Shuaishuai Xu1, Qiuying Yao1, Guiqin Liu1, Di Jin2, Haige Chen2, Jianrong Xu1, Zhicheng Li3,4, Guangyu Wu5. 1. Department of Radiology, Ren Ji Hospital, School of Medicine, Shanghai Jiao Tong University, No.1630, Dongfang road, Pudong, Shanghai, 200127, China. 2. Department of Urology, Ren Ji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China. 3. Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China. zc.li@siat.ac.cn. 4. Shenzhen Peng Cheng Laboratory, Shenzhen, China. zc.li@siat.ac.cn. 5. Department of Radiology, Ren Ji Hospital, School of Medicine, Shanghai Jiao Tong University, No.1630, Dongfang road, Pudong, Shanghai, 200127, China. danielrau@163.com.
Abstract
PURPOSE: To investigate the value of radiomics features from diffusion-weighted imaging (DWI) in differentiating muscle-invasive bladder cancer (MIBC) from non-muscle-invasive bladder cancer (NMIBC). METHODS: This retrospective study included 218 pathologically confirmed bladder cancer patients (training set: 131 patients, 86 MIBC; validation set: 87 patients, 55 MIBC) who underwent DWI before biopsy through transurethral resection (TUR) between July 2014 and December 2018. Radiomics models based on DWI for discriminating state of muscle-invasive were built using random forest (RF) and all-relevant (AR) methods on the training set and were tested on validation set. Combination models based on TUR data were also built. Discrimination performances were evaluated with the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, specificity, and F1 and F2 scores. Qualitative MRI evaluation based on morphology was performed for comparison. RESULTS: No significant difference was found between RF and AR models. RF model was more sensitive than TUR (0.873 vs 0.655, p = 0.019) for discriminating muscle-invasive bladder cancer. When combining RF with TUR, the sensitivity increased to 0.964, significantly higher than TUR (0.655, p < 0.001), MRI evaluation (0.764, p = 0.006), and the combination of TUR and MRI (0.836, p = 0.046). Combining RF and TUR achieved the highest accuracy of 0.897 and F2 score of 0.946. CONCLUSION: Combining DWI radiomics features with TUR could improve the sensitivity and accuracy in discriminating the presence of muscle invasion in bladder cancer for clinical practice. Multicenter, prospective studies are needed to confirm our results. KEY POINTS: • Twenty-seven to 51% of superficial bladder cancers diagnosed by transurethral resection are upstaged to muscle-invasive at radical cystectomy, suggesting its poor sensitivity for discriminating muscle-invasive bladder cancer. • A small subset of selected all-relevant radiomics features exhibited an equivalent performance compared to that of all the extracted features, confirming that radiomics data contained redundant or irrelevant features and that feature selection should be performed in building radiomics models. • Combining DWI radiomics features with transurethral resection could improve in clinical practice the sensitivity and accuracy for the detection of muscle invasion in bladder cancer.
PURPOSE: To investigate the value of radiomics features from diffusion-weighted imaging (DWI) in differentiating muscle-invasive bladder cancer (MIBC) from non-muscle-invasive bladder cancer (NMIBC). METHODS: This retrospective study included 218 pathologically confirmed bladder cancerpatients (training set: 131 patients, 86 MIBC; validation set: 87 patients, 55 MIBC) who underwent DWI before biopsy through transurethral resection (TUR) between July 2014 and December 2018. Radiomics models based on DWI for discriminating state of muscle-invasive were built using random forest (RF) and all-relevant (AR) methods on the training set and were tested on validation set. Combination models based on TUR data were also built. Discrimination performances were evaluated with the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, specificity, and F1 and F2 scores. Qualitative MRI evaluation based on morphology was performed for comparison. RESULTS: No significant difference was found between RF and AR models. RF model was more sensitive than TUR (0.873 vs 0.655, p = 0.019) for discriminating muscle-invasive bladder cancer. When combining RF with TUR, the sensitivity increased to 0.964, significantly higher than TUR (0.655, p < 0.001), MRI evaluation (0.764, p = 0.006), and the combination of TUR and MRI (0.836, p = 0.046). Combining RF and TUR achieved the highest accuracy of 0.897 and F2 score of 0.946. CONCLUSION: Combining DWI radiomics features with TUR could improve the sensitivity and accuracy in discriminating the presence of muscle invasion in bladder cancer for clinical practice. Multicenter, prospective studies are needed to confirm our results. KEY POINTS: • Twenty-seven to 51% of superficial bladder cancers diagnosed by transurethral resection are upstaged to muscle-invasive at radical cystectomy, suggesting its poor sensitivity for discriminating muscle-invasive bladder cancer. • A small subset of selected all-relevant radiomics features exhibited an equivalent performance compared to that of all the extracted features, confirming that radiomics data contained redundant or irrelevant features and that feature selection should be performed in building radiomics models. • Combining DWI radiomics features with transurethral resection could improve in clinical practice the sensitivity and accuracy for the detection of muscle invasion in bladder cancer.
Entities:
Keywords:
Magnetic resonance imaging; Radiomics; Urinary bladder cancer