Rotationally resliced 3D prostate TRUS segmentation using convex optimization with shape priors
Bibliographic record
Abstract
PURPOSE: Efficient and accurate segmentations of 3D end-firing transrectal ultrasound (TRUS) images play an important role in planning of 3D TRUS guided prostate biopsy. However, poor image quality of the input 3D TRUS images, such as strong imaging artifacts and speckles, often makes it a challenging task to extract the prostate boundaries accurately and efficiently. METHODS: In this paper, the authors propose a novel convex optimization-based approach to delineate the prostate surface from a given 3D TRUS image, which reduces the original 3D segmentation problem to a sequence of simple 2D segmentation subproblems over the rotational reslices of the 3D TRUS volume. Essentially, the authors introduce a novel convex relaxation-based contour evolution approach to each 2D slicewise image segmentation with the joint optimization of shape information, where the learned 2D nonlinear statistical shape prior is incorporated to segment the initial slice, its result is propagated as a shape constraint to the segmentation of the following slices. In practice, the proposed segmentation algorithm is implemented on a GPU to achieve the high computational performance. RESULTS: Experimental results using 30 patient 3D TRUS images show that the proposed method can achieve a mean Dice similarity coefficient of 93.4% ± 2.2% in 20 s for one 3D image, outperforming the existing local-optimization-based methods, e.g., level-set and active-contour, in terms of accuracy and efficiency. In addition, inter- and intraobserver variability experiments show its good reproducibility. CONCLUSIONS: A semiautomatic segmentation approach is proposed and evaluated to extract the prostate boundary from 3D TRUS images acquired by a 3D end-firing TRUS guided prostate biopsy system. Experimental results suggest that it may be suitable for the clinical use involving the image guided prostate biopsy procedures.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| 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".