Deep learning on T2WI to predict the muscle-invasive bladder cancer: a multi-center clinical study

• Published in: Scientific reports Vol. 15; no. 1; pp. 9942 - 9
• Main Authors: Cai, Lingkai, Yang, Xiao, Yu, Jie, Shao, Qiang, Wang, Gongcheng, Yuan, Baorui, Zhuang, Juntao, Li, Kai, Wu, Qikai, Liu, Peikun, Yu, Ruixi, Cao, Qiang, Li, Pengchao, Sun, Xueying, Zou, Yuan, Fu, Xue, Fang, Xiangming, Chen, Chunxiao, Lu, Qiang
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 22.03.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 631/67/2321; 631/67/589; Accuracy; Adult; Aged; Aged, 80 and over; Bladder cancer; Cancer; Deep Learning; Female; Humanities and Social Sciences; Humans; Invasiveness; Magnetic Resonance Imaging - methods; Male; MIBC; Middle Aged; MRI; multidisciplinary; Neoplasm Invasiveness; Predictive Value of Tests; Science; Science (multidisciplinary); Urinary Bladder - diagnostic imaging; Urinary Bladder - pathology; Urinary Bladder Neoplasms - diagnostic imaging; Urinary Bladder Neoplasms - pathology; Deep learning; MIBC; MRI; Bladder cancer
• DOI: 10.1038/s41598-024-82909-3
• ISSN: 2045-2322

To develop a deep learning (DL) model based on MRI to predict muscle-invasive bladder cancer (MIBC). A total of 559 patients, including 521 patients in our center and 38 patients in external centers were collected from 2012 to 2023 to construct the DL model. In this study, the DL model was utilized to differentiate between MIBC and NMIBC based on three-channel image inputs, including original T2WI images, segmented bladder, and regions of interest. Inception V3 was employed for model construction. The accuracy, sensitivity (SN), specificity (SP), positive predictive value (PPV) and negative predictive value (NPV) for predicting MIBC by DL model were 92.4%, 94.7%, 91.5%, 81.8% and 97.7% in the validation set and 92.1%, 86.8%, 94.6%, 88.5% and 93.8% in the internal test set. In the external test set, these values were 81.6%, 57.1%, 87.1%, 50.0% and 90.0%. Additionally, the accuracy, SN, SP, PPV, and NPV for predicting MIBC were 93.5%, 100%, 93.4%, 11.1%, and 100% in VI-RADS 2; 80.0%, 66.7%, 87.2%, 73.7% and 82.9% in VI-RADS 3; 90.3%, 91.7%, 85.7%, 95.7%, 75.0% in VI-RADS 4. The accuracy, SN, and PPV were 93.9%, 93.9%, and 100% in VI-RADS 5. The DL model based on T2WI can effectively predict MIBC and serve as a valuable complement to VI-RADS 3.