Can Deep Learning-Based Auto-Contouring Software Achieve Accurate Pelvic Volume Delineation in Volumetric Image-Guided Radiotherapy for Prostate Cancer? A Preliminary Multicentric Analysis
Bibliographic record
Abstract
Background: Radiotherapy (RT) is a mainstay treatment for prostate cancer (PC). Accurate delineation of organs at risk (OARs) is crucial for optimizing the therapeutic window by minimizing side effects. Manual segmentation is time-consuming and prone to inter-operator variability. This study investigates the performance of Limbus® Contour® (LC), a deep learning-based auto-contouring software, in delineating pelvic structures in PC patients. Methods: We evaluated LC’s performance on key structures (bowel bag, bladder, rectum, sigmoid colon, and pelvic lymph nodes) in 52 patients. We compared auto-contoured structures with those manually delineated by radiation oncologists using different metrics. Results: LC achieved good agreement for the bladder (median Dice: 0.95) and rectum (median Dice: 0.83). However, limitations were observed for the bowel bag (median Dice: 0.64) and sigmoid colon (median Dice: 0.6), with inclusion of irrelevant structures. While the median Dice for pelvic lymph nodes was acceptable (0.73), the software lacked sub-regional differentiation, limiting its applicability in certain other oncologic settings. Conclusions: LC shows promise for automating OAR delineation in prostate radiotherapy, particularly for the bladder and rectum. Improvements are needed for bowel bag, sigmoid colon, and lymph node sub-regionalization. Further validation with a broader and larger patient cohort is recommended to assess generalizability.
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 | 0.009 | 0.020 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".