A Thyroid Ultrasound Image-based Artificial Intelligence Model for Diagnosis of Central Compartment Lymph Node Metastasis in Papillary Thyroid Carcinoma / 中国医学科学院学报

Objective To establish an artificial intelligence model based on B-mode thyroid ultrasound images to predict central compartment lymph node metastasis(CLNM)in patients with papillary thyroid carcinoma(PTC). Methods We retrieved the clinical manifestations and ultrasound images of the tumors in 309 patients with surgical histologically confirmed PTC and treated in the First Medical Center of PLA General Hospital from January to December in 2018.The datasets were split into the training set and the test set.We established a deep learning-based computer-aided model for the diagnosis of CLNM in patients with PTC and then evaluated the diagnosis performance of this model with the test set. Result The accuracy,sensitivity,specificity,and area under receiver operating characteristic curve of our model for predicting CLNM were 80%,76%,83%,and 0.794,respectively. Conclusion Deep learning-based radiomics can be applied in predicting CLNM in patients with PTC and provide a basis for therapeutic regimen selection in clinical practice.

Effect of carrier size and surface morphology on the aerosolization of formulation in a capsule-based dry powder inhaler / 药学学报

The size and surface morphology of carrier lactose had influence on the aerosolization performance of dry powder inhalers. In this article, chlorpheniramine maleate was blended with two types of commercial carrier lactose, which were Lactohale 100® and Respitose SV003® (SV003), as formulation model. In vitro experiments were conducted using fast screening impactor at 30 L·min-1 and 60 L·min-1 respectively. Meanwhile, computational fluid dynamics (CFD) coupling with discrete element modelling (DEM) was applied to discuss the movements of those two carrier particles in Handihaler® at the flow rate mentioned above. The dispersion characteristics of two formulations and the dispersion mechanism of Handihaler® were analyzed by establishing the relationship between in vitro experiments and numerical simulation. The results of in vitro experiments and CFD-DEM demonstrated that the aerosolization performance of formulation with SV003 was better. The linear correlation (R2 = 0.940 1) between fine particle dose and total energy loss by carrier collision within the wall of device was found by comparing the in vitro experimental results with CFD-DEM results. It revealed that particle-wall collision in Handihaler® had direct impact on the dispersion results of formulation.