MétaCan
Menu
Back to cohort
Record W3002993892 · doi:10.1101/2020.01.21.913624

Deep learning based behavioral analysis enables high precision rodent tracking and is capable of outperforming commercial solutions

2020· preprint· en· W3002993892 on OpenAlexfundno aff
Oliver Sturman, Lukas von Ziegler, Christa Schläppi, Furkan Akyol, Benjamin F. Grewe, Johannes Bohacek

Bibliographic record

VenuebioRxiv (Cold Spring Harbor Laboratory) · 2020
Typepreprint
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicZebrafish Biomedical Research Applications
Canadian institutionsnot available
FundersNeuroscience Center Zurich, University of ZurichUniversität ZürichOlga Mayenfisch StiftungNovartis FoundationMcGill UniversitySchweizerischer Nationalfonds zur Förderung der Wissenschaftlichen ForschungEidgenössische Technische Hochschule Zürich
KeywordsComputer scienceArtificial intelligenceFlexibility (engineering)Deep learningMachine learningTracking (education)Set (abstract data type)Psychology

Abstract

fetched live from OpenAlex

Abstract To study brain function, preclinical research relies heavily on animal monitoring and the subsequent analyses of behavior. Commercial platforms have enabled semi high-throughput behavioral analyses by providing accurate tracking of animals, yet they often struggle with the analysis of ethologically relevant behaviors and lack the flexibility to adapt to variable testing environments. In the last couple of years, substantial advances in deep learning and machine vision have given researchers the ability to take behavioral analysis entirely into their own hands. Here, we directly compare the performance of commercially available platforms (Ethovision XT14, Noldus; TSE Multi Conditioning System, TSE Systems) to cross-verified human annotation. To this end, we provide a set of videos - carefully annotated by several human raters - of three widely used behavioral tests (open field, elevated plus maze, forced swim test). Using these data, we show that by combining deep learning-based motion tracking (DeepLabCut) with simple post-analysis, we can track animals in a range of classic behavioral tests at similar or even greater accuracy than commercial behavioral solutions. In addition, we integrate the tracking data from DeepLabCut with post analysis supervised machine learning approaches. This combination allows us to score ethologically relevant behaviors with similar accuracy to humans, the current gold standard, thus outperforming commercial solutions. Moreover, the resulting machine learning approach eliminates variation both within and between human annotators. In summary, our approach helps to improve the quality and accuracy of behavioral data, outperforming commercial systems at a fraction of the cost.

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 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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.153
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.001
Research integrity0.0010.001
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 head0.026
GPT teacher head0.275
Teacher spread0.249 · 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 teacher head, not a consensus.

Study designBench or experimental
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

Citations17
Published2020
Admission routes1
Has abstractyes

Explore more

Same venuebioRxiv (Cold Spring Harbor Laboratory)Same topicZebrafish Biomedical Research ApplicationsFrench-language works237,207