AUTHOR=Chen Weitian , Gong Mancheng , Zhou Dongsheng , Zhang Lijie , Kong Jie , Jiang Feng , Feng Shengxing , Yuan Runqiang 

TITLE=CT-based deep learning radiomics signature for the preoperative prediction of the muscle-invasive status of bladder cancer

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.1019749

DOI=10.3389/fonc.2022.1019749

ISSN=2234-943X

ABSTRACT=OBJECTIVES: Although the preoperative assessment of whether a bladder cancer (BCa) indicates muscular invasion is crucial for adequate treatment, there currently exist some challenges involved in preoperative diagnosis of BCa with muscular invasion. In this study, we examined the performance of deep features extracted via transfer learning in assessing the muscle invasive status of BCa by constructing a deep learning radiomics (DLR) signature.
METHODS 
A retrospective review covering 173 patients revealed 43 with pathologically proven muscle-invasive bladder cancer (MIBC) and 130 with non–muscle–invasive bladder cancer (non- MIBC). A total of 128 patients were randomly assigned to the training cohort and 45 to the test cohort. The Pearson correlation coefficient combined with the least absolute shrinkage and selection operator (LASSO) was utilized to reduce radiomic redundancy. To decrease the dimension of deep learning features, Principal Component Analysis (PCA) was adopted. Six machine learning classifiers were finally constructed based on deep learning radiomics features, which were adopted to predict the muscle invasion status of bladder cancer. Comprehensive nomograms were developed based on deep learning radiomic (DLR) features and clinical risk factors, in which the area under the curve (AUC), accuracy, sensitivity, and specificity were used to evaluate the model's performance.
Results:   
According to the comparison, DLRS-based models performed the best in predicting muscle violation status, with MLP (Train AUC: 0.973260 (95% CI 0.9488-0.9978) and Test AUC: 0.884298 (95% CI 0.7831-0.9855)) outperforming the other models. In the test cohort, the sensitivity, specificity and accuracy of the MLP model were 0.91 (95% CI 0.551-0.873), 0.78 (95% CI 0.594-0.863) and 0.58 (95% CI 0.729-0.827), respectively. The Nomogram exhibited robust accuracy in the training cohort (AUC=0,967) that was confirmed in the test cohort (AUC=0,932). DCA indicated that Nomogram showed better clinical utility than DLRS-based models, which was demonstrated by the decision curve analysis.
Conclusions: A deep radiomics model constructed with CT images can accurately predict the muscle invasion status of bladder cancer.