MétaCan
Menu
Back to cohort
Record W4377002285 · doi:10.59275/j.melba.2022-db5c

Label fusion and training methods for reliable representation of inter-rater uncertainty

2023· article· en· W4377002285 on OpenAlexafffund
Andréanne Lemay, Charley Gros, Enamundram Naga Karthik, Julien Cohen‐Adad

Bibliographic record

VenueThe Journal of Machine Learning for Biomedical Imaging · 2023
Typearticle
Languageen
FieldEngineering
TopicMedical Imaging and Analysis
Canadian institutionsPolytechnique MontréalMila - Quebec Artificial Intelligence Institute
FundersFonds de recherche du Québec – Nature et technologiesCanadian Institutes of Health ResearchNatural Sciences and Engineering Research Council of CanadaInstitut de Valorisation des DonnéesCraig H. Neilsen FoundationCanada First Research Excellence FundNvidia
KeywordsSegmentationArtificial intelligenceComputer scienceGround truthMachine learningTask (project management)Pattern recognition (psychology)

Abstract

fetched live from OpenAlex

Medical tasks are prone to inter-rater variability due to multiple factors such as image quality, professional experience and training, or guideline clarity. Training deep learning networks with annotations from multiple raters is a common practice that mitigates the model’s bias towards a single expert. Reliable models generating calibrated outputs and reflecting the inter-rater disagreement are key to the integration of artificial intelligence in clinical practice. Various methods exist to take into account different expert labels. We focus on comparing three label fusion methods: STAPLE, average of the rater’s segmentation, and random sampling of each rater’s segmentation during training. Each label fusion method is studied using both the conventional training framework and the recently published SoftSeg framework that limits information loss by treating the segmentation task as a regression. Our results, across 10 data splittings on two public datasets (spinal cord gray matter challenge, and multiple sclerosis brain lesion segmentation), indicate that SoftSeg models, regardless of the ground truth fusion method, had better calibration and preservation of the inter-rater rater variability compared with their conventional counterparts without impacting the segmentation performance. Conventional models, i.e., trained with a Dice loss, with binary inputs, and sigmoid/softmax final activate, were overconfident and underestimated the uncertainty associated with inter-rater variability. Conversely, fusing labels by averaging with the SoftSeg framework led to underconfident outputs and overestimation of the rater disagreement. In terms of segmentation performance, the best label fusion method was different for the two datasets studied, indicating this parameter might be task-dependent. However, SoftSeg had segmentation performance systematically superior or equal to the conventionally trained models and had the best calibration and preservation of the inter-rater variability. SoftSeg has a low computational cost and performed similarly in terms of uncertainty to ensembles which require multiple models and forward passes. Our code is available at https://ivadomed.org.

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)0.036
metaresearch head score (Gemma)0.075
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: Empirical · Consensus signal: none
Teacher disagreement score0.036
Threshold uncertainty score0.191

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0360.075
Meta-epidemiology (narrow)0.0030.001
Meta-epidemiology (broad)0.0030.002
Bibliometrics0.0040.002
Science and technology studies0.0020.003
Scholarly communication0.0030.004
Open science0.0030.005
Research integrity0.0040.006
Insufficient payload (model declined to judge)0.0030.002

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 head0.032
GPT teacher head0.366
Teacher spread0.334 · 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
GenreEmpirical

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

Citations13
Published2023
Admission routes2
Has abstractyes

Explore more

Same venueThe Journal of Machine Learning for Biomedical ImagingSame topicMedical Imaging and AnalysisFrench-language works237,207