. Your delivered preprocessing pipeline and model will be applied to another held-out test set of subjects (which is invisible to you). Your performance will be evaluated based on the pr...

  40. [41]

    A complete neuroimaging preprocessing pipeline. 13

  41. [42]

    Trained downstream prediction model

  42. [43]

    Remove QC

    The corresponding inference script that can load the trained model(s) and produce predictions on the held-out test set. The provided dataset should be treated as training set. Your delivered preprocessing pipeline and model will be applied to another held-out test set of subjects (which is invisible to you). Your performance will be evaluated based on the...

    2009

  43. [44]

    Run MRIQC to obtain Image Quality Metrics (IQMs) and corresponding visual inspection outputs for each subject

  44. [45]

    Use the metrics to identify subjects with abnormal values

  45. [46]

    Perform visual inspection only on the small subset of subjects flagged as abnormal

  46. [47]

    For each subject, review only the most critical images and provide a final judgment. At the end of this stage, you must report the before-preprocessing QC results to the supervisor: Which subjects have data quality that is too poor and should be excluded from further processing, while the rest of the subjects can proceed to subsequent processing and analy...

  47. [48]

    For each preprocessing step that requires QC, compute the metrics relevant to that specific step only

  48. [49]

    For each preprocessing step separately, identify outlier subjects based only on that step’s own metrics (e.g., the most abnormal 15% for that step)

  49. [50]

    For each preprocessing step separately, perform visual inspection only on the subjects flagged for that same step. 27

  50. [51]

    A subject may therefore receive visual QC for one step but not for another, depending on which step-specific metric screen flagged that subject

  51. [52]

    verdict": Literal[

    After the step-specific visual inspections are completed, aggregate the per-step QC decisions into the final subject-level judgment and clearly report which preprocessing step(s) failed for each rejected subject. --- Note that the neuroimaging processing pipeline may involve many different steps. You only need to perform QC for the specific processing ste...

  52. [53]

    First, write the Python script and use this script to process **a set of sampled subjects (for example, 10 subjects)** to test the validity of the script

  53. [54]

    - If the any expected derivatives files are missing, check the script or logs

    Check the results of these subjects to see whether any expected derivatives files are missing. - If the any expected derivatives files are missing, check the script or logs. Fix any issues if found. If the script is correct, report the issue concisely to the Supervisor Agent for guidance. - If none of the expected derivatives files are missing, you must s...

  54. [55]

    Note that you must not check subjects one by one manually; instead, you should use a script to perform this check

    After all subjects have been processed, write a simple script to check whether any expected derivatives files are missing for all subjects. Note that you must not check subjects one by one manually; instead, you should use a script to perform this check

  55. [56]

    Inform the Supervisor Agent that you have finished your job and any downstream analysis can proceed

    Stop and Report the final preprocessing pipeline, as well as the storage locations of the generated data, to the Supervisor Agent. Inform the Supervisor Agent that you have finished your job and any downstream analysis can proceed. * Note that the log file for each subject may be empty, as some tools do not generate logs during execution. Therefore, the c...