When to biopsy Prostate Imaging and Data Reporting System version 2 (PI-RADSv2) assessment category 3 lesions? Use of clinical and imaging variables to predict cancer diagnosis at targeted biopsy
Bibliographic record
Abstract
INTRODUCTION: We aimed to determine if clinical and imaging features can stratify men at higher risk for clinically significant (CS, International Society of Urological Pathology [ISUP] grade group ≥2) prostate cancer (PCa) in equivocal Prostate Imaging and Data Reporting System (PI-RADS) category 3 lesions on magnetic resonance imaging (MRI). METHODS: Approved by the institutional review board, this retrospective study involved 184 men with 198 lesions who underwent 3T-MRI and MRI-directed transrectal ultrasound biopsy for PI-RADS 3 lesions. Men were evaluated including clinical stage, prostate-specific antigen density (PSAD), indication, and MRI lesion size. Diagnoses for all men and by indication (no cancer, any PCa, CSPCa) were compared using multivariate logistic regression, including stage, PSAD, and lesion size. RESULTS: We found an overall PCa rate of 31.8% (63/198) and 10.1% (20/198) CSPCa (13 grade group 2, five group 3, and two group 4). Higher stage (p=0.001), PSAD (p=0.007), and lesion size (p=0.015) were associated with CSPCa, with no association between CSPCa and age, PSA, or prostate volume (p>0.05). PSAD modestly predicted CSPCa area under the curve (AUC) 0.66 (95% confidence interval [CI] 0.518-0.794) in all men and 0.64 (0.487-0.799) for those on active surveillance (AS). Model combining clinical stage, PSAD, and lesion size improved accuracy for all men and AS (AUC 0.82 [0.736-0.910], p<0.001 and 0.785 [0.666-0.904], p<0.001). In men with prior negative biopsy and persistent suspicion, PSAD (0.90 [0.767-1.000]) was not different from the model (p>0.05), with optimal cutpoint of ≥0.215 ng/mL/cc achieving sensitivity/specificity of 85.7/84.4%. CONCLUSIONS: PI-RADSv2 category 3 lesions are often not CSPCa. PSAD predicted CSPCa in men with a prior negative biopsy; however, PSAD alone had limited value, and accuracy improved when using a model incorporating PSAD with clinical stage and MRI lesion size.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".