Using radiogenomics to characterize MRI-guided prostate cancer biopsy heterogenity.
Bibliographic record
Abstract
25 Background: Current methods for prostate cancer risk stratification are often insufficient to accurately predict outcome after definitive therapy. As tumor multi-focality and genetic heterogeneity can lead to diagnostic prostate biopsy sampling bias, we hypothesize that quantitative imaging with multiparametric (MP)-MRI will more accurately direct targeted biopsies to index lesions associated with highest risk clinical and genomic features, and improve accuracy of current risk classification systems. Methods: Regionally distinct prostate habitats were delineated on MP-MRI (T2w, perfusion and diffusion imaging). Directed biopsies were performed on 17 habitats from 6 patients using MRI-ultrasound fusion. Biopsy location was characterized with 51 radiographic features (including intensity, volume, perfusion, and diffusion paramters). Transcriptome-wide analysis of 1.4 million RNA probes was performed on RNA from each habitat. Genomics features with insignificant expression values (<0.25) and interquartile range <0.5 were filtered, leaving ~2K features. Results: High quality genomic data was derived from 17 (100%) biopsies and clustered by patient origin. Using only prostate cancer related genomic features for hierarchical clustering, samples clustered by Gleason score (GS), indicating these biopsies contain prognostic signal. Similarly, when principal component analysis was performed on 51 imaging features, the primary source of variance segregated the samples into high (≥7) and low (6) GS. Pearson’s correlation analysis identified 152 genomic features that were highly associated with the imaging features (|r| > 0.7). Furthermore, genomic features were found to be significantly enriched for prostate cancer related pathways (p < 0.05), representing a potential biologically meaningful link between imaging and genomic data. Conclusions: MP-MRI-targeted diagnostic biopsies can potentially improve risk classification by directing pathological and genomic analysis to highest risk index lesions. This is the first demonstration of a link between quantitative imaging features (radiomics) with genomic features in MRI-directed prostate biopsies.
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 | 0.001 |
| 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 | 0.000 |
| 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".