A nomogram combined with radiomics features, albuminuria, and metabolic syndrome to predict the risk of myometrial invasion of bladder cancer

Abstract

Background: To establish a preoperative prediction model of myometrial invasion of bladder cancer (BC) based on the radiomics characteristics of multi-parameter thin-slice enhanced computed tomography (CT) imaging.Methods: Data from 100 patients with BC were analyzed retrospectively. The patients were divided into two groups: muscular invasive BC and non-muscular invasive BC. The tumor region was segmented from enhanced CT images (arterial-and venous-phase calibration maps) of all patients using Slicer-3D software. We extracted 1,223 texture features from tumor image data based on the shape and gray-level co-occurrence matrix, gray size region matrix, gray run-length matrix, adjacent gray difference matrix, and gray correlation matrix. The patients were randomly divided into a training group (n=70) and a verification group (n=30) in a 7:3 ratio. Interclass correlation coefficients >0.75, least absolute shrinkage, and selection operator regression were used for feature selection. The prediction model was established by combining Rad-score, independent clinical factors, and support vector machine (SVM), and a radiomics nomogram was constructed. The nomogram was tested using the consistency index, calibration curve, time-dependent receiver operating characteristic curve, and clinical decision curve to predict the myometrial invasion of the bladder preoperatively.Results: Six radiomics features that were significantly related to myometrial invasion of BC were selected to construct a predictive model. The area under the curve (AUC) values of training group and verification group based on SVM were 0.898 (95% CI: 0.820-0.976) and 0.702 (95% CI: 0.495-0.909), respectively.Single factor and multiple factor analysis showed that albuminuria (95% CI: 0.243-2.206, P=0.0014) and metabolic syndrome (95% CI: 0.850-2.935, P<0.001) were independent influencing factors of BC myometrial invasion. Clinical factors and 11 radiomics features were used to construct a comprehensive model for predicting the pathological grade of BC (radiomics + clinical). After a comprehensive comparison, we found that the overall effectiveness of the model (radiomics + clinical) was the highest (AUC =0.8457). Conclusions:Based on the multi-parameter thin-layer enhanced CT radiomics feature can be used as a potential independent predictor of BC myometrial invasion, the model based on parameters can initially quantitatively characterize the risk of myometrial invasion, and has excellent potential for predicting myometrial invasion of BC.

Development and validation of a CT-based deep learning radiomics nomogram to predict muscle invasion in bladder cancer

“…Several studies have reported the promising predictive performance of MRI-based radiomics in preoperatively discriminating between NMIBC and MIBC [ [26] , [27] , [28] , [29] ]. Previous studies have shown that radiomics features extracted from CT can also predict muscular infiltration status in bladder cancer, but most of them were either very small sample sizes [ [ 17 , 18 , 30 ]] or lacked independent external validation [ 31 ]. Our study also demonstrated that radiomics signature alone had promising discriminatory performance in preoperative clinical staging of bladder cancer, with AUCs of 0.840 (95 % CI 0.763–0.918) in the internal validation cohort and 0.807 (95 % CI 0.683–0.930) in the internal validation cohort.…”

“…Recently, radiomics has made great progress in the automatic diagnosis of colorectal tumors, lung masses, breast diseases and some other diseases [ [9] , [10] , [11] , [12] , [13] , [14] ]. The usefulness of CT-based radiomics in differentiating histological variant [ 15 ], tumor grade [ 16 ] and stage [ [ 17 , 18 ]] of bladder tumors has been demonstrated in previous studies, but these studies had some limitations, such as small sample size or no independent external validation set. In addition, deep learning (DL), widely used in image analysis, had the ability to extract deep and complex structures related to specific tasks, which had shown good performance in diagnosis and prognosis prediction for gastric, liver, and renal cancers [ [19] , [20] , [21] ].…”

Nomogram for predicting amputation-free survival in acute lower limb ischemia patients treated by endovascular therapy

“…To the best of our knowledge, the present work is the first study to attempt to estimate the probability of AFS in ALLI patients using a newly developed nomogram. Nomogram establishment is considered a feasible and credible approach for developing disease models [ 9 , 28 ]. In previous studies, determining the probability of AFS based on identified risk factors was not possible.…”

The role of radiomics with machine learning in the prediction of muscle-invasive bladder cancer: A mini review

“…It has become a trend to include clinical risk factors in the prediction model in order to better predict MIS and improve clinical diagnostic performance and application value. These include tumor size ( 15 ), tumor stalk ( 16 ), proteinuria and multiple sclerosis ( 21 ), as well as VI-RADS ( 20 ) and TURBT ( 14 ).The radiomic model incorporating clinical factors performed significantly better than the conventional MRI examination and simply radiomic model in terms of calibration and discrimination. Radiomic-clinical nomogram can be used as a reliable and non-invasive adjunct to differentiate MIBC from NMIBC preoperatively ( 15 ).…”