MétaCan
Menu
Back to cohort

Abstract 4144409: Visualizing Chronic Myocardial Infarction using Native T1-weighted Signal Intensity Patterns with Similar Image Contrast as LGE MRI

2024· article· en· W4404359250 on OpenAlexaff
Khalid Youssef, Xinheng Zhang, Ghazal Yoosefian, Yinyin Chen, Shing Fai Chan, Hsin‐Jung Yang, Keyur P. Vora, Andrew G. Howarth, Andreas Kumar, Behzad Sharif, Rohan Dharmakumar

Bibliographic record

VenueCirculation · 2024
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsMedicineContrast (vision)Myocardial infarctionMagnetic resonance imagingIntensity (physics)CardiologyRadiologyCardiac magnetic resonanceDynamic contrastInternal medicineArtificial intelligence

Abstract

fetched live from OpenAlex

Background: The identification of chronic myocardial infarction (MI) typically relies on contrast-enhanced MRI, late-gadolinium enhancement (LGE) MRI. Native (contrast-free) T1 mapping at 3T has been shown to identify chronic MI but visualization of it is more difficult compared to LGE MRI. Data-driven utilization of distinctive native T1-weighted MRI signal intensity patterns in infarcted and remote myocardium may be a superior alternative to standard native-T1 mapping. We hypothesized that native T1-weighted signal intensity patterns can be used to generate images of chronic MI with similar contrast-to-noise ratio (CNR) to LGE MRI. We tested this hypothesis using a data-driven approach applied to native T1-weighted signal patterns of chronic MI and compared the resulting CNR to the CNRs of LGE and native T1 maps at 3T. Methods: The study included a dataset of spatially aligned short-axis, native-T1-weighted and LGE images of hearts from canine (n=24) with surgically implemented chronic MI. Unsupervised clustering techniques (self-organizing maps and t-distributed stochastic neighbor embedding) were used to analyze the T1-weighted images to arrive at native T1-weighted pixel intensity patterns. Data-driven native mapping (DNM) utilizing deep neural networks were used to map these patterns to corresponding pixels in LGE images. This allowed for creation of visually enhanced maps with improved chronic MI contrast. Pearson correlation analysis compared DNM with standard T1 maps. Results: Native T1-weighted images showed distinct pixel intensity patterns between infarcted and remote myocardium. CNR from DNM (mean ± SD, 15.01±2.88) was significantly higher than native T1 maps (5.64±1.58, p<0.001) but not different from LGE images (15.51±2.43, p=0.40). Infarcted areas in LGE images correlated more strongly with DNM (R 2 =0.85) than with native T1 maps (R 2 =0.71, p<0.001). Conclusion: Native T1-weighted pixels contain information that can be extracted using the DNM approach to enhance image contrast between infarcted and remote myocardium. The proposed approach allows for robust visualization of chronic infarct territories without contrast agents, offering a viable contrast-agent-free alternative to LGE MRI. Patient studies are needed for clinical translation.

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)0.001
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: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.002
Threshold uncertainty score0.006

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0020.000

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 head0.306
Teacher spread0.292 · 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

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueCirculationSame topicRadiomics and Machine Learning in Medical ImagingFrench-language works237,207