Objective To establish an artificial intelligence(AI)diagnostic model for the histopathologic diagnosis of extramammary Paget's disease(EMPD)and to evaluate its efficiency for the diagnosis and differential diagnosis of EMPD.Methods All non-tumor skin disease patients who underwent skin tissue biopsy in Department of Dermatology of First Affiliated Hospital of Army Medical University from September 2003 to February 2023 were recruited,and their pathological data were collected,including EMPD,Bowen's disease(BD),squamous cell carcinoma(SCC),and epidermal hyperplasia and hypertrophy.With EMPD as the main research subject,the histopathological images of BD,SCC,and non-tumor skin diseases were included in the study.The histopathological data of 4 types of diseases was classified and diagnosed by ResNet101 and DenseNet121 deep learning neural networks,and the performance of these models was evaluated.Results The AUC values of the ResNet101 diagnostic model for the diagnosis of EMPD,BD,SCC and non-tumor skin diseases on the images at x20 magnification were 0.97,0.98,1.00 and 0.96,respectively,with an accuracy of 0.925±0.011,while the AUC values on the images at x40 magnification were 1.00,0.99,1.00 and 0.97,respectively,with an accuracy of 0.943±0.017.The AUC values of the DenseNet121 diagnostic model for the diagnosis of 4 diseases on the images at x20 magnification were 0.98,0.95,0.99 and 1.00,respectively,with an accuracy of 0.912±0.034,while the AUC values on the images at x40 magnification were 0.99,0.96,1.00 and 1.00,respectively,with an accuracy of 0.971±0.012.Our results indicated that the histopathologic diagnostic model could effectively differentiate EMPD from BD,SCC and non-tumor skin diseases at low power magnification.The FLPOs of ResNet101 was 786.6 M,and the parameter was 4.5 M;The FLPOs of DensNet121 was 289.7 M,and the parameter was 0.8M.Conclusion Our AI diagnostic model is of good effectiveness in the diagnosis and differential diagnosis of EMPD.DenseNet121 is recommended as the dermatopathological diagnostic model of this study.

The accurate diagnosis of burn depth is one of the important problems in the field of burn surgery.The diagnosis accuracy rate is directly related to the treatment plan and effect.The existed clinical diagnosis methods mainly depend on the experience of burn surgeon,making the accuracy rate from 50％ to 65％.In order to improve the accuracy rate of clinical burn depth diagnosis,a large number of diagnosis methods based on imaging are proposed,however,all of the methods are still in the stage of experimental research.In this paper,the research advances on the diagnosis techniques of burn depth are summarized,both the advantages and the shortcomings are pointed,and the development trend of diagnosis techniques of burn depth is expected.

"Flipped Classroom" is a new kind of "student-centered" teaching model, which can give full play to the advantages of both sides of teaching and learning. According to this teaching model, we redesigned the teaching process, in which the students studied by themselves and built their own knowledge system. Moreover, each of them took part in three stages of experimental design including digital signal collection, analysis and processing in groups. Results have shown that this model can fully stimulate students' learning interest, not only helps students to deepen understanding of digital signal processing theory knowledge, but also strengthen the ability of autonomous learning and team collaboration. The teaching model maybe have certain reference function in comprehensive experiment teaching of Digital Signal Processing course for biomedical engineering specialty.

Based on the summary and reflection of the existing course construction content, this paper redesigns the course teaching to Brain Functional Imaging and forms a new curriculum construction scheme, including improving the professional teachers' ability of the teaching team by means of "internal training" + "external introduction", building an online and offline integrated teaching mode by combining online teaching resources such as course website with offline teaching (such as literature guidance, classroom discussion, comprehensive experimental design, etc.), and designing comprehensive experiments related to Electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS), which is driven by scientific research projects, based on the scientific research experimental platform of the teaching and research department. This construction scheme is of great significance for improving the teaching quality of the course, stimulating the learning interest of graduate students, and cultivating the comprehensive application and practical innovation ability of graduate students' brain imaging technology. And it also provides the reference for the further construction of the course and teaching reform in the future.