MétaCan
Menu
← Back to cohort
Record W4311681019 · doi:10.22215/etd/2022-15198

Image Processing Techniques for Analysis of Myocardial Fibrosis and Related Cardiomyopathies in Cardiac Magnetic Resonance Imaging

2022· dissertation· en· W4311681019 on OpenAlexaff
Nadia Farrag

Bibliographic record

Venuenot available
Typedissertation
Languageen
FieldMedicine
TopicCardiac Imaging and Diagnostics
Canadian institutionsCarleton University
Fundersnot available
KeywordsMyocardial fibrosisMedicineMagnetic resonance imagingCardiac imagingCardiac magnetic resonanceFibrosisSegmentationCardiac magnetic resonance imagingCardiologyRadiologyArtificial intelligenceInternal medicineComputer science

Abstract

fetched live from OpenAlex

Myocardial fibrosis (MF) is a common feature of cardiac disease, characterized by excessive deposition of collagen (i.e., scar tissue) and expansion of the myocardial extracellular volume (ECV).This phenomenon contributes to cardiac dysfunction, promotes further cardiac disease, and has implication in preceding cardiac morbidity and mortality.The extent of myocardial MF can be analyzed globally (across the entire myocardial region) and/or regionally (across the fibrotic area exclusively) using cardiac magnetic resonance (CMR) imaging techniques, such as late gadolinium enhanced imaging or quantitative methods like native T1 and ECV mapping.CMR-based measurements of MF, native T1, and ECV allow for differentiation between various cardiac disease states and are shown to be clinically significant predictors of patient outcomes.However, in order to analyze tissue volumes or classify disease states, clinicians must first perform a manual tracing of the myocardial borders to define an initial region of interest (ROI), while regional MF quantification requires additional manual selection of a reference healthy myocardial tissue region.These manual processes are tedious, user-dependent, and highly prone to operator error, which can significantly confound resultant measures of T1, ECV and quantified MF tissue zones.Thus, alternative, minimally user-dependent techniques for MF, T1 and ECV quantification are appropriate.In this dissertation, several techniques for improving automated quantification of myocardial T1, ECV, and MF regions are presented.The proposed approaches presented in this document incorporate concepts from deep learning and image processing to achieve automated or semi-automated segmentation of the myocardium, MF, T1 and/or ECV in the left ventricle (LV) and left atrium (LA).

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)0.001
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.004
Threshold uncertainty score0.012

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0040.002

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 head0.006
GPT teacher head0.281
Teacher spread0.276 · 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 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

Citations0
Published2022
Admission routes1
Has abstractyes

Explore more

Same topicCardiac Imaging and Diagnostics→French-language works237,207→