Trackerless 3D Ultrasound Stitching for Computer-Assisted Orthopaedic Surgery and Pelvic Fractures
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
In pelvic fracture surgeries, percutaneous screws must be placed accurately for effective fixation and to prevent damage to surrounding tissue structures. Fluoroscopy is currently used to image the pelvis to provide guidance, but this produces harmful ionising radiation and does not allow three-dimensional (3D) visualisation. Ultrasound offers three-dimensional, non-ionising, real-time, and inexpensive imaging. It has thus emerged as an alternative to fluoroscopy for intraoperative imaging in computer-assisted orthopaedic surgery (CAOS). However, ultrasound-based surgical guidance is challenging because ultrasound produces inherently noisy images with limited field-of-view. While several techniques have been proposed to improve bone clarity in ultrasound scans, there is limited work on enhancing ultrasound’s field-of-view for CAOS. In particular, improving the field-of-view for surgical guidance for pelvic fracture surgeries would be needed to achieve accurate and reliable registration to preoperative data, and accurate screw placement in the pelvis. We propose and evaluate the feasibility of a trackerless method for stitching volumetric ultrasound to achieve an extended field-of-view. Stitching is performed using corresponding features in the overlap between three ultrasound volumes, extracted using an implementation of the 3D scale-invariant feature transform. The volumes are processed using confidence-map weighted phase symmetry detection. Alignment between the volumes is calculated using coherent point drift rigid registration. We succeeded in extending the field-of-view of 3D ultrasound by creating a 39×43×115mm volume from three initial overlapping volumes, with reasonable overall accuracy. We show a mean post-registration surface error of 0.54mm, compared to 0.33mm achieved by previous tracking-based stitching. Our method achieved a mean distance error of 5.1%, compared to 2% in a similar tracked and 3D SIFT-based technique. Our stitching method does not use tracking, thus contributing towards simpler surgical navigation.
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.
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 | 0.001 | 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 it