MétaCan
Menu
Back to cohort
Record W4395025790 · doi:10.1162/imag_a_00166

Thalamic nuclei segmentation from T1-weighted MRI: Unifying and benchmarking state-of-the-art methods

2024· article· en· W4395025790 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

fundA Canadian funder is recorded on the work.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueImaging Neuroscience · 2024
Typearticle
Languageen
FieldMedicine
TopicAdvanced Neuroimaging Techniques and Applications
Canadian institutionsnot available
FundersNational Institute of Biomedical Imaging and BioengineeringCanadian Institutes of Health ResearchNational Institutes of HealthGenentechIXICOH. Lundbeck A/SServierUniversität ZürichEisaiEidgenössische Technische Hochschule ZürichNorthern California Institute for Research and EducationF. Hoffmann-La RocheUniversity of Southern CaliforniaPfizerBioClinicaBiogenU.S. Department of DefenseEli Lilly and CompanyBristol-Myers SquibbMeso Scale DiagnosticsAlzheimer's Disease Neuroimaging InitiativeNovartis Pharmaceuticals CorporationNational Institute on AgingAlzheimer's Association
KeywordsThalamusNeuroscienceNeuroimagingSegmentationCognitionHuman Connectome ProjectBrain morphometryArtificial intelligencePsychologyMedicineMagnetic resonance imagingComputer scienceRadiologyFunctional connectivity

Abstract

fetched live from OpenAlex

The thalamus and its constituent nuclei are critical for a broad range of cognitive, linguistic, and sensorimotor processes, and are implicated in many neurological and neurodegenerative conditions. However, the functional involvement and specificity of thalamic nuclei in human neuroimaging work is underappreciated and not well studied due, in part, to technical challenges of accurately identifying and segmenting nuclei. This challenge is further exacerbated by a lack of common nomenclature for comparing segmentation methods. Here, we use data from healthy young (Human Connectome Project, n = 100) and older healthy adults, plus those with mild cognitive impairment and Alzheimer's disease (Alzheimer's Disease Neuroimaging Initiative, n = 540), to benchmark four state-of-the-art thalamic segmentation methods for T1 MRI (FreeSurfer, histogram-based polynomial synthesis [HIPS]-THOMAS, synthesized contrast segmentation [SCS]-convolutional neural network [CNN], and T1-THOMAS) under a single segmentation framework. Segmentations were compared using overlap and dissimilarity metrics to the Morel stereotaxic atlas, a widely accepted thalamic atlas. We also quantified each method's estimation of thalamic nuclear degeneration across Alzheimer's disease progression, and how accurately early and late mild cognitive impairment, and Alzheimer's disease could be distinguished from healthy controls. We show that the HIPS-THOMAS approach produced the most effective segmentations of individual thalamic nuclei relative to the Morel atlas, and was also most accurate in discriminating healthy controls from those with mild cognitive impairment and Alzheimer's disease using individual nucleus volumes. This latter result was different when using whole thalamus volumes, where the SCS-CNN approach was the most accurate in classifying healthy controls. This work is the first to systematically compare the efficacy of anatomical thalamic segmentation approaches under a unified nomenclature. We also provide recommendations of which segmentation method to use for studying the functional relevance of specific thalamic nuclei, based on their overlap and dissimilarity with the Morel atlas.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.499
Threshold uncertainty score0.350

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.047
GPT teacher head0.394
Teacher spread0.347 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it