Development of an Artificial Intelligence System for Assessment of Tumor Risk and Diagnosis and Treatment Based on Multimodal Data Fusion Using Deep Learning Technology
Overview
- Phase
- Not Applicable
- Intervention
- Not specified
- Conditions
- Artificial Intelligence
- Sponsor
- Wuhan Union Hospital, China
- Enrollment
- 3000
- Locations
- 1
- Primary Endpoint
- The outcome of clinical diagnosis of suspected patients with colorectal cancer or lesion (Benign/Malignant).
- Status
- Recruiting
- Last Updated
- 3 years ago
Overview
Brief Summary
To improve the accuracy of risk prediction, screening and treatment outcome of cancer, we aim to establish a medical database that includes standardized and structured clinical diagnosis and treatment information, image features, pathological features, and multi-omics information and to develop a multi-modal data fusion-based technology system using artificial intelligence technology based on database.
Detailed Description
The main aims are as follows: 1. To establish a data platform for multi-modal information of common tumors (lung cancer/pulmonary nodules, stomach and colorectal cancers) : electronic medical records (including routine clinical detection, treatment, outcome), pathological image data, medical imaging (CT, MRI, ultrasound, nuclear medicine, etc.), multiple omics data (genome, transcriptome, and metabolome, proteomics) omics data, etiology and carcinogenic exposure information. 2. We will make use of artificial intelligence technology to create the multi-modal medical big data cross-analysis technology and the above disease individualized accurate diagnosis and curative effect prediction models. In order to solve the three key problems of multi-modal data fusion mining, such as unbalanced, small sample size, and poor interpretability, we will establish an artificial intelligence recognition algorithm for image images and pathological images, and use image processing and deep learning technologies to mine multi-level depth visual features of image data and pathological data. In addition, we will use bioinformatics analysis algorithms to conduct molecular network mining and functional analysis of molecular markers at the level of multiple omics technologies (pathologic, genomic, transcriptome, metabolome, proteome, etc.).
Investigators
Yang Jin
Professor
Wuhan Union Hospital, China
Eligibility Criteria
Inclusion Criteria
- •Participants with the suspected of lung cancer/node, or stomach cancer/lesion, or colorectal cancer/leision
- •Participants that have signed informed consent.
- •Participants with detailed electronic medical records, image records, pathological records, multi-omics information, and other important clinical diagnostic information.
- •Healthy participants with no clinical diagnosis of lung cancer/node, or stomach cancer/lesion, or colorectal cancer/leision.
Exclusion Criteria
- •Participants with primary clinical and pathological data missing.
- •Participants lost to follow-up.
- •Participants with too poor medical image quality to perform segment and mark ROI accurately
Outcomes
Primary Outcomes
The outcome of clinical diagnosis of suspected patients with colorectal cancer or lesion (Benign/Malignant).
Time Frame: 2022-2026
① Benign ② Malignant
The outcome of clinical diagnosis of suspected patients with lung cancer/pulmonary nodular (Benign/Malignant nodule)
Time Frame: 2022-2026
The outcome of clinical diagnosis of patients with lung cancer/pulmonary nodular (Benign/Malignant nodule). ① Benign nodule ② Malignant neoplasm/nodule: squamous cell carcinoma, adenocarcinoma, small cell carcinoma, and large cell carcinoma.
The outcome of clinical diagnosis of suspected patients with stomach cancer or lesion (Benign/Malignant).
Time Frame: 2022-2026
① Benign ② Malignant
Treatment response of anti-cancer therapy at first evaluation in patients with lung/stomach/colorectal cancer (CR, PR, PD, SD).
Time Frame: 2022-2026
The treatment response of anti-cancer therapy at first evaluation in patients with lung/stomach/colorectal cancer follows The Response Evaluation Criteria In Solid Tumors (RECIST version 1.1) from the World Health Organization (WHO). The evaluation index is as follows. CR (complete response): Disappearance of all target lesions and reduction in the short axis measurement of all pathologic lymph nodes to ≤10 mm. PR (partial response): 30% decrease in the sum of the longest diameter of the target lesions compared with baseline. PD (progressive disease):≥20% increase of at least 5 mm in the sum of the longest diameter of the target lesions compared with the smallest sum of the longest diameter recorded OR The appearance of new lesions, including those detected by FDG-PET (fludeoxyglucose positron emission tomography). SD (stable disease): Neither PR nor PD.