Predicting PSA50 response to $$^{177}$$Lu-PSMA therapy using machine learning and automated total tumor volume
Bibliographic record
Abstract
The 177 Lu-PSMA therapy is an established treatment for metastatic castration-resistant prostate cancer (mCRPC), targeting the prostate-specific membrane antigen (PSMA). Despite well-established correlations between 68 Ga-PSMA PET/CT imaging and outcome, predicting individual patient responses remains a significant challenge. This study introduces an automated method for computing the total tumor volume (TTV) from 68 Ga-PSMA PET/CT imaging and develops predictive models to assess patient biological response via the PSA50 criterion. A retrospective analysis was conducted on a real-world data cohort of 139 mCRPC patients treated in our institution. TTV was automatically extracted from PET/CT images and correlated with treatment response, defined by PSA50 criteria. Machine learning models, including Logictic Regression with L1 (LASSO) and Support Vector Machine (SVM), were developed to predict PSA50 response using imaging and clinical features. The best-performing models achieved F1-scores of 0.68 and 0.67, comparable to existing nomograms. Correlation analysis identified TTV-derived features and time since diagnosis as significant predictors of response. The proposed workflow offers an automated and reproducible approach to predicting treatment response in 177 Lu-PSMA therapy. Limitations remain for lesion segmentation within physiological regions.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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".