Online Learning-Based Robust Deep Feature Ultrasound Visual Servoing: Applications to Echocardiography
Bibliographic record
Abstract
This paper proposes a robust ultrasound image-based visual servoing (UIBVS) method designed for intelligent autonomous echocardiography with online learning capability. A cascade control scheme, comprising internal and external loops, ensures robust and intelligent cardiac imaging. The internal loop integrates a filtered integral quasi-super-twisting algorithm (FIQSTA) with an ultrasound-cardiac-feature-net (UCF-Net). UCF-Net, a pretrained convolutional neural network (CNN), extracts six unique ultrasound image features essential for UIBVS. Within the internal loop, FIQSTA exploits these features to minimize errors between desired and current ultrasound images to zero in finite time, despite system uncertainties. In the external loop, another CNN acts as a feature modifier, adjusting the desired image features based on cardiologist-provided updates. Thus, the internal loop provides robust and accurate visual servoing with proven stability, while the external loop contributes intelligence and adaptability through supervised online learning. Combining the feature modifier and UCF-Net results in the adaptive UCF-Net (AUCF-Net), the key component enabling continuous online learning and improving accuracy with increased usage. Experimental results using a cardiac phantom demonstrate the effectiveness of the proposed method in achieving the parasternal short-axis (PSAX) view and its ability to adaptively update and correct desired images online.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".