Artificial Intelligence (AI)-based Medical Image Segmentation for 3D Printing and Naked Eye 3D Visualization

Abstract: Image segmentation for 3D printing and 3D visualization has become an essential component in many fields of medical research, teaching, and clinical practice. Radiation oncologists plan treatment based on 3D tumor target segmentation from CT and MRI images. Radiologists and neurosurgeons detect atherosclerotic plaques based on 3D vessel segmentation from MRI and vessel wall imaging. Cardiac surgeons plan valve replacement surgery based on 3D printing of heart structure from CT and MRI images. Urologists communicate with patients by displaying 3D view of tumors and pelvic organs from MRI and CT images. Diagnosis and treatment planning of bone fracture and osteosarcoma heavily relies on 3D bone and tumor segmentation from CT images. Medical image segmentation requires sophisticated computerized quantifications and visualization tools. Recently, with the development of AI technology, tumors or organs can be quickly and accurately detected and automatically contoured from medical images. This paper introduces a platform-independent, general purpose image segmentation and 3D visualization program specifically designed to meet the needs of medical research and clinical practice communities. This application, named AIMIS-3D (Artificial Intelligence-based Medical Image Segmentation for 3D Printing and Naked Eye 3D Visualization), enables clinical and quantitative analysis of 3D objects segmented from medical images. AIMIS-3D can be embedded into a naked eye 3D visualization system with the support of hand gesture recognition and voice control by multiple users. This all-in-one machine can enhance communication among doctors and between doctors and patients.

Key words: Medical Image Segmentation, 3D Printing, Naked Eye 3D Visualization.