Sci‐Fri AM General‐08: Image Fusion for Catheter Tracking in MR‐Guided Endovascular Therapy
Bibliographic record
Abstract
Endovascular therapy describes a class of minimally invasive treatments for certain vascular diseases, including the placement of stents to correct arterial stenoses, and the administration of intra‐arterial thrombolysis for ischemic stroke. Our objective is to develop a real‐time system to guide interventional endovascular procedures with MR imaging. Our approach in developing this system is to mimic, where appropriate and possible, the functionality of current clinical x‐ray fluoroscopy systems. Our endovascular MR system is comprised of two major components: a data acquisition module and an image reconstruction module. Data acquisition was performed using a 3‐tesla MR scanner (Signa VH/i; General Electric Healthcare; Waukesha, WI). Image reconstruction was performed on a separate dedicated workstation (2.2‐GHz Athlon processor‐equipped workstation running Windows XP). We achieved catheter visualization by filling catheters with MR contrast and imaging using a multi‐cycle projection dephaser to suppress the background signal. We used image‐processing filters available in the VTK library to isolate the catheter in the background‐suppressed images. The output of this image‐filtering pipeline was then used as a mask for an anatomical roadmap image. The image fusion process described herein has successfully been used to combine background‐suppressed in vivo images of a catheter with anatomical roadmap images. The fusion process removed most of the noise and residual background signal from the background‐suppressed image, leaving the catheter with improved conspicuity. Our endovascular MR system functions in a similar manner to x‐ray fluoroscopic systems and has applications in the treatment of stroke and other vascular diseases.
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 | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.083 | 0.045 |
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".