MétaCan
Menu
Back to cohort
Record W2899974865 · doi:10.1109/trpms.2018.2880617

An Empirical Approach for Avoiding False Discoveries When Applying High-Dimensional Radiomics to Small Datasets

2018· article· en· W2899974865 on OpenAlexafffund
Avishek Chatterjee, Martin Vallières, Anthony Dohan, Ives R. Levesque, Yoshiko Ueno, Vipul Bist, Sameh Saif, Caroline Reinhold, Jan Seuntjens

Bibliographic record

VenueIEEE Transactions on Radiation and Plasma Medical Sciences · 2018
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsMcGill University Health Centre
FundersNatural Sciences and Engineering Research Council of CanadaCanadian Institutes of Health ResearchTerry Fox Research Institute
KeywordsOverfittingFeature selectionArtificial intelligenceRadiomicsLogistic regressionComputer scienceSupport vector machineFeature (linguistics)Machine learningReceiver operating characteristicPattern recognition (psychology)

Abstract

fetched live from OpenAlex

Purpose: Radiomic studies, where correlations are drawn between patients' medical image features and patient outcomes, often deal with small datasets. Consequently, results can suffer from lack of replicability and stability. This paper establishes a methodology to assess and reduce the impact of statistical fluctuations that may occur in small datasets. Such fluctuations can lead to false discoveries, particularly when applying feature selection or machine learning (ML) methods commonly used in the radiomics literature. Methods: Two feature selection methods were created, one for choosing single predictive features, and another for obtaining features sets that could be combined in a predictive model. The features were combined using ML tools less affected by overfitting (Naïve Bayes, logistic regression, and linear support vector machines). Only three features were allowed to be combined at a time, further limiting overfitting. This methodology was applied to MR images from small datasets in metastatic liver disease (69 samples) and primary uterine adenocarcinoma (93 samples), and the outcomes studied were: desmoplasia (for liver metastases), lymphovascular space invasion (LVSI), cancer staging (FIGO), and tumor grade (for uterine tumors). For outcomes in uterine cancer, the predictive models were tested on independent subsets. Results: With respect to the combined predictive feature approach: for LVSI, a prognostic factor that a human reader cannot detect, the predictive model yielded AUC = 0.87 ± 0.07 and accuracy = 0.84 ± 0.09 in the testing set. For FIGO staging, AUC = 0.81 ± 0.03 and accuracy = 0.79 ± 0.08. For tumor grade, AUC = 0.76 ± 0.05 and accuracy = 0.70 ± 0.08. Conclusion: Despite considering a large set (~104) of texture features, the false discovery avoidance methodology allowed only robust predictive models to be retained. Thus, the stringent false discovery avoidance methods introduced here do not preclude the discovery of promising correlations.

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)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation 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 score0.968
Threshold uncertainty score0.732

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.001
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
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 head0.040
GPT teacher head0.338
Teacher spread0.298 · 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.

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

Citations25
Published2018
Admission routes2
Has abstractyes

Explore more

Same venueIEEE Transactions on Radiation and Plasma Medical SciencesSame topicRadiomics and Machine Learning in Medical ImagingFrench-language works237,207