AI-Based Diagnosis and Staging of Bladder Cancer Using Ultrasound, MRI, and Pathology Images Predicting Effectiveness of New Chemotherapy Treatments

What this Trial Is About

Bladder cancer is the most common malignant tumor in the urinary system, and determining whether it has invaded the muscle layer is important for choosing the right treatment. This research focuses on using advanced artificial intelligence methods, including deep learning and transfer learning, to improve the accuracy of bladder cancer staging before surgery and to predict how well patients might respond to new chemotherapy treatments. The goal is to reduce overtreatment and help doctors make better decisions based on a multi-omics diagnostic model combining imaging and pathology data. The study involves collecting ultrasound images, magnetic resonance images, pathology slides, and clinical data from patients diagnosed with bladder cancer. These data will be processed using AI algorithms to build models that can accurately identify muscle invasion and predict prognosis. Participants will be grouped into training, internal validation, and external validation sets to develop and test these AI systems. The project also includes creating immune cell maps from ultrasound images and pathology to explore tumor microenvironment features. Participants will undergo contrast-enhanced ultrasound within two weeks before surgery and have follow-up visits at three months postoperatively. Researchers will collect baseline clinical information and imaging data for AI analysis, with tissue samples stained for immune cell study. The studys main measure is the detection of muscle invasion through ultrasound imaging, and outcomes include evaluating the AI systems diagnostic performance. The research aims to provide a helpful tool for clinical treatment decisions and improve diagnostic efficiency in bladder cancer care.

Bladder Cancer Staging and Prediction of New Adjuvant Chemotherapy Efficacy Based on Deep Learning and Transfer Learning in Ultrasound-Magnetic Resonance-Pathology Multimodal Multiscale