MétaCan
Menu
Back to cohort
Record W3023773746 · doi:10.1016/j.media.2020.101714

The reliability of a deep learning model in clinical out-of-distribution MRI data: A multicohort study

2020· article· en· W3023773746 on OpenAlexfundno aff
Gustav Mårtensson, Daniel Ferreira, Tobias Granberg, Lena Cavallin, Ketil Oppedal, Alessandro Padovani, Irena Rektorová, Laura Bonanni, Matteo Pardini, Milica G. Kramberger, John‐Paul Taylor, Jakub Hort, Jón Snædal, Jaime Kulisevsky, Frédéric Blanc, Angelo Antonini, Patrizia Mecocci, Bruno Vellas, Magda Tsolaki, Iwona Kłoszewska, Hilkka Soininen, Simon Lovestone, Andrew Simmons, Dag Aarsland, Eric Westman

Bibliographic record

VenueMedical Image Analysis · 2020
Typearticle
Languageen
FieldMedicine
TopicMRI in cancer diagnosis
Canadian institutionsnot available
FundersNational Institute on AgingCanadian Institutes of Health ResearchNational Institutes of HealthIXICOH. Lundbeck A/SServierKarolinska InstitutetAlzheimerfondenSwedish Brain PowerHjärnfondenVetenskapsrådetEisaiStiftelsen Olle Engkvist ByggmästareGenentechStiftelsen för Strategisk ForskningCenter for Innovative MedicineNorthern California Institute for Research and EducationStockholms Läns LandstingDoD Alzheimer's Disease Neuroimaging InitiativePfizerBiogenBioClinicaNvidiaUniversity of Southern CaliforniaU.S. Department of DefenseEli Lilly and CompanyBristol-Myers SquibbMeso Scale DiagnosticsAlzheimer's Disease Neuroimaging InitiativeNovartis Pharmaceuticals CorporationAlzheimer's AssociationÅke Wiberg Stiftelse
KeywordsArtificial intelligenceComputer scienceReliability (semiconductor)Deep learningConvolutional neural networkProtocol (science)Machine learningNeuroradiologistNeuroimagingMedical physicsPattern recognition (psychology)Magnetic resonance imagingMedicinePathologyRadiology

Abstract

fetched live from OpenAlex

Deep learning (DL) methods have in recent years yielded impressive results in medical imaging, with the potential to function as clinical aid to radiologists. However, DL models in medical imaging are often trained on public research cohorts with images acquired with a single scanner or with strict protocol harmonization, which is not representative of a clinical setting. The aim of this study was to investigate how well a DL model performs in unseen clinical datasets-collected with different scanners, protocols and disease populations-and whether more heterogeneous training data improves generalization. In total, 3117 MRI scans of brains from multiple dementia research cohorts and memory clinics, that had been visually rated by a neuroradiologist according to Scheltens' scale of medial temporal atrophy (MTA), were included in this study. By training multiple versions of a convolutional neural network on different subsets of this data to predict MTA ratings, we assessed the impact of including images from a wider distribution during training had on performance in external memory clinic data. Our results showed that our model generalized well to datasets acquired with similar protocols as the training data, but substantially worse in clinical cohorts with visibly different tissue contrasts in the images. This implies that future DL studies investigating performance in out-of-distribution (OOD) MRI data need to assess multiple external cohorts for reliable results. Further, by including data from a wider range of scanners and protocols the performance improved in OOD data, which suggests that more heterogeneous training data makes the model generalize better. To conclude, this is the most comprehensive study to date investigating the domain shift in deep learning on MRI data, and we advocate rigorous evaluation of DL models on clinical data prior to being certified for deployment.

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)0.075
metaresearch head score (Gemma)0.141
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.075
Threshold uncertainty score0.395

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0750.141
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0020.001
Science and technology studies0.0010.003
Scholarly communication0.0020.003
Open science0.0030.003
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0010.001

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 head0.073
GPT teacher head0.426
Teacher spread0.353 · 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 designObservational
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

Citations171
Published2020
Admission routes1
Has abstractyes

Explore more

Same venueMedical Image AnalysisSame topicMRI in cancer diagnosisFrench-language works237,207