Improving the efficiency of Cardiovascular MR for assessing Ischemic Cardiomyopathy diagnosis: a machine learning based approach
Bibliographic record
Abstract
Ischemic cardiomyopathy is a condition characterized by impaired heart function due to damage to the myocardium, generally resulting from coronary artery disease or myocardial infarction. Diagnosing ischemic cardiomyopathy using cardiac magnetic resonance imaging involves detecting and quantifying abnormalities in cardiac function from various imaging modalities. Parameters that describe the cardiac function are acquired from multiple views, or slices, of the heart. Recent progress in machine learning research has led to machine learning applications being developed for multiparametric cardiac magnetic resonance imaging to create a more efficient diagnostic process. Thousands of images are needed for multiparametric cardiac analysis. Their acquisition and post-processing increase both scan and diagnostic time. This study aims to find out whether diagnosing ischemic cardiomyopathy is possible using a single cardiac slice from a single imaging modality. This study hypothesized that oxygenation-sensitive cardiac resonance imaging would contain data that, when extracted, would allow machine learning algorithms to determine whether a patient is a healthy volunteer or has ischemic cardiomyopathy with a high degree of accuracy. This study aimed to test this hypothesis by extracting left ventricular cardiac strain data from a short-axis view using a neural network from the oxygenation-sensitive images of previously diagnosed ischemic cardiomyopathy patients. Comparing the results of the proposed method, with the results obtained when applying the method to strain values extracted from a steady-state free precession imaging modality for the same patients, revealed that the oxygenation-sensitive imaging modality provides a much lower diagnostic accuracy which contradicts studies that suggest that a heart under stress shows abnormalities in cardiac strain for ischemic patients. However, the relatively high diagnostic accuracy of the steady-state free precession imaging modality shows the potential of using a single cardiac slice in combination with machine learning for diagnostic purposes. Future work should concentrate on extracting additional parameters from the same set of images, such as radiomics, signal intensities, and right ventricular function
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".