Computationally Derived Image Signature of Stromal Morphology Is Prognostic of Prostate Cancer Recurrence Following Prostatectomy in African American Patients
Computationally Derived Image Signature of Stromal Morphology Is Prognostic of Prostate Cancer Recurrence Following Prostatectomy in African American Patients
复制标题
DOI：
10.1158/1078-0432.ccr-19-2659
复制
发表时间：
2020-04-01
影响因子：
11.5
通讯作者：
Madabhushi, Anant
中科院分区：
文献类型：
--
作者：
Bhargava, Hersh K.;Leo, Patrick;Madabhushi, Anant
目的：30%-40%的前列腺癌患者在前列腺癌根治术后复发。现有的复发风险预测临床模型不能解释肿瘤表型在人群中的差异，尽管最近的证据表明在非裔美国人(AA)患者中存在一种独特的、更具侵袭性的前列腺癌表型。实验设计：本研究包括334名前列腺癌根治术患者，分为训练(V-T，n=127)、验证1(V-1，n=62)和验证2(V-2，n=145)。来自切除的前列腺的苏木素和曙红染色的切片被数字化，并使用计算算法计算出242个肿瘤间质的定量描述符。基于这些特征，利用VT建立了机器学习和弹性网络Cox回归模型来预测生化无复发生存率。结果：AA-1，V-AA：AUC=0.87，HR=4.71(95%可信区间，1.65-13.4)，P=0.003；V-2，V-AA：AUC=0.77，HR=5.7(95%CI，1.48-21.90)，P=0.01]。Astro的表现优于临床标准的卡坦和卡普拉-S诺模图，而且潜在的间质描述符与IHC对特定肿瘤生物标记物表达水平的测量密切相关。结论：我们的结果表明，考虑特定人群的信息和间质形态可以显著提高前列腺癌AA患者预后和风险分层的准确性。
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-T, n = 127), validation 1 (V-1, n = 62), and validation 2 (V-2, n = 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 VT to predict biochemical recurrence-free survival based on these features. Performance of these models was assessed using V-1 and V-2, 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-1,V-AA: AUC = 0.87, HR = 4.71 (95% confidence interval (CI), 1.65-13.4), P = 0.003; V-2,V-AA: AUC = 0.77, HR = 5.7 (95% CI, 1.48-21.90), P = 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.