MétaCan
Menu
← Back to cohort

Radiogenomic characterization of multifocal prostate cancer.

2019· article· en· W2921423014 on OpenAlexaff
Simpa S. Salami, Jeremy Kaplan, Srinivas Nallandhighal, Mandeep Takhar, Jeffrey J. Tosoian, Matthew Lee, Junhee Yoon, Daniel H. Hovelson, Komal Plouffe, Samuel D. Kaffenberger, Arvin K. George, Jeffrey S. Montgomery, Matthew S. Davenport, Sungyong You, Scott A. Tomlins, Nicole E. Curci, Hyung Lae Kim, Daniel E. Spratt, Aaron M. Udager, Ganesh S. Palapattu

Bibliographic record

VenueJournal of Clinical Oncology · 2019
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsGenome British Columbia
Fundersnot available
KeywordsProstate cancerMedicineMagnetic resonance imagingRadiogenomicsProstatectomyATRXProstateCancerPathologyRadiologyInternal medicineGeneMutationBiologyRadiomics

Abstract

fetched live from OpenAlex

126 Background: Up to 20% of patients with negative multiparametric magnetic resonance imaging (MRI) harbor Gleason score ≥7 prostate cancer (PCa). We sought to elucidate the molecular basis of and determine the prognostic significance of PCa visibility on MRI. Methods: We identified a retrospective cohort of patients who underwent MRI prior to prostatectomy with both MRI visible (PIRADS 3 – 5) and invisible PCa. MRI for each patient was re-reviewed and co-registered with whole-mount histopathology. DNA and RNA were co-isolated from all tumor foci pre-identified on FFPE specimens. High depth, targeted DNA and RNA next generation sequencing was performed to characterize the molecular profile of each tumor focus using the Oncomine Comprehensive Panel (DNA) and a custom targeted RNAseq panel assessing PCa relevant alterations. A multigene RNAseq model was developed and validated in two independent cohorts to predict MRI visible PCa and to determine the prognostic significance of MRI visibility. Results: A total of 26 primary tumor foci from 10 patients were analyzed. Of the 14 (54%) invisible lesions on MRI, 5 (36%) were Gleason 3+4 = 7 and the remainder were Gleason 6. We detected high-confidence prioritized PCa relevant mutations in 54% (14/26) of tumor foci, 43% (6/14) of which were in MRI invisible lesions. Notable point mutations were in APC, AR, ARID1B, ATM, ATRX, BRCA2, FAT1, MAP3K1, NF1, SPEN, SPOP, and TP53. A 9-gene RNA signature, the majority of which were under-expressed cellular organization and structure genes, was developed to predict MRI visibility with an AUC of 0.89. Validation of this signature in an independent data set (n = 16) yielded an AUC of 0.88 with a specificity of 100% for predicting MRI visible tumors. Using this signature in a cohort of 375 patients with clinical follow up, we found that predicted MRI visibility status was not an independent predictor of biochemical recurrence, metastasis-free survival, or PCa specific mortality (all p > 0.05). Conclusions: We observed under-expression of cellular organization and structural genes in MRI visible tumors compared to MRI invisible cancer foci. Using our validated signature to predict MRI visibility status, we found that MRI visibility is not a significant predictor of oncological outcomes.

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 imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.001
Threshold uncertainty score0.004

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.000

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.

Opus teacher head0.045
GPT teacher head0.447
Teacher spread0.402 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2019
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Clinical Oncology→Same topicRadiomics and Machine Learning in Medical Imaging→French-language works237,207→