scholarly journals Combination of Peri-Tumoral and Intra-Tumoral Radiomic Features on Bi-Parametric MRI Accurately Stratifies Prostate Cancer Risk: A Multi-Site Study

Cancers ◽  
2020 ◽  
Vol 12 (8) ◽  
pp. 2200 ◽  
Author(s):  
Ahmad Algohary ◽  
Rakesh Shiradkar ◽  
Shivani Pahwa ◽  
Andrei Purysko ◽  
Sadhna Verma ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
High Risk ◽  
Risk Stratification ◽  
Operating Characteristic ◽  
Prostate Cancer Risk ◽  
Magnetic Resonance Imaging Mri ◽  
Validation Set ◽  
And Diffusion ◽  
Risk Categories

Background: Prostate cancer (PCa) influences its surrounding habitat, which tends to manifest as different phenotypic appearances on magnetic resonance imaging (MRI). This region surrounding the PCa lesion, or the peri-tumoral region, may encode useful information that can complement intra-tumoral information to enable better risk stratification. Purpose: To evaluate the role of peri-tumoral radiomic features on bi-parametric MRI (T2-weighted and Diffusion-weighted) to distinguish PCa risk categories as defined by D’Amico Risk Classification System. Materials and Methods: We studied a retrospective, HIPAA-compliant, 4-institution cohort of 231 PCa patients (n = 301 lesions) who underwent 3T multi-parametric MRI prior to biopsy. PCa regions of interest (ROIs) were delineated on MRI by experienced radiologists following which peri-tumoral ROIs were defined. Radiomic features were extracted within the intra- and peri-tumoral ROIs. Radiomic features differentiating low-risk from: (1) high-risk (L-vs.-H), and (2) (intermediate- and high-risk (L-vs.-I + H)) lesions were identified. Using a multi-institutional training cohort of 151 lesions (D1, N = 116 patients), machine learning classifiers were trained using peri- and intra-tumoral features individually and in combination. The remaining 150 lesions (D2, N = 115 patients) were used for independent hold-out validation and were evaluated using Receiver Operating Characteristic (ROC) analysis and compared with PI-RADS v2 scores. Results: Validation on D2 using peri-tumoral radiomics alone resulted in areas under the ROC curve (AUCs) of 0.84 and 0.73 for the L-vs.-H and L-vs.-I + H classifications, respectively. The best combination of intra- and peri-tumoral features resulted in AUCs of 0.87 and 0.75 for the L-vs.-H and L-vs.-I + H classifications, respectively. This combination improved the risk stratification results by 3–6% compared to intra-tumoral features alone. Our radiomics-based model resulted in a 53% accuracy in differentiating L-vs.-H compared to PI-RADS v2 (48%), on the validation set. Conclusion: Our findings suggest that peri-tumoral radiomic features derived from prostate bi-parametric MRI add independent predictive value to intra-tumoral radiomic features for PCa risk assessment.

Is clinical stage T2c prostate cancer intermediate- or high-risk disease? Results from the SEARCH database.

2012 ◽  
Vol 30 (5_suppl) ◽  
pp. 123-123
Author(s):  
Abhay A Singh ◽  
Leah Gerber ◽  
Stephen J. Freedland ◽  
William J Aronson ◽  
Martha K. Terris ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
High Risk ◽  
Risk Stratification ◽  
Predictive Accuracy ◽  
Cox Model ◽  
Clinical Stage ◽  
Prostate Cancer Risk ◽  
Clinical Staging ◽  
Intermediate Risk ◽  
Concordance Index

123 Background: Clinical stage T2c is a nebulous factor in the algorithm for prostate cancer risk stratification. According to D’Amico risk stratification cT2c is high-risk category where NCCN guidelines place this stage in intermediate-risk. As diagnostic work up with the use of MRI continues to escalate clinical staging may become more important. As cT2c represents a possible decision fork in treatment decisions we sought to investigate which risk group the clinical behavior of cT2c tumors more closely resembles. Methods: We retrospectively analyzed data from 1089 men who underwent radical prostatectomy (RP) from 1988 to 2009 who did not have low-risk CaP from the SEARCH database. We compared time to BCR between men with cT2c disease, those with intermediate-risk (PSA 10-20 ng/ml or Gleason sum (GS) =7), and those with high-risk (PSA>20 ng/ml, GS 8-10, cT3) using Cox regression models adjusting for age, race, year of RP, center, and percent cores positive. We also compared predictive accuracy of two Cox models wherein cT2c was considered either intermediate- or high-risk by calculating concordance index c. Results: A total of 68 men (3.4%) had cT2c tumors. After a median follow-up of 47.5 months, there was no difference in BCR risk between men with intermediate-risk CaP and those with cT2c tumors (HR=0.90; p=0.60). In contrast, there was a trend for men with high-risk CaP to have nearly 50% increased BCR risk compared to men with cT2c tumors (HR=1.50; 95% CI=0.97-2.30; p=0.07) which did not reach statistical significance. Concordance index c was higher in the Cox model wherein cT2c tumors were considered intermediate-risk (c=0.6147) as opposed to high-risk (c=0.6106). Conclusions: BCR risk for patients with clinical stage T2c was more comparable to men who had intermediate-risk CaP than men with high-risk. In addition, a model which incorporates cT2c disease as intermediate-risk has better predictive accuracy. These findings suggest men with cT2c disease should be offered treatment options for men with intermediate-risk CaP. As clinical staging more routinely incorporates MRI there is the potential to better identify bilateral organ-confined CaP and further establish risk classification.

