MétaCan
Menu
Back to cohort
Record W4416117870 · doi:10.48550/arxiv.2504.04911

IterMask3D: Unsupervised Anomaly Detection and Segmentation with Test-Time Iterative Mask Refinement in 3D Brain MR

2025· preprint· en· W4416117870 on OpenAlexfundno aff
Ziyun Liang, Xiaoqing Guo, Wentian Xu, Yasin Ibrahim, Natalie Voets, Pieter Pretorius, J. Alison Noble, Konstantinos Kamnitsas

Bibliographic record

VenueArXiv.org · 2025
Typepreprint
Languageen
FieldComputer Science
TopicAnomaly Detection Techniques and Applications
Canadian institutionsnot available
FundersEngineering and Physical Sciences Research CouncilCanadian Institutes of Health ResearchAvid RadiopharmaceuticalsNational Institutes of HealthUniversity of OxfordGenentechIXICOH. Lundbeck A/SServierEisaiMeso Scale DiagnosticsDepartment of Health and Social CareNational Institute for Health and Care ResearchNorthern California Institute for Research and EducationBioClinicaBiogenPfizerNovartis Pharmaceuticals CorporationWellcome TrustUniversity of Southern CaliforniaUK Research and InnovationU.S. Department of DefenseEli Lilly and CompanyBristol-Myers SquibbAlzheimer's Disease Neuroimaging InitiativeAlzheimer's Association
KeywordsSegmentationIterative reconstructionPattern recognition (psychology)Anomaly detectionImage segmentationProcess (computing)Feature (linguistics)Image (mathematics)

Abstract

fetched live from OpenAlex

Unsupervised anomaly detection and segmentation methods train a model to learn the training distribution as `normal'. In the testing phase, they identify patterns that deviate from this normal distribution as `anomalies'. To learn the `normal' distribution, prevailing methods corrupt the images and train a model to reconstruct them. During testing, the model attempts to reconstruct corrupted inputs based on the learned `normal' distribution. Deviations from this distribution lead to high reconstruction errors, which indicate potential anomalies. However, corrupting an input image inevitably causes information loss even in normal regions, leading to suboptimal reconstruction and an increased risk of false positives. To alleviate this, we propose $\rm{IterMask3D}$, an iterative spatial mask-refining strategy designed for 3D brain MRI. We iteratively spatially mask areas of the image as corruption and reconstruct them, then shrink the mask based on reconstruction error. This process iteratively unmasks `normal' areas to the model, whose information further guides reconstruction of `normal' patterns under the mask to be reconstructed accurately, reducing false positives. In addition, to achieve better reconstruction performance, we also propose using high-frequency image content as additional structural information to guide the reconstruction of the masked area. Extensive experiments on the detection of both synthetic and real-world imaging artifacts, as well as segmentation of various pathological lesions across multiple MRI sequences, consistently demonstrate the effectiveness of our proposed method. Code is available at https://github.com/ZiyunLiang/IterMask3D.

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 imitation

Not 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.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.004
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.010
Threshold uncertainty score0.020

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.004
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0020.001
Science and technology studies0.0010.001
Scholarly communication0.0020.002
Open science0.0050.004
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0050.003

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 head0.014
GPT teacher head0.252
Teacher spread0.238 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueArXiv.orgSame topicAnomaly Detection Techniques and ApplicationsFrench-language works237,207