Xiang Liu1, Xiangpeng Wang2, Yaofeng Zhang2, Zhaonan Sun1, Xiaodong Zhang1, Xiaoying Wang3. 1. Department of Radiology, Peking University First Hospital, No. 8 Xishiku Street, Xicheng District, Beijing, 100034, China. 2. Beijing Smart Tree Medical Technology Co. Ltd., No. 24, Huangsi Street, Xicheng District, Beijing, 100011, China. 3. Department of Radiology, Peking University First Hospital, No. 8 Xishiku Street, Xicheng District, Beijing, 100034, China. wangxiaoying@bjmu.edu.cn.
Abstract
PURPOSE: To develop and test radiomics models based on manually corrected or automatically gained masks on ADC maps for pelvic lymph node metastasis (PLNM) prediction in patients with prostate cancer (PCa). METHODS: A primary cohort of 474 patients with PCa who underwent prostate mpMRI were retrospectively enrolled for PLNM prediction between January 2017 and January 2020. They were then randomly split into training/validation (n = 332) and test (n = 142) groups for model development and internal testing. Four radiomics models were developed using four masks (manually corrected/automatic prostate gland and PCa lesion segmentation) based on the ADC maps using the primary cohort. Another cohort of 128 patients who underwent radical prostatectomy (RP) with extended pelvic lymph node dissection (ePLND) for PCa was used as the testing cohort between February 2020 and October 2021. The performance of the models was evaluated in terms of discrimination and clinical usefulness using the area under the curve (AUC) and decision curve analysis (DCA). The optimal radiomics model was further compared with Memorial Sloan Kettering Cancer Center (MSKCC) and Briganti 2017 nomograms, and PI-RADS assessment. RESULTS: 17 (13.28%) Patients with PLNM were included in the testing cohort. The radiomics model based on the mask of automatically segmented prostate obtained the highest AUC among the four radiomics models (0.73 vs. 0.63 vs. 0.70 vs. 0.56). Briganti 2017, MSKCC nomograms, and PI-RADS assessment-yielded AUCs of 0.69, 0.71, and 0.70, respectively, and no significant differences were found compared with the optimal radiomics model (P = 0.605-0.955). CONCLUSION: The radiomics model based on the mask of automatically segmented prostate offers a non-invasive method to predict PLNM for patients with PCa. It shows comparable accuracy to the current MKSCC and Briganti nomograms.
PURPOSE: To develop and test radiomics models based on manually corrected or automatically gained masks on ADC maps for pelvic lymph node metastasis (PLNM) prediction in patients with prostate cancer (PCa). METHODS: A primary cohort of 474 patients with PCa who underwent prostate mpMRI were retrospectively enrolled for PLNM prediction between January 2017 and January 2020. They were then randomly split into training/validation (n = 332) and test (n = 142) groups for model development and internal testing. Four radiomics models were developed using four masks (manually corrected/automatic prostate gland and PCa lesion segmentation) based on the ADC maps using the primary cohort. Another cohort of 128 patients who underwent radical prostatectomy (RP) with extended pelvic lymph node dissection (ePLND) for PCa was used as the testing cohort between February 2020 and October 2021. The performance of the models was evaluated in terms of discrimination and clinical usefulness using the area under the curve (AUC) and decision curve analysis (DCA). The optimal radiomics model was further compared with Memorial Sloan Kettering Cancer Center (MSKCC) and Briganti 2017 nomograms, and PI-RADS assessment. RESULTS: 17 (13.28%) Patients with PLNM were included in the testing cohort. The radiomics model based on the mask of automatically segmented prostate obtained the highest AUC among the four radiomics models (0.73 vs. 0.63 vs. 0.70 vs. 0.56). Briganti 2017, MSKCC nomograms, and PI-RADS assessment-yielded AUCs of 0.69, 0.71, and 0.70, respectively, and no significant differences were found compared with the optimal radiomics model (P = 0.605-0.955). CONCLUSION: The radiomics model based on the mask of automatically segmented prostate offers a non-invasive method to predict PLNM for patients with PCa. It shows comparable accuracy to the current MKSCC and Briganti nomograms.
Authors: Lorenzo Bianchi; Giorgio Gandaglia; Nicola Fossati; Nazareno Suardi; Marco Moschini; Vito Cucchiara; Marco Bianchi; Rocco Damiano; Riccardo Schiavina; Shahrokh F Shariat; Francesco Montorsi; Alberto Briganti Journal: Urologia Date: 2015-12-16
Authors: Armando Stabile; Paolo Dell'Oglio; Giorgio Gandaglia; Nicola Fossati; Giorgio Brembilla; Giulia Cristel; Federico Dehò; Vincenzo Scattoni; Tommaso Maga; Andrea Losa; Franco Gaboardi; Gianpiero Cardone; Antonio Esposito; Francesco De Cobelli; Alessandro Del Maschio; Francesco Montorsi; Alberto Briganti Journal: Eur Urol Oncol Date: 2018-05-15
Authors: Felix Preisser; Roderick C N van den Bergh; Giorgio Gandaglia; Piet Ost; Christian I Surcel; Prasanna Sooriakumaran; Francesco Montorsi; Markus Graefen; Henk van der Poel; Alexandre de la Taille; Alberto Briganti; Laurent Salomon; Guillaume Ploussard; Derya Tilki Journal: J Urol Date: 2019-08-22 Impact factor: 7.450
Authors: Khushabu Kasabwala; Neal Patel; Eliza Cricco-Lizza; Adrian A Shimpi; Stanley Weng; Rose M Buchmann; Samaneh Motanagh; Yiyuan Wu; Samprit Banerjee; Francesca Khani; Daniel J Margolis; Brian D Robinson; Jim C Hu Journal: Eur Urol Oncol Date: 2018-08-17
Authors: Giorgio Gandaglia; Nicola Fossati; Emanuele Zaffuto; Marco Bandini; Paolo Dell'Oglio; Carlo Andrea Bravi; Giuseppe Fallara; Francesco Pellegrino; Luigi Nocera; Pierre I Karakiewicz; Zhe Tian; Massimo Freschi; Rodolfo Montironi; Francesco Montorsi; Alberto Briganti Journal: Eur Urol Date: 2017-04-12 Impact factor: 20.096
Authors: Alberto Briganti; Michael L Blute; James H Eastham; Markus Graefen; Axel Heidenreich; Jeffrey R Karnes; Francesco Montorsi; Urs E Studer Journal: Eur Urol Date: 2009-03-10 Impact factor: 20.096