MP28-04 CORRELATION BETWEEN MRI PHENOTYPES AND A GENOMIC CLASSIFIER OF PROSTATE CANCER
Bibliographic record
Abstract
You have accessJournal of UrologyProstate Cancer: Markers II (MP28)1 Apr 2019MP28-04 CORRELATION BETWEEN MRI PHENOTYPES AND A GENOMIC CLASSIFIER OF PROSTATE CANCER Andrei Purysko*, Cristina Magi-Galluzzi, Omar Mian, Elai Davicioni, Marguerite du Plessis, Christine Buerki, Jennifer Bullen, Lin Li, Anant Madabhushi, Andrew Stephenson, and Eric Klein Andrei Purysko*Andrei Purysko* More articles by this author , Cristina Magi-GalluzziCristina Magi-Galluzzi More articles by this author , Omar MianOmar Mian More articles by this author , Elai DavicioniElai Davicioni More articles by this author , Marguerite du PlessisMarguerite du Plessis More articles by this author , Christine BuerkiChristine Buerki More articles by this author , Jennifer BullenJennifer Bullen More articles by this author , Lin LiLin Li More articles by this author , Anant MadabhushiAnant Madabhushi More articles by this author , Andrew StephensonAndrew Stephenson More articles by this author , and Eric KleinEric Klein More articles by this author View All Author Informationhttps://doi.org/10.1097/01.JU.0000555709.00017.09AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVES: We sought to evaluate the correlation between MRI phenotypes of prostate cancer as defined by the Prostate Imaging Reporting and Data System version 2 (PI-RADS v2) and Decipher Genomic Classifier (used to estimate the risk of early metastases). METHODS: This single-center, retrospective study included 72 men with prostate cancer who underwent 3T MRI before radical prostatectomy performed between April 2014 and August 2017 and whose lesions were microdissected from radical prostatectomy specimens and then tested with Decipher (89 lesions; 23 MRI invisible [PI-RADS v2 scores ≤ 2] and 66 MRI visible [PI-RADS v2 scores ≥ 3]). Linear regression analysis was used to assess clinicopathologic and MRI predictors of Decipher results; correlation coefficients (r) were used to quantify these associations. Area under the receiver operating characteristic curve (AUC) was used to determine whether PI-RADS v2 could accurately distinguish between low-risk and intermediate-/high-risk lesions (cutoff Decipher score, 0.45). RESULTS: Median age was 63 years (range: 42-76), and median PSA was 9.8 ng/mL (range: 1.2-69). The lesions’ grade groups (GG) were GG1=8, GG2=40, GG3=18, GG4=5, GG5=18. MRI-visible lesions had higher Decipher scores than MRI-invisible lesions (mean difference 0.22; 95% CI 0.13, 0.32; p < 0.0001); most MRI-invisible lesions (82.6%) were low risk. PI-RADS v2 had moderate correlation with Decipher (r = 0.54) and had higher accuracy to distinguish between low-risk and intermediate-/high-risk lesions (AUC 0.863) than prostate cancer grade groups (AUC 0.780) in peripheral zone lesions (95% CI for difference 0.01, 0.15; p = 0.018). CONCLUSIONS: MRI phenotypes of prostate cancer are positively correlated with Decipher risk groups. Although PI-RADS v2 can accurately distinguish between lesions classified by Decipher as low or intermediate/high risk, some MRI-invisible lesions have the potential for aggressive behavior. Source of Funding: Philips/Radiological Society North America Research and Education Foundation Seed Grant and Cleveland Clinic Center for Clinical Genomics Cleveland, OH; Birmingham, AL; Cleveland, OH; Vancouver, Canada; Cleveland, OH© 2019 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 201Issue Supplement 4April 2019Page: e404-e404 Advertisement Copyright & Permissions© 2019 by American Urological Association Education and Research, Inc.MetricsAuthor Information Andrei Purysko* More articles by this author Cristina Magi-Galluzzi More articles by this author Omar Mian More articles by this author Elai Davicioni More articles by this author Marguerite du Plessis More articles by this author Christine Buerki More articles by this author Jennifer Bullen More articles by this author Lin Li More articles by this author Anant Madabhushi More articles by this author Andrew Stephenson More articles by this author Eric Klein More articles by this author Expand All Advertisement PDF downloadLoading ...
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 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 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) | 0.068 | 0.018 |
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".