Title | Computationally Derived Image Signature of Stromal Morphology Is Prognostic of Prostate Cancer Recurrence Following Prostatectomy in African American Patients. |
Publication Type | Journal Article |
Year of Publication | 2020 |
Authors | Bhargava HK, Leo P, Elliott R, Janowczyk A, Whitney J, Gupta S, Fu P, Yamoah K, Khani F, Robinson BD, Rebbeck TR, Feldman M, Lal P, Madabhushi A |
Journal | Clin Cancer Res |
Volume | 26 |
Issue | 8 |
Pagination | 1915-1923 |
Date Published | 2020 04 15 |
ISSN | 1557-3265 |
Keywords | African Americans, Biomarkers, Tumor, Disease Progression, Humans, Image Processing, Computer-Assisted, Machine Learning, Male, Middle Aged, Neoplasm Recurrence, Local, Nomograms, Predictive Value of Tests, Prognosis, Prostate-Specific Antigen, Prostatectomy, Prostatic Neoplasms, Risk Assessment, ROC Curve, Stromal Cells, Survival Rate |
Abstract | PURPOSE: Between 30%-40% of patients with prostate cancer experience disease recurrence following radical prostatectomy. Existing clinical models for recurrence risk prediction do not account for population-based variation in the tumor phenotype, despite recent evidence suggesting the presence of a unique, more aggressive prostate cancer phenotype in African American (AA) patients. We investigated the capacity of digitally measured, population-specific phenotypes of the intratumoral stroma to create improved models for prediction of recurrence following radical prostatectomy. EXPERIMENTAL DESIGN: This study included 334 radical prostatectomy patients subdivided into training (V, = 127), validation 1 (V, = 62), and validation 2 (V, = 145). Hematoxylin and eosin-stained slides from resected prostates were digitized, and 242 quantitative descriptors of the intratumoral stroma were calculated using a computational algorithm. Machine learning and elastic net Cox regression models were constructed using V to predict biochemical recurrence-free survival based on these features. Performance of these models was assessed using V and V, both overall and in population-specific cohorts. RESULTS: An AA-specific, automated stromal signature, AAstro, was prognostic of recurrence risk in both independent validation datasets [V: AUC = 0.87, HR = 4.71 (95% confidence interval (CI), 1.65-13.4), = 0.003; V: AUC = 0.77, HR = 5.7 (95% CI, 1.48-21.90), = 0.01]. AAstro outperformed clinical standard Kattan and CAPRA-S nomograms, and the underlying stromal descriptors were strongly associated with IHC measurements of specific tumor biomarker expression levels. CONCLUSIONS: Our results suggest that considering population-specific information and stromal morphology has the potential to substantially improve accuracy of prognosis and risk stratification in AA patients with prostate cancer. |
DOI | 10.1158/1078-0432.CCR-19-2659 |
Alternate Journal | Clin Cancer Res |
PubMed ID | 32139401 |
PubMed Central ID | PMC7165025 |
Grant List | P20 CA233255 / CA / NCI NIH HHS / United States R01 CA216579 / CA / NCI NIH HHS / United States U24 CA199374 / CA / NCI NIH HHS / United States I01 BX004121 / BX / BLRD VA / United States R43 EB028736 / EB / NIBIB NIH HHS / United States U01 CA239055 / CA / NCI NIH HHS / United States R01 CA220581 / CA / NCI NIH HHS / United States R01 CA202752 / CA / NCI NIH HHS / United States R01 CA208236 / CA / NCI NIH HHS / United States |
Related Faculty:
Brian Robinson, M.D. Francesca Khani, M.D.