This study was a prospective, multicenter observational clinical study, A total of 150 patients with bladder malignant tumor who was admitted to the urology department of each center for treatment and underwent electric resection or radical cystectomy were planned to be enrolled. In order to analyze the sensitivity、specificity and accuracy of artificial intelligence in predicting postoperative pathological staging, Patients who entered the group were followed up for 3 years, then, we analyzed the correlation between artificial intelligence prediction results and patient OS PFS RFS. It was preliminarily verified that the results of the artificial intelligence model have the potential to predict the prognosis of patients with bladder cancer.

Preliminary research: This research is multi-disciplinary joint research by combining artificial intelligence with magnetic resonance, it can make the preoperative determination of bladder cancer stage more accurate and guides the clinician worker's treatment plan. At present, It has been constructed that an artificial intelligence model based on preoperative magnetic resonance images to predict staging and patient prognosis. We built a staging prediction model through deep learning artificial intelligence network, and collected magnetic resonance image data and related postoperative pathological data of patients, afterwards, We followed 576 patients on the basis of staging model construction. By obtaining OS, PFS, and RFS of patients, a part was randomly selected as a training set for training the deep learning network model. The other part is used as a test set to verify its accuracy. This study was a prospective, multicenter observational clinical study, A total of 150 patients with bladder malignant tumor who was admitted to the urology department of each center for treatment and underwent electric resection or radical cystectomy were planned to be enrolled. In order to analyze the sensitivity、specificity and accuracy of artificial intelligence in predicting postoperative pathological staging, Patients who entered the group were followed up for 3 years, then, we analyzed the correlation between artificial intelligence prediction results and patient OS PFS RFS. It was preliminarily verified that the results of the artificial intelligence model have the potential to predict the prognosis of patients with bladder cancer.

Inclusion Criteria:

1. Preoperative examination prompts the patient to be bladder cancer;
2. There is no limit on the gender;
3. The age of 18 years old or more;
4. Can provide preoperative MRI images;
5. Agree to provide personal basic clinical information and pathological and imaging data for scientific research, and sign informed consent;
6. Agree to provide monitoring results during follow-up monitoring for recurrence.

Exclusion Criteria:

1. Patient was unable to provide preoperative MRI images, including MRI images after neoadjuvant therapy and before surgery；
2. Patients with incomplete pathological information of samples were unable to provide accurate staging and grading information；
3. Patients cannot be operated on due to their own reasons: severe heart failure, acute myocardial infarction, severe heart and lung diseases, etc., they cannot tolerate normal surgical treatment;
4. Patients who had recently undergone surgery (e.g., TURBT) prior to MRI examination；
5. The researcher thinks there are any conditions that may impair the subject or cause the subject to fail to meet or perform study requirements;
6. Patients unable to provide written informed consent.

Patients receive MRI at each study center and undergo the operation.