AI-Assisted Non-Contrast CT for Multi-Cancer Screening

Brief summary public domain (ClinicalTrials.gov)

Cancer poses a major public health challenge in China. Early detection can improve treatment outcomes and survival rates. In this study, we will conduct a large-scale, prospective, multi-center cohort study to evaluate the utility of AI-assisted non-contrast CT for multi-cancer screening. The study aims to enroll 1 million asymptomatic participants undergoing routine health examinations, using an AI imaging model based on non-contrast CT to detect seven cancers such as lung, liver, gastric, colorectal, esophageal, pancreatic, and breast cancers. Positive cases will be required to be referred to Shanghai Changhai Hospital for further imaging and care based on National Comprehensive Cancer Network (NCCN) and American College of Radiology (ACR) guidelines. The goal is to assess the AI model's diagnostic performance for seven cancer types, especially for early-stage, resectable tumors.

Detailed description public domain (ClinicalTrials.gov)

Cancer has become a major public health issue in China, seriously affecting population health, the economy, and social development. In 2022, there were an estimated 4.82 million new cancer cases and 2.57 million cancer-related deaths. Lung cancer, liver cancer, gastric cancer, colorectal cancer, esophageal cancer, pancreatic cancer, and breast cancer are the seven leading causes of cancer-related mortality. A successful earlier detection strategy would allow patients to receive timely interventions, improve treatment outcomes, enhance overall survival, and reduce the complexity and cost of treatment. In this study, we will conduct a large-scale, prospective, multi-center cohort study, aiming to evaluate the utility of AI-assisted non-contrast CT for multi-cancer screening. The population consists of individuals who have undergone non-contrast abdominal or chest CT scans at Meinian Onehealth Health Examination Center or Shanghai Changhai Health Examination Center, with an expected enrollment of 1 million participants. A multi-cancer screening model via non-contrast CT, developed by Alibaba DAMO Academy, will be integrated into the PACS system of health examination centers. The imaging AI model will be used to automatically detect various cancerous lesions, including lung cancer, liver cancer, gastric cancer, colorectal cancer, esophageal cancer, pancreatic cancer, and breast cancer. Subjects identified with positive lesions by the AI model will be required to be referred to Shanghai Changhai Hospital for further imaging examinations (such as contrast-enhanced CT, MRI, Endoscopy, etc.) to confirm the final disease status and formulate a treatment plan. Additionally, the medical team should follow care pathways developed based on guidelines from NCCN and ACR, and if necessary, patients will be directed to the multidisciplinary team (MDT) clinic for specific cancer types to determine the diagnostic procedures. The ultimate goal of this study is to comprehensively assess the diagnostic performance metrics of the AI model for each of the seven cancer types individually. These metrics include, but are not limited to, sensitivity, specificity, and positive/negative predictive value. Particular emphasis will be placed on evaluating the model's efficacy in detecting early-stage, resectable tumors. The overarching aim is to determine whether the implementation of this AI-assisted screening approach could potentially lead to improved overall survival rates through …

Intervention public domain (ClinicalTrials.gov)

Diagnostic_Test: AI-Assisted Non-Contrast CT for Multi-Cancer Screening. Participants identified by the AI model as having potential cancerous lesions, including those suspected of lung, liver, gastric, colorectal, esophageal, pancreatic, and breast cancer, will be required to undergo blood tests (for tumor markers) and additional imaging studies (such as contrast-enhanced CT, MRI, Endoscopy, etc.) to confirm the diagnosis of cancerous lesions.

Arm public domain (ClinicalTrials.gov)

Health Examination Cohort (experimental): Asymptomatic participants in routine health examinations receive abdominal or chest non-contrast CT scans, categorized as follows: 1. Meinian cohort 2. Changhai cohort

Primary outcome public domain (ClinicalTrials.gov)

Diagnostic yield. Determine the diagnostic performance metrics of the multi-cancer screening model for each of the seven cancer types (lung, liver, gastric, colorectal, esophageal, pancreatic, and breast cancer) independently. The metrics will encompass sensitivity, specificity, positive/negative predictive values, and overall accuracy. Time frame: 3 years.

Primary outcome public domain (ClinicalTrials.gov)

Incidence. Determine the incidence of the seven cancer types (lung, liver, gastric, colorectal, esophageal, pancreatic, and breast cancer) among the health examination cohort. Time frame: 3 years.

Primary outcome public domain (ClinicalTrials.gov)

Resectable rate. Determine the proportion of resectable tumor among detected cases for each of the seven cancer types (lung, liver, gastric, colorectal, esophageal, pancreatic, and breast cancer). Time frame: 3 years.

Secondary outcome public domain (ClinicalTrials.gov)

Survival time. Time frame: 3 years.

Eligibility public domain (ClinicalTrials.gov)

Inclusion Criteria: 1. Subject is able and willing to provide informed consent and sign an informed consent form. 2. Subject has undergone an abdominal or chest non-contrast CT scan. Exclusion Criteria: 1. Subject has been diagnosed with one of the following cancers within the last five years: lung, liver, stomach, colon, esophageal, pancreatic, or breast cancer; 2. Subject has any medical condition that contraindicates high-resolution MRI/CT/Endoscopy; 3. Subject cannot be followed up or is participating in other clinical trials.

Enrollment public domain (ClinicalTrials.gov)

Enrollment: 1000000 participants (estimated).