Nomogram Based On Clinical And MR Radiomics Features In Predicting Bone Metastasis In Newly Diagnosed Prostate Cancer Patients

Purpose:To establish nomogram based on clinical and MR radiomics features and discuss its value in predicting bone metastasis of newly diagnosed prostate cancer patients.Materials and Methods:One-hundred and ten patients with newly diagnosed prostate cancer who underwent prostate MRI imaging and were confirmed by pathology in the first Hospital of Lanzhou University from January 2017 to January2022 were enrolled.All patients were divided into bone metastasis group（n=50）and non-bone metastasis group（n=60）according to the results of ^99mTc-methylene diphosphonate whole body skeletal imaging.Radiomics features were extracted from T2WI and ADC maps.The radiomics features were filter by Lasso regression,and the radiomics score（rad-score）was calculated.Univariate and multivariate logistic regression analysis were used to screen the independent clinical risk factors of incipient prostate cancer bone metastasis and to establish a clinical model.Then a combined model based on the independent clinical risk factors and radiomics score was constructed,then its nomogram was drawn to visualize the combined model.Receiver operating characteristic（ROC）curve was used to evaluate the efficacy of each model in predicting bone metastasis in incipient prostate cancer,and the clinical application value of combined model was evaluated by decision curve analysis（DCA）.Results:11 radiomics features were involved to calculate rad-score,and the AUC of the radiomics model was 0.82（95%CI[0.74-0.90]）.Univariate and multivariate analysis showed that t PSA,ALP and N stage were clinical risk factors,and the AUC of the clinical model establised by these three risk factors was 0.93（95%CI[0.88-0.98]）.The combined model composed of a combination of clinical risk factors and radiomics features showed good discrimination and correction（AUC=0.96 95%CI[0.94-0.98]）.DCA demonstrates the clinical utility of the combined model.Conclusion:The nomogram combined with clinical and MR radiomics features has clinical value in predicting bone metastasis of newly diagnosed prostate cancer patients.