A prediction model for bone metastasis of prostate cancer:based on clinical and ultrasound radiomics features
ZUBAYRA·Yisikandaier
JIA Zhiying
WANG Changchun
WANG Yizhen
QIN Shuang
GUO Kai
Abstract：Objective To develop a model integrating ultrasound radiomics features and clinical indicators for the preliminary prediction of prostate cancer bone metastasis and to explore its diagnostic value.Methods One hundred and ten patients who underwent transrectal two-dimensional prostate ultrasound,whole-body bone scan,and were pathologically confirmed to have prostate cancer(via biopsy or radical resection specimens)at the Affiliated Cancer Hospital of Xinjiang Medical University from April 2023 to April 2024 were retrospectively enrolled.Based on the presence of bone metastasis detected by whole-body bone scan,they were categorized into group A(bone metastasis-positive)and group B(bone metastasis-negative).After delineating target lesions and extracting ultrasound gray-scale features,we compared the ultrasound radiomics features and clinical indicators between the two groups.Then,we constructed three prediction models for prostate cancer bone metastasis:the ultrasound radiomics prediction model,the clinical feature prediction model,and the combined prediction model.Internal validation,calibration,and ROC curve analysis were performed to assess the models predictive efficacy.Results Clinical baseline data analysis revealed that total prostate-specific antigen was an independent risk factor for clinical manifestations(P<0.05).Nine ultrasound radiomics features were selected to build the radiomics prediction model.The AUC of the clinical model was 0.719(95%CI:0.656-0.855),while the combined model exhibited superior predictive performance with an AUC of 0.850(95%CI:0.482-0.820).The calibration curve indicated that the Nomogram had favorable predictive capability,and the DCA curve demonstrated that the combined model possessed high clinical applicability.Conclusion The nomogram integrating clinical and ultrasound features holds certain clinical value in predicting prostate cancer bone metastasis.It can provide a reference for ultrasonographers and clinicians in diagnosis and treatment decision-making.
Keywords：prostate cancerbone metastasisultrasound radiomics
Publication Date：2025-08-20
Online Publishing Date：2025-09-22(First online date of this platform, not the publication date of the document)
Pages：6( 1010-1015 )