In this talk, I will share my journey as a researcher and an educator in medical image analysis and visualization. One of the main topics is a model-based approach to 3D shape recovery to bring the morphometry study to representing the anatomical shape characteristics of human organs in a computational shape model. In particular, I will showcase the deformable modeling research work applied to the hippocampus and ventricles of the brain. For such an application, it is important to robustly restore the individual shape details of the target structure as well as to build the anatomical point correspondences for shape comparisons. It is also critical to decide intuitively what we want to measure from the model deformation. As for the second topic, the MICCAI Challenges that we participated in the last year will be presented. The work is about medical out-of-distribution detection analysis (MOOD), where we proposed a 3D fully self-supervised learning method for volumetric medical image data inspired by recent advancements in representation learning. Finally, I will discuss my efforts in founding and leading the KAIST Special Interest Group on Future Emerging Technology of Medical Imaging. When we started the group with the research labs from various departments, there were many different ways of addressing problems. However, these days, Machine Learning (ML) methods are dominant and become a shared ground, which has various implications.