Prostate MRI learning curves: establishing training benchmarks for radiology and urology trainees
Bibliographic record
Abstract
OBJECTIVES: Evidence-based training benchmarks for prostate multiparametric MRI (mpMRI) interpretation remain undefined amid growing educational demands. We compared learning curves between radiology and urology trainees and quantified the impact of prior radiological experience. MATERIALS AND METHODS: Fourteen trainees (10 radiology, median 2.7 years experience; 4 urology, no imaging experience), all naïve to prostate mpMRI, prospectively interpreted 200 cases using a feedback-based platform. Performance metrics included agreement with expert consensus reference for PI-RADSv2.1 (≥ 3), PI-QUALv2 image quality, extraprostatic extension (EPE) grading, and readout time. Learning curves were modeled using generalized estimating equations; segmented regression identified inflection points; bootstrapping generated 95% CIs. RESULTS: Prior radiological experience showed no significant impact on PI-RADSv2.1 (OR per year 1.06 [95% CI: 0.96, 1.16]) or PI-QUALv2 (1.05 [0.99, 1.23]), with a minor effect on EPE grading (1.11 [1.03, 1.24]). Final PI-RADSv2.1 agreement with reference was similar (urology 80.9%, radiology 77.4%; OR 1.24 [0.55, 3.10]), with sensitivity/specificity 0.84/0.80 and 0.83/0.79, and Cohen's κ values (0.64 and 0.61) matching inter-expert κ = 0.63. Learning plateaued after 69-75 cases. Urology trainees demonstrated higher baseline PI-QUALv2/EPE agreement (OR 2.01 [1.35, 3.02] and 1.90 [1.11, 2.93]), but radiology trainees achieved similar final performance (PI-QUALv2: 88.0% vs 89.9%, OR 0.82 [0.35, 1.72]; EPE: 84.6% vs 90.0%, OR 0.61 [0.31, 1.42]). Readout times decreased markedly in both groups (final difference 53.3 s [-9.4, 95.9]). CONCLUSION: Feedback-based training enabled similar prostate mpMRI interpretation performance across specialties, with most learning within 75 cases. Prior radiological experience had a limited impact. These empirical benchmarks inform certification standards and early-residency curricula in radiology and urology. KEY POINTS: Question Evidence-based training benchmarks for prostate mpMRI interpretation competency in radiology and urology trainees remain undefined, despite growing educational needs and clinical demands. Findings Learning curves of 200 prostate mpMRI cases with feedback showed radiology and urology trainees plateauing after 69-75 cases with similar PI-RADSv2.1, PI-QUALv2, EPE grading performance. Clinical relevance Our findings establish an empirical benchmark (~75 cases) to guide prostate mpMRI certification standards and support the implementation of training curricula early in residency across specialties, regardless of prior radiological experience.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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 | 0.001 |
| 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".