Interactive 3D segmentation of the prostate in magnetic resonance images using shape and local appearance similarity analysis
Bibliographic record
Abstract
3D segmentation of the prostate in medical images is useful to prostate cancer diagnosis and therapy guidance, but is time-consuming to perform manually. Clinical translation of computer-assisted segmentation algorithms for this purpose requires a comprehensive and complementary set of evaluation metrics that are informative to the clinical end user. We have developed an interactive 3D prostate segmentation method for 1.5T and 3.0T T2-weighted magnetic resonance imaging (T2W MRI) acquired using an endorectal coil. We evaluated our method against manual segmentations of 36 3D images using complementary boundary-based (mean absolute distance; MAD), regional overlap (Dice similarity coefficient; DSC) and volume difference (ΔV) metrics. Our technique is based on inter-subject prostate shape and local boundary appearance similarity. In the training phase, we calculated a point distribution model (PDM) and a set of local mean intensity patches centered on the prostate border to capture shape and appearance variability. To segment an unseen image, we defined a set of rays – one corresponding to each of the mean intensity patches computed in training – emanating from the prostate centre. We used a radial-based search strategy and translated each mean intensity patch along its corresponding ray, selecting as a candidate the boundary point with the highest normalized cross correlation along each ray. These boundary points were then regularized using the PDM. For the whole gland, we measured a mean±std MAD of 2.5±0.7 mm, DSC of 80±4%, and ΔV of 1.1±8.8 cc. We also provided an anatomic breakdown of these metrics within the prostatic base, mid-gland, and apex.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".