Fusing magnetic resonance imaging data for studying ventricular fibrillation
Bibliographic record
Abstract
Ventricular Fibrillation (VF) has been described as seemingly random activations on the ventricles of the mammalian heart and is one of the causes of Sudden Cardiac Deaths (SCD). Medical imaging techniques, such as Magnetic Resonance Imaging (MRI), could potentially provide a better way of collecting data and understanding the true nature of VF than the techniques that are currently being employed. In addition, as there is a wide variety of MR techniques, fusing and jointly analyzing complementary data sets could also prove beneficial in providing parameters that are informative in studying VF and are otherwise unobservable by inspection. In this thesis, the author explores the quantification of the combination of MRI techniques, Current Density Imaging (CDI) and Diffusion Tensor Imaging (DTI), as novel tools for studying VF. This was accomplished by performing two feature-based data fusion techniques, Joint Independent Component Analysis (jICA) and Canonical Correlation Analysis (CCA). Using 12 imaging data sets from 10 live porcine heart experiments, both data fusion techniques provided unique ways from which the variations of CDI and DTI data sets were used to distinguish cardiac states. The results obtained by the jICA approach demonstrated discrimination between VF and non-VF subjects (p = 0:020) using the jICA loadings with evidence of a significant increase in the mutual information post fusion. For the CCA approach, using the pairwise mixing profiles, we observed discrimination between VF and non-VF subjects (p = 0:023) with a 7.25% increase in average correlation between the modalities, post fusion. The results of the study demonstrate that the fusion of CDI and DTI data sets captures and enhances the variations in electrical current pathways in relation to a myocardial structure that are unique to a cardiac state, such as VF. This study serves as a strong precursor for exploring MRI and data fusion techniques in studying VF. Such a study could provide greater insights on VF characteristics inspiring better treatment options for patients vulnerable to VF.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".