Peking Union Medical College Hospital

Beijing United Imaging Research Institute of Intelligent Imaging

Yining Wang

Jian Wang

Xiao Dong Li

Yue Sun

Jian Cao

Yan Yi

Chanjuan Qu

Zhengyu Jin

Yanyu Li

Keting Xu

Zhen Qian

Kang Zhou

Shuaikun Wang

Lu Lin

A method and apparatus for identifying a vulnerable coronary plaque based on a multimodal large language model (MM-LLM) are provided. The method includes: acquiring a target 3D coronary computed tomography angiography (CCTA) image and a target straightened curved planar reformation (SCPR) image; acquiring plaque mask information of a blood vessel based on the target SCPR image; acquiring basic plaque data based on the plaque mask information; acquiring fluid dynamics data of each plaque area based on the SCPR image; acquiring basic clinical testing information; standardizing above image data, structural data, and textual data separately, and performing, by a regression mapping network, feature fusion to acquire a first fusion feature; acquiring a trained vulnerable plaque identification LLM; and inputting the first fusion feature into the vulnerable plaque identification LLM to acquire an identification result. The method solve problems of poor single-image feature expression ability and low identification performance in traditional technologies.

Method and apparatus for identifying vulnerable coronary plaque based on multimodal large language model (MM-LLM)

A preparation method of an anti-PD-1/PD-L1 monoclonal antibody (mAb)-induced autoimmune myocarditis model is provided, including: mediating a model with adeno-associated virus 9 (AAV9) to achieve the high expression of PDL1 in a myocardial tissue, and applying an anti-PD-1/PD-L1 mAb to the model with high PDL1 expression in the myocardial tissue for modeling. The present disclosure also provides use of an animal model prepared by the preparation method. The model prepared by the present disclosure truly simulates the pathogenesis and clinical course of autoimmune myocarditis in a patient administered with an anti-PD1/PD-L1 mAb, is close to a pathophysiological status of a clinical patient, has a high modeling rate, and can be dynamically monitored.

Mouse model of myocarditits

Growing community of inventors

Beijing, China

Yining Wang