Lei Liang1, Xin Zhi1, Ya Sun1, Huarong Li1, Jiajun Wang1, Jingxu Xu2, Jun Guo1. 1. Department of Ultrasound, Aerospace Center Hospital, Beijing, China. 2. Department of Research Collaboration, R&D Center, Beijing Deepwise & League of PHD Technology Co., Ltd, Beijing, China.
Abstract
OBJECTIVES: To evaluate the potential of a clinical-based model, a multiparametric ultrasound-based radiomics model, and a clinical-radiomics combined model for predicting prostate cancer (PCa). METHODS: A total of 112 patients with prostate lesions were included in this retrospective study. Among them, 58 patients had no prostate cancer detected by biopsy and 54 patients had prostate cancer. Clinical risk factors related to PCa (age, prostate volume, serum PSA, etc.) were collected in all patients. Prior to surgery, patients received transrectal ultrasound (TRUS), shear-wave elastography (SWE) and TRUS-guided prostate biopsy. We used the five-fold cross-validation method to verify the results of training and validation sets of different models. The images were manually delineated and registered. All modes of ultrasound radiomics were retrieved. Machine learning used the pathology of "12+X" biopsy as a reference to draw the benign and malignant regions of interest (ROI) through the application of LASSO regression. Three models were developed to predict the PCa: a clinical model, a multiparametric ultrasound-based radiomics model and a clinical-radiomics combined model. The diagnostic performance and clinical net benefit of each model were compared by receiver operating characteristic curve (ROC) analysis and decision curve. RESULTS: The multiparametric ultrasound radiomics reached area under the curve (AUC) of 0.85 for predicting PCa, meanwhile, AUC of B-mode radiomics and SWE radiomics were 0.74 and 0.80, respectively. Additionally, the clinical-radiomics combined model (AUC: 0.90) achieved greater predictive efficacy than the radiomics model (AUC: 0.85) and clinical model (AUC: 0.84). The decision curve analysis also showed that the combined model had higher net benefits in a wide range of high risk threshold than either the radiomics model or the clinical model. CONCLUSIONS: Clinical-radiomics combined model can improve the accuracy of PCa predictions both in terms of diagnostic performance and clinical net benefit, compared with evaluating only clinical risk factors or radiomics score associated with PCa.
OBJECTIVES: To evaluate the potential of a clinical-based model, a multiparametric ultrasound-based radiomics model, and a clinical-radiomics combined model for predicting prostate cancer (PCa). METHODS: A total of 112 patients with prostate lesions were included in this retrospective study. Among them, 58 patients had no prostate cancer detected by biopsy and 54 patients had prostate cancer. Clinical risk factors related to PCa (age, prostate volume, serum PSA, etc.) were collected in all patients. Prior to surgery, patients received transrectal ultrasound (TRUS), shear-wave elastography (SWE) and TRUS-guided prostate biopsy. We used the five-fold cross-validation method to verify the results of training and validation sets of different models. The images were manually delineated and registered. All modes of ultrasound radiomics were retrieved. Machine learning used the pathology of "12+X" biopsy as a reference to draw the benign and malignant regions of interest (ROI) through the application of LASSO regression. Three models were developed to predict the PCa: a clinical model, a multiparametric ultrasound-based radiomics model and a clinical-radiomics combined model. The diagnostic performance and clinical net benefit of each model were compared by receiver operating characteristic curve (ROC) analysis and decision curve. RESULTS: The multiparametric ultrasound radiomics reached area under the curve (AUC) of 0.85 for predicting PCa, meanwhile, AUC of B-mode radiomics and SWE radiomics were 0.74 and 0.80, respectively. Additionally, the clinical-radiomics combined model (AUC: 0.90) achieved greater predictive efficacy than the radiomics model (AUC: 0.85) and clinical model (AUC: 0.84). The decision curve analysis also showed that the combined model had higher net benefits in a wide range of high risk threshold than either the radiomics model or the clinical model. CONCLUSIONS: Clinical-radiomics combined model can improve the accuracy of PCa predictions both in terms of diagnostic performance and clinical net benefit, compared with evaluating only clinical risk factors or radiomics score associated with PCa.
Authors: Daniel W Good; Grant D Stewart; Steven Hammer; Paul Scanlan; Wenmiao Shu; Simon Phipps; Robert Reuben; Alan S McNeill Journal: BJU Int Date: 2013-07-26 Impact factor: 5.588
Authors: Peter R Carroll; J Kellogg Parsons; Gerald Andriole; Robert R Bahnson; Erik P Castle; William J Catalona; Douglas M Dahl; John W Davis; Jonathan I Epstein; Ruth B Etzioni; Thomas Farrington; George P Hemstreet; Mark H Kawachi; Simon Kim; Paul H Lange; Kevin R Loughlin; William Lowrance; Paul Maroni; James Mohler; Todd M Morgan; Kelvin A Moses; Robert B Nadler; Michael Poch; Chuck Scales; Terrence M Shaneyfelt; Marc C Smaldone; Geoffrey Sonn; Preston Sprenkle; Andrew J Vickers; Robert Wake; Dorothy A Shead; Deborah A Freedman-Cass Journal: J Natl Compr Canc Netw Date: 2016-05 Impact factor: 11.908
Authors: Nicolas Mottet; Joaquim Bellmunt; Michel Bolla; Erik Briers; Marcus G Cumberbatch; Maria De Santis; Nicola Fossati; Tobias Gross; Ann M Henry; Steven Joniau; Thomas B Lam; Malcolm D Mason; Vsevolod B Matveev; Paul C Moldovan; Roderick C N van den Bergh; Thomas Van den Broeck; Henk G van der Poel; Theo H van der Kwast; Olivier Rouvière; Ivo G Schoots; Thomas Wiegel; Philip Cornford Journal: Eur Urol Date: 2016-08-25 Impact factor: 20.096