RESUMO
Background/Aims@#The accuracy of endosonographers in diagnosing gastric subepithelial lesions (SELs) using endoscopic ultrasonography (EUS) is influenced by experience and subjectivity. Artificial intelligence (AI) has achieved remarkable development in this field. This study aimed to develop an AI-based EUS diagnostic model for the diagnosis of SELs, and evaluated its efficacy with external validation. @*Methods@#We developed the EUS-AI model with ResNeSt50 using EUS images from two hospitals to predict the histopathology of the gastric SELs originating from muscularis propria. The diagnostic performance of the model was also validated using EUS images obtained from four other hospitals. @*Results@#A total of 2,057 images from 367 patients (375 SELs) were chosen to build the models, and 914 images from 106 patients (108 SELs) were chosen for external validation. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the model for differentiating gastrointestinal stromal tumors (GISTs) and non-GISTs in the external validation sets by images were 82.01%, 68.22%, 86.77%, 59.86%, and 78.12%, respectively. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy in the external validation set by tumors were 83.75%, 71.43%, 89.33%, 60.61%, and 80.56%, respectively. The EUS-AI model showed better performance (especially specificity) than some endosonographers.The model helped improve the sensitivity, specificity, and accuracy of certain endosonographers. @*Conclusions@#We developed an EUS-AI model to classify gastric SELs originating from muscularis propria into GISTs and non-GISTs with good accuracy. The model may help improve the diagnostic performance of endosonographers. Further work is required to develop a multi-modal EUS-AI system.
RESUMO
OBJECTIVE： To synthetize the synthesis of mitoxantrone and evaluate its quality. METHODS： Crude product of mitoxantrone was prepared by slow oxidation of 1，4，5，8-tetrahydro-anthraquinone with N-（2-hydroxyethyl） ethylenediamine in water bath at 50 ℃ for 2 h under argon protection and in dry air for 4 h. The crude product was crystallized by ethanol-n-hexane （4 ∶ 1，V/V） mixture solution， which was cooled overnight and then washed by ethanol-n-hexane mixture for many times. The melting range， pH value of solution， ultraviolet-visible absorption spectrum， infrared structural characteristics， drying weight loss （water loss rate） and critical relative humidity （CRH） of the purified products （4 batches） were investigated. HPLC method was used to determine the contents of mitoxantrone. RESULTS： The mitoxantrone was prepared successfully， and synthetic yield of mitoxantrone was 34.3％； the melting point ranged from 159.1-163.6 ℃. The aqueous solution was alkaline （pH 7.63-9.54）； there was a maximum ultraviolet absorption peak at 235-245 nm； there was a maximum absorption peak of visible light at 590-600 nm； the infrared characteristics were consistent with those described of mitoxantrone in the 2015 edition of the Infrared Spectrum Collection of Drugs； water loss rate were －0.83％-2.36％； CRH value was 54.7％， and the average content of the product was 78.1％（n＝4） by HPLC method. CONCLUSIONS： The mitoxantrone is synthesized under mild， non-toxic and harmless experiment conditions. The synthesis step is simple， the cost is low and the yield is high. The quality of products meets the quality requirements.