Yansheng Kan1, Qing Zhang1, Jiange Hao1, Wei Wang1, Junlong Zhuang1, Jie Gao1, Haifeng Huang1, Jing Liang1, Giancarlo Marra2, Giorgio Calleris2, Marco Oderda2, Xiaozhi Zhao3, Paolo Gontero4, Hongqian Guo5. 1. Department of Urology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Institute of Urology, Nanjing University, No. 321 Zhongshan Rd, Nanjing, 210008, Jiangsu Province, China. 2. Department of Urology, Molinette Hospital, Città della Salute e della Scienza, University of Turin, Turin, Italy. 3. Department of Urology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Institute of Urology, Nanjing University, No. 321 Zhongshan Rd, Nanjing, 210008, Jiangsu Province, China. zhaoxz@nju.edu.cn. 4. Department of Urology, Molinette Hospital, Città della Salute e della Scienza, University of Turin, Turin, Italy. paolo.gontero@unito.it. 5. Department of Urology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Institute of Urology, Nanjing University, No. 321 Zhongshan Rd, Nanjing, 210008, Jiangsu Province, China. dr.ghq@nju.edu.cn.
Abstract
OBJECTIVE: To evaluate machine learning-based classifiers in detecting clinically significant prostate cancer (PCa) with Prostate Imaging Reporting and Data System (PI-RADS) score 3 lesions. METHODS: We retrospectively enrolled 346 patients with PI-RADS 3 lesions at two institutions. All patients underwent prostate multiparameter MRI (mpMRI) and transperineal MRI-ultrasonography (MRI-US)-targeted biopsy. We collected data on age, pre-biopsy serum prostate-specific antigen (PSA) level, prostate volume (PV), PSA density (PSAD), the location of suspicious PI-RADS 3 lesions, and histopathology results. Four machine learning-based classifiers-logistic regression, support vector machine, eXtreme Gradient Boosting (XGBoost), and random forest-were trained using datasets from Nanjing Drum Tower Hospital. External validation was carried out using datasets from Molinette Hospital. RESULTS: Among 287 PI-RADS 3 patients, prostate cancer was proven pathologically in 59 (20.6%), and 228 (79.4%) had benign lesions. For 380 PI-RADS 3 lesions, 81 (21.3%) were proven to be PCa and 299 (78.7%) benign. Among four classifiers, the random forest classifier had the best performance in both patient-based and lesion-based datasets, with overall accuracy of 0.713 and 0.860, sensitivity of 0.857 and 0.613, and area under curve (AUC) of 0.771 and 0.832, respectively. In external validation, our best classifiers had an AUC of 0.688 with the best sensitivity (0.870) and specificity (0.500) in the 59 PI-RADS 3 patients in Molinette Hospital dataset. CONCLUSIONS: The machine learning-based random forest classifier provided a reliable probability if a PI-RADS 3 patient was benign. KEY POINTS: • Machine learning-based classifiers could combine the clinical characteristics with accessible information on image report of PI-RADS 3 patient to generate a probability of malignancy. • This probability could assist surgeons to make diagnostic decisions with more confidence and higher efficiency.
OBJECTIVE: To evaluate machine learning-based classifiers in detecting clinically significant prostate cancer (PCa) with Prostate Imaging Reporting and Data System (PI-RADS) score 3 lesions. METHODS: We retrospectively enrolled 346 patients with PI-RADS 3 lesions at two institutions. All patients underwent prostate multiparameter MRI (mpMRI) and transperineal MRI-ultrasonography (MRI-US)-targeted biopsy. We collected data on age, pre-biopsy serum prostate-specific antigen (PSA) level, prostate volume (PV), PSA density (PSAD), the location of suspicious PI-RADS 3 lesions, and histopathology results. Four machine learning-based classifiers-logistic regression, support vector machine, eXtreme Gradient Boosting (XGBoost), and random forest-were trained using datasets from Nanjing Drum Tower Hospital. External validation was carried out using datasets from Molinette Hospital. RESULTS: Among 287 PI-RADS 3 patients, prostate cancer was proven pathologically in 59 (20.6%), and 228 (79.4%) had benign lesions. For 380 PI-RADS 3 lesions, 81 (21.3%) were proven to be PCa and 299 (78.7%) benign. Among four classifiers, the random forest classifier had the best performance in both patient-based and lesion-based datasets, with overall accuracy of 0.713 and 0.860, sensitivity of 0.857 and 0.613, and area under curve (AUC) of 0.771 and 0.832, respectively. In external validation, our best classifiers had an AUC of 0.688 with the best sensitivity (0.870) and specificity (0.500) in the 59 PI-RADS 3 patients in Molinette Hospital dataset. CONCLUSIONS: The machine learning-based random forest classifier provided a reliable probability if a PI-RADS 3 patient was benign. KEY POINTS: • Machine learning-based classifiers could combine the clinical characteristics with accessible information on image report of PI-RADS 3 patient to generate a probability of malignancy. • This probability could assist surgeons to make diagnostic decisions with more confidence and higher efficiency.
Authors: Marloes van der Leest; Erik Cornel; Bas Israël; Rianne Hendriks; Anwar R Padhani; Martijn Hoogenboom; Patrik Zamecnik; Dirk Bakker; Anglita Yanti Setiasti; Jeroen Veltman; Huib van den Hout; Hans van der Lelij; Inge van Oort; Sjoerd Klaver; Frans Debruyne; Michiel Sedelaar; Gerjon Hannink; Maroeska Rovers; Christina Hulsbergen-van de Kaa; Jelle O Barentsz Journal: Eur Urol Date: 2018-11-23 Impact factor: 20.096
Authors: Patrick Schelb; Simon Kohl; Jan Philipp Radtke; Manuel Wiesenfarth; Philipp Kickingereder; Sebastian Bickelhaupt; Tristan Anselm Kuder; Albrecht Stenzinger; Markus Hohenfellner; Heinz-Peter Schlemmer; Klaus H Maier-Hein; David Bonekamp Journal: Radiology Date: 2019-10-08 Impact factor: 11.105
Authors: Bharath Ambale-Venkatesh; Xiaoying Yang; Colin O Wu; Kiang Liu; W Gregory Hundley; Robyn McClelland; Antoinette S Gomes; Aaron R Folsom; Steven Shea; Eliseo Guallar; David A Bluemke; João A C Lima Journal: Circ Res Date: 2017-08-09 Impact factor: 17.367
Authors: Jelle O Barentsz; Jeffrey C Weinreb; Sadhna Verma; Harriet C Thoeny; Clare M Tempany; Faina Shtern; Anwar R Padhani; Daniel Margolis; Katarzyna J Macura; Masoom A Haider; Francois Cornud; Peter L Choyke Journal: Eur Urol Date: 2015-09-08 Impact factor: 20.096
Authors: Martin C S Wong; William B Goggins; Harry H X Wang; Franklin D H Fung; Colette Leung; Samuel Y S Wong; Chi Fai Ng; Joseph J Y Sung Journal: Eur Urol Date: 2016-06-08 Impact factor: 20.096
Authors: Daniël F Osses; Christian Arsov; Lars Schimmöller; Ivo G Schoots; Geert J L H van Leenders; Irene Esposito; Sebastiaan Remmers; Peter Albers; Monique J Roobol Journal: J Pers Med Date: 2020-12-10
Authors: Valentina Brancato; Marco Aiello; Luca Basso; Serena Monti; Luigi Palumbo; Giuseppe Di Costanzo; Marco Salvatore; Alfonso Ragozzino; Carlo Cavaliere Journal: Sci Rep Date: 2021-01-12 Impact factor: 4.379