MétaCan
Menu
Back to cohort
Record W3124703593 · doi:10.59275/j.melba.2021-3581

FlowReg: Fast Deformable Unsupervised Medical Image Registration using Optical Flow

2021· article· en· W3124703593 on OpenAlexafffund
Sergiu Mocanu, Alan R. Moody, April Khademi

Bibliographic record

VenueThe Journal of Machine Learning for Biomedical Imaging · 2021
Typearticle
Languageen
FieldComputer Science
TopicMedical Image Segmentation Techniques
Canadian institutionsToronto Metropolitan UniversityUniversity of TorontoSt. Michael's Hospital
FundersCanadian Institutes of Health ResearchYork UniversityNational Institutes of HealthNatural Sciences and Engineering Research Council of CanadaAlzheimer's Disease Neuroimaging InitiativeU.S. Department of Defense
KeywordsArtificial intelligenceComputer scienceImage registrationPixelComputer visionNeuroimagingAffine transformationSimilarity (geometry)Optical flowPattern recognition (psychology)Deep learningImage (mathematics)Mathematics

Abstract

fetched live from OpenAlex

In this work we propose FlowReg, a deep learning-based framework that performs unsupervised image registration for neuroimaging applications. The system is composed of two architectures that are trained sequentially: FlowReg-A which affinely corrects for gross differences between moving and fixed volumes in 3D followed by FlowReg-O which performs pixel-wise deformations on a slice-by-slice basis for fine tuning in 2D. FlowReg-A warps the moving volume using gross global parameters to align rotation, scale, shear, and translation to the fixed volume. A correlation loss that encourages global alignment between the moving and the fixed volumes is employed to regress the affine parameters. The deformable network FlowReg-O operates on 2D image slices and is based on the optical flow CNN network that is adapted to neuroimaging with three loss components. The photometric loss minimizes pixel intensity differences, the smoothness loss encourages similar magnitudes between neighbouring vectors, and a correlation loss that is used to maintain the intensity similarity between fixed and moving image slices. The proposed method is compared to four open source registration techniques ANTs, Demons, SE, and Voxelmorph for FLAIR MRI applications. In total, 4643 FLAIR MR imaging volumes (approximately 255,000 image slices) are used from dementia and vascular disease cohorts, acquired from over 60 international centres with varying acquisition parameters. To quantitatively assess the performance of the registration tools, a battery of novel validation metrics are proposed that focus on the structural integrity of tissues, spatial alignment, and intensity similarity. Experimental results show FlowReg (FlowReg-A+O) performs better than iterative-based registration algorithms for intensity and spatial alignment metrics with a Pixelwise Agreement (PWA) of 0.65, correlation coefficient (R) of 0.80, and Mutual Information (MI) of 0.29. Among the deep learning frameworks evaluated, FlowReg-A or FlowReg-A+O provided the highest performance over all but one of the metrics. Results show that FlowReg is able to obtain high intensity and spatial similarity between the moving and the fixed volumes while maintaining the shape and structure of anatomy and pathology.

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 score0.005
Threshold uncertainty score0.013

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.004
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0010.001
Scholarly communication0.0010.002
Open science0.0020.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0040.002

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 head0.015
GPT teacher head0.303
Teacher spread0.288 · 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

Citations19
Published2021
Admission routes2
Has abstractyes

Explore more

Same venueThe Journal of Machine Learning for Biomedical ImagingSame topicMedical Image Segmentation TechniquesFrench-language works237,207