Motion Estimation in Cardiac Fluorescence Imaging With Scale-Space Landmarks and Optical Flow: A Comparative Study
Bibliographic record
Abstract
Motion artifacts are a major disadvantage of cardiac optical mapping studies. Pixel misalignment due to contraction is a main cause of the presence of gross motion artifacts in action potential recordings. This study is focused on methods for identifying landmarks and tracking the motion of cardiac tissue for preparations in optical mapping recordings. This is a first step toward our long-term goal to implement a landmark-based image registration technique to correct for pixel misalignment in cardiac optical mapping fluorescence videos and, hence, for gross motion artifacts. Preliminary results for the registration step are presented as an initial proof of concept. The characteristics of the optical mapping images are challenging, since their lack of contrast and well-defined features impose a limitation on the techniques than can be used for landmark selection and motion tracking. This paper compares results of motion estimation of the cardiac surface with two approaches that do not rely on high-contrast features: 1) Scale-invariant feature transform (SIFT) detected "keypoints," to be used as landmarks for motion tracking, as well as 2) a classical global optical flow (OF) algorithm. Both are applied to low-contrast and low-resolution cardiac fluorescence images. We demonstrate that the performance of SIFT is superior to that of OF for pixel motion tracking in cardiac optical mapping images with simulated motion. Results for action potential recovery and action potential duration calculation after landmark-based image registration show that SIFT landmark-based registration yields superior performance in this regard as well.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| 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 | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".