861 THE ROLE OF PREOPERATIVE MR IMAGING FOR RISK STRATIFICATION OF PATIENTS WITH HIGH RISK PROSTATE CANCER

2011 ◽  
Vol 10 (2) ◽  
pp. 271-272
Author(s):  
C. Lee ◽  
J.H. Yoon ◽  
D. You ◽  
I.G. Jeong ◽  
C. Song ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
High Risk ◽  
Mr Imaging ◽  
Risk Stratification ◽  
High Risk Prostate Cancer ◽  
Risk Prostate Cancer

scholarly journals The role of chemotherapy and new targeted agents in the management of primary prostate cancer

2016 ◽  
Vol 9 (2_suppl) ◽  
pp. 30-37 ◽  
Author(s):  
Sanjeev Srinivas Kumar ◽  
Simon Pacey
Keyword(s):  
Prostate Cancer ◽  
High Risk ◽  
Risk Stratification ◽  
Survival Benefit ◽  
Metastatic Prostate Cancer ◽  
Targeted Agents ◽  
Molecular Features ◽  
Primary Prostate Cancer ◽  
Significant Survival

While early treatment of primary prostate cancer is very effective, the incidence of primary prostate cancer continues to rise and therefore the detection of men with high-risk non-metastatic prostate cancer and their subsequent management is becoming increasingly important. There continues to be no molecularly-targeted or chemotherapeutic options with proven, statistically significant survival benefit in this setting. However, there are indications that further risk stratification using molecular features could potentially help distinguish indolent from aggressive prostate cancer, ultimately providing biological markers that could guide a more personalised approach to therapy selection.

scholarly journals Genetic predisposition to prostate cancer: an update

2021 ◽  
Author(s):  
Holly Ni Raghallaigh ◽  
Rosalind Eeles
Keyword(s):  
Prostate Cancer ◽  
Risk Factors ◽  
Genetic Variation ◽  
High Risk ◽  
Cancer Risk ◽  
Prostate Cancer Screening ◽  
Prostate Cancer Risk ◽  
Targeted Screening ◽  
European Populations

AbstractImprovements in DNA sequencing technology and discoveries made by large scale genome-wide association studies have led to enormous insight into the role of genetic variation in prostate cancer risk. High-risk prostate cancer risk predisposition genes exist in addition to common germline variants conferring low-moderate risk, which together account for over a third of familial prostate cancer risk. Identifying men with additional risk factors such as genetic variants or a positive family history is of clinical importance, as men with such risk factors have a higher incidence of prostate cancer with some evidence to suggest diagnosis at a younger age and poorer outcomes. The medical community remains in disagreement on the benefits of a population prostate cancer screening programme reliant on PSA testing. A reduction in mortality has been demonstrated in many studies, but at the cost of significant amounts of overdiagnosis and overtreatment. Developing targeted screening strategies for high-risk men is currently the subject of investigation in a number of prospective studies. At present, approximately 38% of the familial risk of PrCa can be explained based on published SNPs, with men in the top 1% of the risk profile having a 5.71-fold increase in risk of developing cancer compared with controls. With approximately 170 prostate cancer susceptibility loci now identified in European populations, there is scope to explore the clinical utility of genetic testing and genetic-risk scores in prostate cancer screening and risk stratification, with such data in non-European populations eagerly awaited. This review will focus on both the rare and common germline genetic variation involved in hereditary and familial prostate cancer, and discuss ongoing research in exploring the role of targeted screening in this high-risk group of men.

scholarly journals CHEK2∗1100delC Mutation and Risk of Prostate Cancer

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Victoria Hale ◽  
Maren Weischer ◽  
Jong Y. Park
Keyword(s):  
Prostate Cancer ◽  
Current Knowledge ◽  
Prostate Cancer Screening ◽  
Critical Role ◽  
Prostate Cancer Risk ◽  
Conclusive Evidence ◽  
Increased Risk ◽  
History Of ◽  
Cancer Studies

Although the causes of prostate cancer are largely unknown, previous studies support the role of genetic factors in the development of prostate cancer.CHEK2plays a critical role in DNA replication by responding to double-stranded breaks. In this review, we provide an overview of the current knowledge of the role of a genetic variant, 1100delC, ofCHEK2on prostate cancer risk and discuss the implication for potential translation of this knowledge into clinical practice. Currently, twelve articles that discussedCHEK2∗1100delC and its association with prostate cancer were identified. Of the twelve prostate cancer studies, five studies had independent data to draw conclusive evidence from. The pooled results of OR and 95% CI were 1.98 (1.23–3.18) for unselected cases and 3.39 (1.78–6.47) for familial cases, indicating thatCHEK2∗1100delC mutation is associated with increased risk of prostate cancer. Screening for CHEK2∗1100delC should be considered in men with a familial history of prostate cancer.

Sign in / Sign up

Export Citation Format

Share Document