Abstract: Objective　To explore the application value of artificial intelligence (AI) imaging visualization teaching method based on 3D reconstruction in chest CT anatomy teaching, and solve the pain points of complex chest anatomical structure, high requirement for spatial imagination, and difficulty in image reading in traditional teaching.Methods　A total of 100 resident physicians who participated in chest CT anatomy teaching in Beijing Shijitan Hospital, Capital Medical University, from January 2023 to December 2024 were enrolled as subjects and they were randomly divided into the experimental group (n=50) and the control group (n=50) using the random number table method. The control group adopted the traditional teaching method, lectures combining with anatomical atlases, organ models and two-dimensional CT images. The experimental group adopted the AI-assisted 3D reconstruction visualization teaching method, which converted chest CT images into three-dimensional models through automatic 3D reconstruction software and carried out interactive teaching combined with problem-based learning (PBL). After the teaching, the teaching effects were evaluated through theoretical examinations, practical skill assessments and satisfaction questionnaires.Results　The theoretical examination scores of the experimental group [(87.23±4.35) points] were significantly higher than those of the control group [(81.05±5.21) points](P<0.001). In the practical skill assessment, the scores of CT image reading [(17.86±1.52) points], lesion localization [(18.12±1.37) points], clinical thinking [(17.69±1.45) points] and intraoperative score (18.35±1.28) in the experimental group were all superior to the corresponding indicators in the control group [(14.23±1.86) points, (13.95±1.74) points, (14.51±1.63) points, (14.87±1.59) points] (all P<0.001). The overall teaching satisfaction score of the experimental group [(79.02±5.58) points] was higher than that of the control group [(70.75±6.09) points] (P<0.001), and 92.00% of the students believed that this method could improve learning interest.Conclusion　AI imaging visualization teaching method based on 3D reconstruction can intuitively present complex thoracic anatomical structures, significantly improve students' theoretical level, practical skills and learning enthusiasm, and provide an efficient new model for chest CT anatomy teaching.

Key words:  3D reconstruction, artificial intelligence, imaging visualization, chest CT, anatomy teaching, teaching effect