Font Size: a A A

Multi-sequence And Multi-regional MR Radiomics For The Preoperative Assessment Of Muscle Invasion In Bladder Cancer

Posted on:2024-08-17Degree:MasterType:Thesis
Country:ChinaCandidate:L ZhangFull Text:PDF
GTID:2544307148479114Subject:Imaging and nuclear medicine
Abstract/Summary:PDF Full Text Request
Objective:Whether bladder cancer(BCa)invades muscle is a determinant of management.However,the accuracy of preoperative diagnosis of muscle invasion is not satisfactory.Magnetic resonance imaging(MRI)-based radiomics is a tool to assess the muscular invasion of BCa.To investigate the value of multi-sequence and multi-regional MRI-based radiomics for assessing muscle invasion of BCa.Methods:342 patients with pathologically confirmed BCa were retrospectively enrolled and randomly divided into a training set(239 cases)and a validation set(103 cases).All patients underwent MRI within 20 days before surgery including T2-weighted imaging(T2WI),diffusion-weighted imaging(DWI),and dynamic contrast-enhanced(DCE)imaging.Patients were divided into muscle-invasive(79 cases)and non-muscle-invasive(263 cases).Two radiologists delineated the whole tumor,tumor body,and muscle layer of BCa,respectively,and extracted radiomic features.Recursive feature elimination(RFE),pearson correlation coefficient(PCC),logistic regression,least absolute shrinkage and selection operator(Lasso)regression analysis and 5-fold cross-validation were used to screen features and build a radiomics scoring model.The clinical data were collected to construct a clinical model and a radiomics-clinical nomogram.Results:23,688 features were extracted.After screening,the radiomics scoring model was constructed using 9 radiomics features with area under curve(AUC)values of 0.933 and0.916 in the training and validation sets,respectively.The clinical model was constructed using 5 clinical independent risk factors;the AUC values in the training set and validation set were 0.876 and 0.840,respectively.After logistic regression analysis,the AUC values of the radiomics-clinical nomogram were made up of 4 clinical independent risk factors and radiomics scores were 0.955 and 0.924 for the training and the validation sets,respectively.The Delong test between radiomics-clinical nomogram and clinical model shows p<0.001.The Delong test between radiomics scoring model and clinical model shows p<0.05.Conclusion:Multi-sequence and multi-regional MRI-based radiomics scoring model could effectively assess the state of BCa muscular invasion.In terms of evaluating the muscular invasion of bladder cancer,the radiomics scoring model is superior to the clinical model,and the radiomics clinical nomogram is significantly superior to the clinical model.
Keywords/Search Tags:Bladder Cancer, Magnetic Resonance Imaging, Radiomics, Muscle invasion, Tumor staging
PDF Full Text Request
Related items