Yuji Iyama1,2, Takeshi Nakaura3, Kazuhiro Katahira4, Ayumi Iyama5, Yasunori Nagayama3, Seitaro Oda4, Daisuke Utsunomiya3, Yasuyuki Yamashita3. 1. Department of Diagnostic Radiology, Kumamoto Chuo Hospital, Tainoshima 1-5-1, Kumamoto, Kumamoto, 862-0965, Japan. iyamayuuji28@gmail.com. 2. Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, Honjo 1-1-1, Kumamoto, Kumamoto, 860-8556, Japan. iyamayuuji28@gmail.com. 3. Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, Honjo 1-1-1, Kumamoto, Kumamoto, 860-8556, Japan. 4. Department of Diagnostic Radiology, Kumamoto Chuo Hospital, Tainoshima 1-5-1, Kumamoto, Kumamoto, 862-0965, Japan. 5. Department of Diagnostic Radiology, National Hospital Organization Kumamoto Medical Center, Ninomaru 1-5, Kumamoto, Kumamoto, 860-0008, Japan.
Abstract
PURPOSE: To develop a prediction model to distinguish between transition zone (TZ) cancers and benign prostatic hyperplasia (BPH) on multi-parametric prostate magnetic resonance imaging (mp-MRI). MATERIALS AND METHODS: This retrospective study enrolled 60 patients with either BPH or TZ cancer, who had undergone 3 T-MRI. We generated ten parameters for T2-weighted images (T2WI), diffusion-weighted images (DWI) and dynamic MRI. Using a t-test and multivariate logistic regression (LR) analysis to evaluate the parameters' accuracy, we developed LR models. We calculated the area under the receiver operating characteristic curve (ROC) of LR models by a leave-one-out cross-validation procedure, and the LR model's performance was compared with radiologists' performance with their opinion and with the Prostate Imaging Reporting and Data System (Pi-RADS v2) score. RESULTS: Multivariate LR analysis showed that only standardized T2WI signal and mean apparent diffusion coefficient (ADC) maintained their independent values (P < 0.001). The validation analysis showed that the AUC of the final LR model was comparable to that of board-certified radiologists, and superior to that of Pi-RADS scores. CONCLUSION: A standardized T2WI and mean ADC were independent factors for distinguishing between BPH and TZ cancer. The performance of the LR model was comparable to that of experienced radiologists. KEY POINTS: • It is difficult to diagnose transition zone (TZ) cancer. • We performed quantitative image analysis in multi-parametric MRI. • Standardized-T2WI and mean-ADC were independent factors for diagnosing TZ cancer. • We developed logistic-regression analysis to diagnose TZ cancer accurately. • The performance of the logistic-regression analysis was higher than PIRADSv2.
PURPOSE: To develop a prediction model to distinguish between transition zone (TZ) cancers and benign prostatic hyperplasia (BPH) on multi-parametric prostate magnetic resonance imaging (mp-MRI). MATERIALS AND METHODS: This retrospective study enrolled 60 patients with either BPH or TZ cancer, who had undergone 3 T-MRI. We generated ten parameters for T2-weighted images (T2WI), diffusion-weighted images (DWI) and dynamic MRI. Using a t-test and multivariate logistic regression (LR) analysis to evaluate the parameters' accuracy, we developed LR models. We calculated the area under the receiver operating characteristic curve (ROC) of LR models by a leave-one-out cross-validation procedure, and the LR model's performance was compared with radiologists' performance with their opinion and with the Prostate Imaging Reporting and Data System (Pi-RADS v2) score. RESULTS: Multivariate LR analysis showed that only standardized T2WI signal and mean apparent diffusion coefficient (ADC) maintained their independent values (P < 0.001). The validation analysis showed that the AUC of the final LR model was comparable to that of board-certified radiologists, and superior to that of Pi-RADS scores. CONCLUSION: A standardized T2WI and mean ADC were independent factors for distinguishing between BPH and TZ cancer. The performance of the LR model was comparable to that of experienced radiologists. KEY POINTS: • It is difficult to diagnose transition zone (TZ) cancer. • We performed quantitative image analysis in multi-parametric MRI. • Standardized-T2WI and mean-ADC were independent factors for diagnosing TZ cancer. • We developed logistic-regression analysis to diagnose TZ cancer accurately. • The performance of the logistic-regression analysis was higher than PIRADSv2.
Authors: Caroline M A Hoeks; Jelle O Barentsz; Thomas Hambrock; Derya Yakar; Diederik M Somford; Stijn W T P J Heijmink; Tom W J Scheenen; Pieter C Vos; Henkjan Huisman; Inge M van Oort; J Alfred Witjes; Arend Heerschap; Jurgen J Fütterer Journal: Radiology Date: 2011-10 Impact factor: 11.105
Authors: A Hoang Dinh; R Souchon; C Melodelima; F Bratan; F Mège-Lechevallier; M Colombel; O Rouvière Journal: Diagn Interv Imaging Date: 2014-12-23 Impact factor: 4.026
Authors: Makoto Ohori; Michael W Kattan; Hideshige Koh; Norio Maru; Kevin M Slawin; Shahrokh Shariat; Masatoshi Muramoto; Victor E Reuter; Thomas M Wheeler; Peter T Scardino Journal: J Urol Date: 2004-05 Impact factor: 7.450
Authors: Caroline M A Hoeks; Eline K Vos; Joyce G R Bomers; Jelle O Barentsz; Christina A Hulsbergen-van de Kaa; Tom W Scheenen Journal: Invest Radiol Date: 2013-10 Impact factor: 6.016
Authors: Mike Wenzel; Maria N Welte; Lina Grossmann; Felix Preisser; Lena H Theissen; Clara Humke; Marina Deuker; Simon Bernatz; Philipp Gild; Sascha Ahyai; Pierre I Karakiewicz; Boris Bodelle; Luis A Kluth; Felix K H Chun; Philipp Mandel; Andreas Becker Journal: Front Surg Date: 2021-02-25