Validation of Prostate Imaging Reporting and Data System Version 2 for the Detection of Prostate Cancer

Hofbauer, Sebastian L.; Maxeiner, Andreas; Kittner, Beatrice; Heckmann, Robin; Reimann, Maximillian; Wiemer, Laura; Asbach, Patrick; Haas, Matthias; Penzkofer, Tobias; Stephan, Carsten; Friedersdorff, Frank; Fuller, Florian; Miller, Kurt; Cash, Hannes

doi:10.1016/j.juro.2018.05.003

Cited by 58 publications

(54 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of our study confirm the already known importance of mpMRI and MRI-TRUS fusion guided prostate biopsy for the diagnosis of PCa. Similar overall and csPCa diagnosis rates have been reported by several centers [17][18][19]. A higher PIRADS score is significantly correlated with the presence of clinically significant disease.…”

Section: Discussionsupporting

confidence: 82%

MRI-TRUS fusion guided prostate biopsy – initial experience and assessment of the role of contralateral lobe systematic biopsy

Andraș

Crişan

Căta³

et al. 2019

Med Ultrason

View full text Add to dashboard Cite

Aims: To present our initial experience and results of MRI-TRUS fusion guided prostate biopsy and assess the role of contralateral lobe systematic biopsy.Material and method: A number of 119 patients with clinical or biochemical suspicion for prostate cancer (PCa) were included. All patients harbored at least one PIRADS score ≥ 3 lesion and underwent MRI-TRUS fusion guided biopsy, as well as a concurrent systematic biopsy. The biopsy was performed by the same operator, using a rigidregistration software system.Results: The mean age of the patients was 62.2 years. The mean pre-biopsy PSA was 9.15 ng/dl. The diagnosis rate of MRI-TRUS fusion guided biopsy was 47% for overall PCa and 29.4% for clinically significant (cs) PCa. A higher PIRADS score was significantly associated with the presence of overall and csPCa. MRI-TRUS fusion guided biopsy had a higher percentage of positive biopsy cores (51% vs 29%), higher likelihood of csPCa (OR 5.36, p=0.008) and upgrading (14.8%) in comparison with systematic biopsy but missed 6.7% csPCa. The contralateral lobe systematic biopsy could have been avoided without losing the PCa diagnosis all patients with PIRADS score 5, both in initial and repeat biopsy setting. Anterior and transitional lesions were more likely to be diagnosed only by targeted cores.Conclusion: MRI-TRUS guided prostate biopsy improves the detection of PCa, but systematic biopsy is still essential. In selected cases (PIRADS 5), contralateral lobe systematic biopsy can safely be avoided. Pre-biopsy mpMRI might reduce the number of biopsy sessions in patients with anterior and transitional lesions.

show abstract

Section: Discussionsupporting

confidence: 82%

MRI-TRUS fusion guided prostate biopsy – initial experience and assessment of the role of contralateral lobe systematic biopsy

Andraș

Crişan

Căta³

et al. 2019

Med Ultrason

View full text Add to dashboard Cite

show abstract

“…Furthermore, a combination of multivariate feature selection and XGB was found to be the best machine learning approach, while expert-based feature pre-selection and the addition of features taken from filtered images did not lead to a significant improvement. Importantly, we used datasets with prospectively called PI-RADS 3-5 lesions, in which the overall detection rate of CS PCa is known to be only 55% [12]. Therefore, our results indicate that the developed model may provide additional diagnostic value and might potentially reduce the number of unnecessary biopsies.…”

Section: Discussionmentioning

confidence: 96%

“…Nevertheless, PI-RADS v2 is by no means a perfect system. Radiologists still need extensive experience to correctly discriminate CS from non-CS tumors [11,12], with the additional issue that some lesions are not visible on mpMRI [13,14]. Computer-aided diagnosis (CAD) aimed to increase correct diagnosis; however, due to the use of a small group of handcrafted features, its success is dependent on expert knowledge [15].…”

