K-Means Clustering of Hyperpolarised 13C-MRI Identifies Intratumoral Perfusion/Metabolism Mismatch in Renal Cell Carcinoma as the Best Predictor of the Highest Grade
Bibliographic record
Abstract
Background: Early and accurate grading of renal cell carcinoma (RCC) improves patient risk stratification and has implications for clinical management and mortality. However, current diagnostic approaches using imaging and renal mass biopsy have limited specificity and may lead to undergrading. Methods: This study explored the use of hyperpolarised [1-13C]pyruvate MRI (HP 13C-MRI) to identify the most aggressive areas within the tumour of patients with clear cell renal cell carcinoma (ccRCC) as a method to guide biopsy targeting and to reduce undergrading. Six patients with ccRCC underwent presurgical HP 13C-MRI and conventional contrast-enhanced MRI. From the imaging data, three k-means clusters were computed by combining the kPL as a marker of metabolic activity, and the 13C-pyruvate signal-to-noise ratio (SNRPyr) as a perfusion surrogate. The combined clusters were compared to those derived from individual parameters and to those derived from the percentage of enhancement on the nephrographic phase (%NG). The diagnostic performance of each cluster was assessed based on its ability to predict the highest histological tumour grade in postsurgical tissue samples. The postsurgical tissue samples underwent immunohistochemical staining for the pyruvate transporter (monocarboxylate transporter 1, MCT1), as well as RNA and whole-exome sequencing. Results: The clustering approach combining SNRPyr and kPL demonstrated the best performance for predicting the highest tumour grade: specificity 85%; sensitivity 64%; positive predictive value 82%; and negative predictive value 68%. Epithelial MCT1 was identified as the major determinant of the HP 13C-MRI signal. The perfusion/metabolism mismatch cluster showed an increased expression of metabolic genes and markers of aggressiveness. Conclusions: This study demonstrates the potential of using HP 13C-MRI-derived metabolic clusters to identify intratumoral variations in tumour grade with high specificity. This work supports the use of metabolic imaging to guide biopsies to the most aggressive tumour regions and could potentially reduce sampling error.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| 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".