EM‐enhanced US‐based seed detection for prostate brachytherapy
Bibliographic record
Abstract
PURPOSE: Intraoperative dosimetry in low-dose-rate (LDR) permanent prostate brachytherapy requires accurate localization of the implanted seeds with respect to the prostate anatomy. Transrectal Ultrasound (TRUS) imaging, which is the main imaging modality used during the procedure, is not sufficiently robust for accurate seed localization. We present a method for integration of electromagnetic (EM) tracking into LDR prostate brachytherapy procedure by fusing it with TRUS imaging for seed localization. METHOD: Experiments were conducted on five tissue mimicking phantoms in a controlled environment. The seeds were implanted into each phantom using an EM-tracked needle, which allowed recording of seed drop locations. After each needle, we reconstructed a 3D ultrasound (US) volume by compounding a series of 2D US images acquired during retraction of an EM-tracked TRUS probe. Then, a difference image was generated by nonrigid registration and subtraction of two consecutive US volumes. A US-only seed detection method was used to detect seed candidates in the difference volume, based on the signature of the seeds. Finally, the EM-based positions of the seeds were used to detect the false positives of the US-based seed detection method and also to estimate the positions of the missing seeds. After the conclusion of the seed implant process, we acquired a CT image. The ground truth for seed locations was obtained by localizing the seeds in the CT image and registering them to the US coordinate system. RESULTS: Compared to the ground truth, the US-only detection algorithm achieved a localization error mean of 1.7 mm with a detection rate of 85%. By contrast, the EM-only seed localization method achieved a localization error mean of 3.7 mm with a detection rate of 100%. By fusing EM-tracking information with US imaging, we achieved a localization error mean of 1.8 mm while maintaining a 100% detection rate without any false positives. CONCLUSIONS: Fusion of EM-tracking and US imaging for prostate brachytherapy can combine high localization accuracy of US-based seed detection with the robustness and high detection rate of EM-based seed localization. Our phantom experiments serve as a proof of concept to demonstrate the potential value of integrating EM-tracking into LDR prostate brachytherapy.
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 | 0.002 |
| 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) | 0.001 | 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".