Post Radiotherapy MRI Based AI System to Predict Radiation Proctitis for Pelvic Cancers

This is a multicenter, prospective, observational clinical study for seeking out a better way to predict the radiation proctitis in patients with pelvic cancers based on the post-radiotherapy Magnetic Resonance Imaging (MRI) data. Patients who have been pathologically diagnosed as pelvic cancers will be enrolled from the Sixth Affiliated Hospital of Sun Yat-sen University, Sir Run Run Shaw Hospital and the Third Affiliated Hospital of Kunming Medical College. Patients with pelvic cancers who received radiotherapy will be enrolled and their post-radiotherapy MRI images will be used to predict their radiation proctitis or not. The clinical symptoms, endoscopic findings, imaging and histopathology as a standard. The predictive efficacy will be tested in this multicenter, prospective clinical study.

• Artificial Intelligence (Diagnostic test): investigators utilize a Artificial Intelligence (AI) supportive system to predict radiation proctitis for patients with pelvic cancers underwent radiotherapy

Primary outcomes

• The area under curve (AUC) of Receiver Operating Characteristic (ROC) curves of AI prediction system in prediction radiation proctitis [baseline]: The area under curve (AUC) of Receiver Operating Characteristic (ROC) curves of AI prediction system in identifying the radiation proctitis candidates from non-radiation proctitis individuals among pelvic cancers underwent radiotherapy

Secondary outcomes

• The specificity of AI prediction system in prediction radiation proctitis [baseline]: The specificity of AI prediction system in identifying the radiation proctitis candidates from non-radiation proctitis individuals among pelvic cancers underwent radiotherapy

Other outcomes

• The sensitivity of AI prediction system in prediction the radiation proctitis candidates [baseline]: The sensitivity of AI prediction system in identifying the radiation proctitis candidates from non-radiation proctitis individuals among pelvic cancers underwent radiotherapy

Sex: All, ages: 18 Years to 75 Years

Inclusion Criteria:

* pathologically diagnosed as pelvic tumours
* intending to receive or undergoing radiotherapy
* MRI (high-solution T2-weighted imaging, contrast-enhanced T1-weighted imaging, and diffusion-weighted imaging are required) examination is completed after radiotherapy

Exclusion Criteria:

* insufficient imaging quality of MRI (e.g., lack of sequence, motion artifacts)
* incomplete radiotherapy

• Xinjuan Fan, MD, Study chair, Sixth Affiliated Hospital, Sun Yat-sen University
• Weidong Han, MD, Principal investigator, Sir Run Run Shaw Hospital
• Zhenhui Li, MD, Principal investigator, The Third Affiliated Hospital of Kunming Medical College.