Clinical Research Directory

Validation on Clinical Adaptability of the Foundation Model Specific to Neuroimaging Diagnosis

This clinic trial aims to investigate whether artificial intelligence (AI) diagnostic tools at neurological diseases diagnosis on brain CT/MRI can improve the work efficiency of specialized neuroimaging physicians, with a specific focus on its clinical value in distinguishing normal from abnormal findings, critical value identification, and neurological disease classification. Using pathological and/or discharge diagnoses of neurological diseases as the gold standard, an AI model will be trained on over 10,000 CT/MRI cases to achieve diagnostic performance comparable to that of neurological radiologists before being transformed and putted to use. Furthermore, clinical trials will be conducted in sub-studies (abnormal cases identification, critical value assessment, and neurological disease classification) to validate the clinical utility of AI and human-AI collaboration in the precise diagnosis of neurological disorders. The expected outcomes include reducing missed and misdiagnosis rates, enabling rapid screening of critical conditions, and achieving precise imaging-based diagnosis by using AI tools.

AI-Powered Precision Decision-Making for Pancreatic Diseases

This multicenter clinical trial evaluates an artificial intelligence (AI) system designed to assist in the diagnosis and management of pancreatic diseases. Using contrast-enhanced CT scans, the study compares the AI's recommendations against the decisions of experienced clinicians to verify the system's accuracy and safety in a real-world setting. Patients are categorized into three management groups: Intervention (surgery/treatment), Intensive Surveillance (close monitoring), or Routine Surveillance (standard follow-up). The primary goal is to determine if the AI system can reliably classify patients, reduce the risk of missing malignant lesions, and prevent unnecessary surgeries, thereby improving clinical decision-making for pancreatic conditions.

Radiomics-Based Non-Invasive MRI Differentiation of Uterine Sarcomas and Fibroids

This retrospective case-control study aims to develop and validate a diagnostic model based on multimodal big data and artificial intelligence to differentiate uterine leiomyoma from uterine sarcoma. Investigators will extract historical case data from existing inpatient and outpatient records, including medical history, physical and gynecological examination findings, MRI imaging data, laboratory results, and pathological records. The study seeks to address the question of whether integrating diverse retrospective clinical data with advanced AI techniques can accurately classify uterine tumors as benign leiomyomas or malignant sarcomas, thereby supporting clinical decision-making and optimizing diagnostic workflows.

Early Diagnosis of Upper Digestive Tract Disease

Upper digestive tract cancer (UDC) is a major disease burden worldwide encompassing all cancers involving the digestive tract (from oral cavity to duodenum). A majority of patients presenting with this disease are diagnosed late and have poor overall survival rates (\<20%). NICE referral guidelines for diagnostic endoscopy are usually associated with late disease. Exhaled breath testing is a non-invasive and acceptable technology utilising mass spectrometry (MS) which has shown promise at diagnosing cancer at an early stage. Previous research has shown that products formed as a result of metabolism can be measured in breath and saliva (biomarkers). This has the ability to accurately identify patients with upper gastrointestinal (UGI) cancers from breath. Our initial pilot data has demonstrated that changes in the breakdown of metabolites release volatile organic compounds (VOC) which can be measured with MS. This data is supported by other patient studies. However no previous study has been performed utilising a non-invasive technique with breath and saliva. Thus the aim of this study is to identify VOCs present in patients with this disease. In this multi-centre study the investigators want to overcome the limitations of previous work by utilising non-invasive samples (breath, saliva and urine) in patients in multiple sites. The investigators aim to conduct a study in patients with UDC and those without. The investigators hope that the results of this study will provide evidence for large scale analysis of patients with this disease, demonstrate the feasibility of this technique and move this valuable test forward into mainstream medical practice. The major advantage of this test is that it is easy to undertake and painless for the patient. This study of products in breath, saliva and urine will be useful for detecting UDC to allow treatment at an early stage, improving overall survival.

Assessment of Pancreatic Physiological and Pathological Characteristics Based on Spectral CT

Patients who visited our hospital for various reasons from January 2024, underwent CT scans involving the pancreas, and were eligible for spectral post-processing reconstruction were included in the study. This research collected spectral CT data related to the pancreas at different phases, as well as physiological and pathological states for these patients. Quantitative analysis was conducted on post-processed data under different physiological and pathological states, including parameters such as pancreatic iodine uptake features, attenuation interval slopes, and extracellular volume size. In conjunction with general patient status, biochemical tests, and postoperative pathological results, the study aimed to identify correlations between parameters, develop models, and conduct research by comparing traditional CT data, which could be matched with spectral CT from the PACS database since its establishment.