MRI-based radiomics nomogram to predict complete response to definitive chemoradiation in patients with anal cancer
Bibliographic record
Abstract
OBJECTIVES: Treatment response to definitive chemoradiation (dCRT) in patients with anal cancer varies significantly, with a subset experiencing persistent or progressive disease despite therapy. Radiomics extracts quantitative features from radiological images, with the potential to develop predictive tools to assess treatment response. We aim to develop and validate an MRI-based radiomics nomogram to predict response to dCRT in patients with anal cancer. METHODS: A single-institutional retrospective analysis of 45 patients with anal cancer treated with dCRT was performed. Radiomic features were extracted from pre-treatment T2-weighted MRI scans, and predictive models were constructed. Clinical and radiomic features were analysed to develop the nomogram. Internal validation with 1000 bootstrap samples was performed to calculate optimism-corrected performance measures. RESULTS: Overall, 30/45(66.7%) achieved a complete treatment response. Male gender was found to be an independent predictor of incomplete response to dCRT (OR 4.763,95% CI: 1.170-19.384,*P = .029). Two radiomic signatures emerged as strong predictors of treatment response to dCRT. The combined model outperformed the clinical and radiomic models. The combined model showed the highest predictive accuracy, achieving an apparent area under the receiver operating characteristic curve (AUC): 0.87 (0.75-0.99) and an optimism-corrected AUC: 0.85, mean absolute error: 0.029, positive predictive value (0.68) and negative predictive value (0.92), indicating excellent discriminative performance. It demonstrated a positive net benefit in decision analysis. The optimism-corrected calibration curves demonstrate that the radiomic and combined model provide well-calibrated predictions. CONCLUSION: This MRI-based radiomics nomogram offers a promising approach to predict response to dCRT in patients with anal cancer. ADVANCES IN KNOWLEDGE: This study is the first to integrate radiomics and clinical features into a validated predictive model for anal cancer.
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 | 0.005 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".