Clinical Research Directory

Value of Super-resolution Ultrasonography in Differentiating Benign and Malignant Lymph Nodes

Lymph nodes are one of the most important components of the human immune system, and superficial lymph node enlargement lacks specificity. Ultrasound examination has been widely used in the diagnosis of lymph node lesions and is of great significance in distinguishing between benign and malignant. However, the two-dimensional and Doppler ultrasound features of different types of lymph node lesions overlap and intersect, and the blood flow perfusion information of lymph nodes can provide more information for differentiation. At present, the widely used contrast-enhanced ultrasound is easier to evaluate blood flow perfusion and can display small blood vessels smaller than 100 microns. The diagnostic accuracy of cervical lymph nodes using contrast-enhanced ultrasound is 80-90%. However, current contrast-enhanced ultrasound is limited by physical diffraction, with a resolution ranging from sub-millimeter to millimeter. This limitation hinders the visualization of small blood vessels or microcirculation by ultrasound, and parameters such as vascular size, spatial vascular pattern, and velocity of microcirculation are crucial for disease diagnosis and prognosis evaluation. Super resolution ultrasound (SRUS) is a new blood flow imaging technique. By tracking the movement trajectory of micro-bubbles instead of imaging the micro-bubbles themselves, the ultrasound diffraction limit can be exceeded to improve the sensitivity and image resolution of blood flow. Thus the study aim to evaluate the feasibility of SRUS technology in distinguishing between benign and malignant lymph nodes, and compare the differences in blood flow distribution and perfusion index between benign and malignant lymph nodes under SRUS imaging.

Artificial Intelligence-based Model for the Prediction of Occult Lymph Node Metastasis and Improvement of Clinical Decision-making in Non-small Cell Lung Cancer

This nationwide, multicenter observational study aims to develop and validate a multimodal artificial intelligence (AI) model for detecting occult lymph node metastasis in early-stage non-small cell lung cancer (NSCLC) patients. Despite advances in lymph node staging, 12.9%-39.3% of occult nodal metastasis cases remain undetected preoperatively, affecting treatment decisions. This study will use deep learning to extract imaging features of occult metastasis and combine them with clinical data to build an AI model for risk prediction. This study will provide insights into the feasibility of AI-driven detection of occult metastasis, supporting clinical decision-making and potentially revealing underlying biological mechanisms of lymph node metastasis in NSCLC.