The Application Value of Artificial Intelligence in MRI Precision Diagnosis and Treatment of Bladder Cancer

Bladder Cancer Clinical Trial

Official title:

Prospective Multi-center Clinical Study on the Application Value of Artificial Intelligence in MRI Precision Diagnosis and Treatment of Bladder Cancer

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT05096533
• Other study ID #: 2021-SR-409
• Status: Recruiting
• Start date: January 1, 2021
• Est. completion date: January 1, 2023

Study information

• Verified date: October 2021
• Source: The First Affiliated Hospital with Nanjing Medical University
• Contact: Lingkai Cai
• Phone: +86 15206213500
• Email: lingkaicai1996[@]163.com
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

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.

Description:

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.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 150
• Est. completion date: January 1, 2023
• Est. primary completion date: May 1, 2022
• Accepts healthy volunteers: No
• Gender: All
• Age group: N/A and older

Eligibility

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.

Related Conditions & MeSH terms

• Bladder Cancer
• Urinary Bladder Neoplasms

Locations

Country	Name	City	State
China	The first affiliated hospital of Nanjing Medical University	Nanjing	Jiangsu

Sponsors (2)

Lead Sponsor	Collaborator
The First Affiliated Hospital with Nanjing Medical University	Nanjing University of Aeronautics and Astronautics

Country where clinical trial is conducted

China, 

References & Publications (3)

Panebianco V, Narumi Y, Altun E, Bochner BH, Efstathiou JA, Hafeez S, Huddart R, Kennish S, Lerner S, Montironi R, Muglia VF, Salomon G, Thomas S, Vargas HA, Witjes JA, Takeuchi M, Barentsz J, Catto JWF. Multiparametric Magnetic Resonance Imaging for Bladder Cancer: Development of VI-RADS (Vesical Imaging-Reporting And Data System). Eur Urol. 2018 Sep;74(3):294-306. doi: 10.1016/j.eururo.2018.04.029. Epub 2018 May 10. Review. — View Citation

Suarez-Ibarrola R, Hein S, Reis G, Gratzke C, Miernik A. Current and future applications of machine and deep learning in urology: a review of the literature on urolithiasis, renal cell carcinoma, and bladder and prostate cancer. World J Urol. 2020 Oct;38(10):2329-2347. doi: 10.1007/s00345-019-03000-5. Epub 2019 Nov 5. Review. — View Citation

Wang H, Luo C, Zhang F, Guan J, Li S, Yao H, Chen J, Luo J, Chen L, Guo Y. Multiparametric MRI for Bladder Cancer: Validation of VI-RADS for the Detection of Detrusor Muscle Invasion. Radiology. 2019 Jun;291(3):668-674. doi: 10.1148/radiol.2019182506. Epub 2019 Apr 23. — View Citation

Outcome

Type	Measure	Description	Time frame	Safety issue
Other	recurrence-free survival	The correlation between artificial intelligence model and RFS in bladder cancer patients was analyzed to preliminarily verify the potential ability of artificial intelligence model results in predicting the prognosis of bladder cancer patients.	3 years after surgery
Other	progression-free survival	The correlation between artificial intelligence model and PFS in bladder cancer patients was analyzed to preliminarily verify the potential ability of artificial intelligence model results in predicting the prognosis of bladder cancer patients.	3 years after surgery
Primary	To explore the application value of artificial intelligence in the precise diagnosis and treatment of bladder tumor, and to improve the accuracy of MRI diagnosis of bladder cancer stage and grade through artificial intelligence.	2?Through Concordance analysis of artificial intelligence diagnosis assay results with gold standard results of surgery, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) of artificial intelligence diagnosis before the operation.	1 year
Secondary	Overall survival	The correlation between artificial intelligence model and OS in bladder cancer patients was analyzed to preliminarily verify the potential ability of artificial intelligence model results in predicting the prognosis of bladder cancer patients.	3 years after surgery