Use of a new tracking system based on ArToolkit for a surgical simulator: accuracy test and overall evaluation
Bibliographic record
Abstract
Computer assisted surgery (CAS) uses expensive tracking systems, such as Optotrak (Northern Digital, Canada). These cameras use infra-red (IR) light detection and give sub-millimeter accuracy for the tracking of surgical tools in a real surgical context. In simulation, such accuracy is not mandatory. To replace the standard tracking systems used in CAS simulation, this paper promotes the use of video tracking systems that are easy to set up and less expensive. This work was motivated by the 5/sup th/ European Framework project VOEU that is aiming to produce new training tools for orthopedic surgery. One problems to solve is to provide an autonomous system for supporting surgeons in learning CAS procedures, since new training components are frequently requested. Such training technologies can be used during surgical lessons given to medical students, or are delivered to surgeons for preparing a real CAS procedure. Due to new computer technologies based on PCs, surgical simulators can be built at low cost featuring video tracking. Tracking is a key part of each CAS simulator, since surgical tools are used and need to be located in space. Several test series were carried out according to confidence values given by the ArToolkit library to evaluate its accuracy regarding various different parameters (size of markers, video cameras, volume of interest). The simulator implementation proposes a new interface for ArToolkit displaying a 3D scene without showing the image sequence captured by the video camera. The implemented 3D module is entirely based on an OpenInventor (SGI, USA) engine and can easily be included as a subcomponent of any complex user interface. One to several tools can be displayed in real time allowing the completion of each step of a common CAS procedure.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
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".