Clinically significant prostate cancer detection on MRI: A radiomic shape features study. Issue 116 (July 2019)

• Record Type: Journal Article
• Authors: Cuocolo, Renato; Stanzione, Arnaldo; Ponsiglione, Andrea; Romeo, Valeria; Verde, Francesco; Creta, Massimiliano; La Rocca, Roberto; Longo, Nicola; Pace, Leonardo; Imbriaco, Massimo
• Is Part Of: European journal of radiology. Issue 116(2019)
• Page Start: 144
• Page End: 149
• Publication Date: 2019-07
• Subjects: PCa prostate cancer -- PSA prostate-specific antigen -- GS Gleason score -- mpMRI multiparametric MRI -- csPCa clinically significant prostate cancer -- TRUS transrectal ultrasound -- VOI volume of interest -- AUC area under the curve -- ROC receiver operating characteristic -- T2w T2 weighted -- SAVR surface area to volume ratio -- DCE dynamic contrast enhanced; MRI -- Radiomics -- Shape -- Prostate cancer -- Gleason score; Medical radiology -- Periodicals; Radiology -- Periodicals; Radiologie médicale -- Périodiques; Medical radiology; Periodicals; 616.075705
• DOI: 10.1016/j.ejrad.2019.05.006
• Languages: English
• ISSNs: 0720-048X

Abstract

Highlights: MRI index lesion shape features can differentiate between csPCa and non csPCa. Surface area to volume ratio is the best predictor of high-grade prostate cancer. Surface area to volume ratio performs better when extracted from the ADC map. Abstract: Purpose: Prostate multiparametric MRI (mpMRI) is the imaging modality of choice for detecting clinically significant prostate cancer (csPCa). Among various parameters, lesion maximum diameter and volume are currently considered of value to increase diagnostic accuracy. Quantitative radiomics allows for the extraction of more advanced shape features. Our aim was to assess which shape features derived from MRI index lesions correlate with csPCa presence. Materials and Methods: We retrospectively enrolled 75 consecutive subjects, who underwent mpMRI on a 3 T scanner, divided based on MRI index lesion Gleason Score in a csPCa group (GS > 3 + 4, n = 41) and a non-csPCa one (n = 34). Ten shape features were extracted both from axial T2-weighted and ADC maps images, after lesion tridimensional segmentation. Univariable and multivariable logistic analysis were used to evaluate the relationship between shape features and csPCa. Diagnostic performance was assessed measuring the area under the curve of the receiver operating characteristic (ROC) analysis. Diagnostic accuracy, sensitivity, and specificity were determined using the best cut-off on each ROC. A P value < 0.05 was considered statistically significant. Results: Univariable analysis demonstrated that almost every shape feature was statistically significant between csPCa e non-csPCa groups. However, multivariable analysis revealed that the parameter defined as surface area to volume ratio (SAVR), especially when extracted from ADC maps is the strongest independent predictor of csPCa among tested shape features. Conclusion: The radiomic shape feature SAVR, extracted from ADC maps after index lesion segmentation, appears as a promising tool for csPCa detection.