Section: Introductionmentioning

confidence: 99%

Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral zone prostate cancer

et al. 2019

View full text Add to dashboard Cite

Objectives To create a radiomics approach based on multiparametric magnetic resonance imaging (mpMRI) features extracted from an auto-fixed volume of interest (VOI) that quantifies the phenotype of clinically significant (CS) peripheral zone (PZ) prostate cancer (PCa). Methods This study included 206 patients with 262 prospectively called mpMRI prostate imaging reporting and data system 3-5 PZ lesions. Gleason scores > 6 were defined as CS PCa. Features were extracted with an auto-fixed 12-mm spherical VOI placed around a pin point in each lesion. The value of dynamic contrast-enhanced imaging(DCE), multivariate feature selection and extreme gradient boosting (XGB) vs. univariate feature selection and random forest (RF), expert-based feature pre-selection, and the addition of image filters was investigated using the training (171 lesions) and test (91 lesions) datasets. Results The best model with features from T2-weighted (T2-w) + diffusion-weighted imaging (DWI) + DCE had an area under the curve (AUC) of 0.870 (95% CI 0.980-0.754). Removal of DCE features decreased AUC to 0.816 (95% CI 0.920-0.710), although not significantly (p = 0.119). Multivariate and XGB outperformed univariate and RF (p = 0.028). Expert-based feature pre-selection and image filters had no significant contribution. Conclusions The phenotype of CS PZ PCa lesions can be quantified using a radiomics approach based on features extracted from T2-w + DWI using an auto-fixed VOI. Although DCE features improve diagnostic performance, this is not statistically significant. Multivariate feature selection and XGB should be preferred over univariate feature selection and RF. The developed model may be a valuable addition to traditional visual assessment in diagnosing CS PZ PCa. Key Points • T2-weighted and diffusion-weighted imaging features are essential components of a radiomics model for clinically significant prostate cancer; addition of dynamic contrast-enhanced imaging does not significantly improve diagnostic performance. • Multivariate feature selection and extreme gradient outperform univariate feature selection and random forest. • The developed radiomics model that extracts multiparametric MRI features with an auto-fixed volume of interest may be a valuable addition to visual assessment in diagnosing clinically significant prostate cancer.

show abstract

“…Notably, in the majority of studies using PI-RADS, a category of ≥3 was considered as targetable lesion for biopsy to evaluate its performance in detecting PCa [1,[7][8][9][10][11][12][13][14][15]. Studies on PI-RADS category 1 and 2 lesions are lacking [11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Comparing Prostate Imaging-Reporting and Data System Version 2 (PI-RADSv2) Category 1 and 2 Groups: Clinical Implication of Negative Multiparametric Magnetic Resonance Imaging

Kim

Lee

Hwang

et al. 2020

BioMed Research International

View full text Add to dashboard Cite

Objectives. To evaluate the clinicopathological differences between Prostate Imaging-Reporting and Data System (PI-RADS) version 2 (v2) category 1 and 2 groups. Materials and Methods. We retrospectively reviewed our two institutional clinical databases: (1) transrectal ultrasound (TRUS)/magnetic resonance imaging (MRI) fusion biopsy cohort (n=706) and (2) radical prostatectomy (RP) cohort (n=1403). Subsequently, we performed comparative analyses between PI-RADSv2 category 1 and 2 groups. Clinically significant prostate cancer (csPCa) was defined as the presence of Gleason score GS≥3+4 in a single biopsy core, and adverse pathology (AP) was defined as high-grade (primary Gleason pattern 4 or any pattern 5) and/or non-organ-confined disease (pT3/N1). We also performed multivariate logistic regression analyses for AP. Results. In the TRUS/MRI fusion biopsy cohort, no significant differences in detection rates of all cancer (18.2% vs. 29.0%, respectively, P=0.730) or csPCa (9.1% vs. 9.9%, respectively, P=0.692) were observed between PI-RADSv2 category 1 and 2 groups. There were no significant differences in pathologic outcomes including Gleason score (≥4+3, 21.2% vs. 29.9%, respectively, P=0.420) or detection rate of AP (27.3% vs. 33.8%, respectively, P=0.561) between the two groups in the RP cohort either. PI-RADSv2 category 1 or 2 had no significant association with AP, even in univariate analysis (P=0.299). Conclusions. PI-RADSv2 categories 1 and 2 had similar performance to predict clinicopathological outcomes. Consequently, these two categories may be unified into a single category. Negative mpMRI does not guarantee the absence of AP, as with csPCa.

show abstract

Validation of Prostate Imaging Reporting and Data System Version 2 for the Detection of Prostate Cancer

Cited by 58 publications

References 19 publications

MRI-TRUS fusion guided prostate biopsy – initial experience and assessment of the role of contralateral lobe systematic biopsy

MRI-TRUS fusion guided prostate biopsy – initial experience and assessment of the role of contralateral lobe systematic biopsy

Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral zone prostate cancer

Comparing Prostate Imaging-Reporting and Data System Version 2 (PI-RADSv2) Category 1 and 2 Groups: Clinical Implication of Negative Multiparametric Magnetic Resonance Imaging

Contact Info

Product

Resources

About