Utilizing Weighted Spatio-Temporal Information for Automated Transthoracic Echocardiography View Classification
Bibliographic record
Abstract
Transthoracic echocardiography (TTE) is a critical imaging modality for assessing cardiac function and diagnosing cardiomyopathies. These videos, captured from various heart angles, must be accurately categorized for comprehensive diagnosis, making automated view classification essential. This study develops and evaluates multiple model architectures and feature fusion techniques to classify eleven standard TTE views from video input. We examine both spatial and temporal feature extraction approaches alongside a Dynamic Feature Fusion technique (DFF) that adaptively balances the importance of either feature in analyzing TTE studies. Our results highlight the superior performance of a model architecture utilizing an EfficientNet and Dilated Convolutional Networks, achieving a micro F1 Score of 0.951. Additionally, we leverage a custom cycle detector algorithm to partition a TTE sequence into individual cardiac cycles, i.e., heartbeats, providing consistent input for model training and enabling an ensemble technique for a more reliable prediction. Our findings present valuable insights into effective TTE analysis, identifying the most effective model architecture for echocardiogram interpretation and advancing clinical workflows.Clinical RelevanceThis approach improves echocardiogram view classification, aiding clinicians by streamlining work-flows and reducing errors. The method can also be applied to broader TTE data analysis tasks, such as disease classification, while offering insights into interpretable spatial and temporal patterns.
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) | 0.000 | 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 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".