Recent years, convolutional neural network (CNN) is a research hot spot in machine learning and has some application value in computer aided diagnosis. Firstly, this paper briefly introduces the basic principle of CNN. Secondly, it summarizes the improvement on network structure from two dimensions of model and structure optimization. In model structure, it summarizes eleven classical models about CNN in the past 60 years, and introduces its development process according to timeline. In structure optimization, the research progress is summarized from five aspects (input layer, convolution layer, down-sampling layer, full-connected layer and the whole network) of CNN. Thirdly, the learning algorithm is summarized from the optimization algorithm and fusion algorithm. In optimization algorithm, it combs the progress of the algorithm according to optimization purpose. In algorithm fusion, the improvement is summarized from five angles: input layer, convolution layer, down-sampling layer, full-connected layer and output layer. Finally, CNN is mapped into the medical image domain, and it is combined with computer aided diagnosis to explore its application in medical images. It is a good summary for CNN and has positive significance for the development of CNN.
Objective To explore the training framework for medical-engineering interdisciplinary postgraduate students during their early education phase from the perspective of “digital and intelligent rehabilitation”, investigate pedagogical reforms centered on the corresponding curriculum, evaluate the students’ digital health awareness, perception of professional relevance, and attitudes toward future industry trends, and provide empirical evidence for optimizing early-stage training systems. Methods A total of 111 postgraduate students enrolled in the course Medical Technology Integration and Innovation: Intelligent Medicine and Rehabilitation during the 2022-2024 autumn semesters were included as study subjects. Pre- and post-course questionnaires assessed digital health cognition, professional demands, technological relevance, and future-oriented attitudes. Statistical analysis was conducted using SPSS 20.0 software. Results The 111 students included 19 from the 2022 academic year, 39 from the 2023 academic year, and 53 from the 2024 academic year. In each academic year, the student population consisted predominantly of females (>70%) and first-year learners (>90%). Prior to the course, most students were unfamiliar with digital health; only 6, 11, and 24 students from the 2022, 2023, and 2024 academic years, respectively, reported having some knowledge of digital health, though most were merely aware of or had only heard of the concept. From the 2022 to 2024 academic years, the proportions of students who reported having a general understanding of the definition of digital health were 83.3% (5/6), 54.5% (6/11), and 41.7% (10/24), respectively. Over 85% of students in each academic year believed that their profession “needs” digital health technologies across four dimensions: patient-facing services, healthcare provider services, management systems, and data services. Technologies such as artificial intelligence (2022 academic year: 100.0%; 2023 academic year: 90.9%; 2024 academic year: 98.0%), cloud computing and big data (2022 academic year: 100.0%; 2023 academic year: 93.9%; 2024 academic year: 100.0%), and sensors and wearable devices (2022 academic year: 87.5%; 2023 academic year: 87.9%; 2024 academic year: 96.1%) were considered highly relevant to their profession. The proportion of students holding a “very open” attitude increased significantly after the course (2022 academic year: from 47.4% to 58.8%; 2023 academic year: from 33.3% to 40.0%; 2024 academic year: from 45.3% to 70.0%). Conclusions The “Digital and Intelligent Rehabilitation” course may expand students’ professional knowledge breadth and depth during early training, strengthen their comprehension of medical-engineering integration, and foster positive industry engagement attitudes. These findings provide actionable insights and empirical validation for developing systematic, differentiated early-phase training frameworks for medical-engineering interdisciplinary education.