MétaCan
Menu
Back to cohort
Record W4281768802 · doi:10.1002/jmri.28274

Automated Detection of Brain Metastases on <scp>T1</scp>‐Weighted <scp>MRI</scp> Using a Convolutional Neural Network: Impact of Volume Aware Loss and Sampling Strategy

2022· article· en· W4281768802 on OpenAlexaff
Gabriel Chartrand, Ramón D. Emiliani, Sophie Anne Pawlowski, Daniel Markel, Houda Bahig, Alexandre Cengarle‐Samak, S. Rajakesari, Jeremi Lavoie, Simon Ducharme, David Roberge

Bibliographic record

VenueJournal of Magnetic Resonance Imaging · 2022
Typearticle
Languageen
FieldPhysics and Astronomy
TopicAdvanced Radiotherapy Techniques
Canadian institutionsMontreal Neurological Institute and HospitalCentre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-MontréalMcGill UniversityDouglas Mental Health University InstituteHôpital Charles-Le MoyneCentre Hospitalier de l’Université de Montréal
Fundersnot available
KeywordsGround truthMcNemar's testSørensen–Dice coefficientSampling (signal processing)Convolutional neural networkNuclear medicineData setTest setVoxelMagnetic resonance imagingComputer scienceSegmentationArtificial intelligenceVolume (thermodynamics)MedicinePattern recognition (psychology)StatisticsMathematicsRadiologyPhysicsImage segmentationComputer visionFilter (signal processing)

Abstract

fetched live from OpenAlex

BACKGROUND: Detection of brain metastases (BM) and segmentation for treatment planning could be optimized with machine learning methods. Convolutional neural networks (CNNs) are promising, but their trade-offs between sensitivity and precision frequently lead to missing small lesions. HYPOTHESIS: Combining volume aware (VA) loss function and sampling strategy could improve BM detection sensitivity. STUDY TYPE: Retrospective. POPULATION: A total of 530 radiation oncology patients (55% women) were split into a training/validation set (433 patients/1460 BM) and an independent test set (97 patients/296 BM). FIELD STRENGTH/SEQUENCE: 1.5 T and 3 T, contrast-enhanced three-dimensional (3D) T1-weighted fast gradient echo sequences. ASSESSMENT: Ground truth masks were based on radiotherapy treatment planning contours reviewed by experts. A U-Net inspired model was trained. Three loss functions (Dice, Dice + boundary, and VA) and two sampling methods (label and VA) were compared. Results were reported with Dice scores, volumetric error, lesion detection sensitivity, and precision. A detected voxel within the ground truth constituted a true positive. STATISTICAL TESTS: McNemar's exact test to compare detected lesions between models. Pearson's correlation coefficient and Bland-Altman analysis to compare volume agreement between predicted and ground truth volumes. Statistical significance was set at P ≤ 0.05. RESULTS: Combining VA loss and VA sampling performed best with an overall sensitivity of 91% and precision of 81%. For BM in the 2.5-6 mm estimated sphere diameter range, VA loss reduced false negatives by 58% and VA sampling reduced it further by 30%. In the same range, the boundary loss achieved the highest precision at 81%, but a low sensitivity (24%) and a 31% Dice loss. DATA CONCLUSION: Considering BM size in the loss and sampling function of CNN may increase the detection sensitivity regarding small BM. Our pipeline relying on a single contrast-enhanced T1-weighted MRI sequence could reach a detection sensitivity of 91%, with an average of only 0.66 false positives per scan. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

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: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.437
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
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
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 head0.014
GPT teacher head0.297
Teacher spread0.283 · 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 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

Citations31
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Magnetic Resonance ImagingSame topicAdvanced Radiotherapy TechniquesFrench-language works237,207