As a graduate student with a background in computer science, my journey did not begin with artificial intelligence or medical image segmentation. Initially, I often felt overwhelmed and anxious about the steep technical barriers posed by deep learning and model training. However, thanks to the open-source community and the wealth of available tools, I had the opportunity to start from scratch and gradually build my own AI research project.
In this talk, I will share my journey from the perspective of a newcomer without a formal background in AI. I will explain how I leveraged public medical datasets, the PyTorch framework, and open-source models on GitHub—such as Vision Mamba UNet—to develop a practical, research-ready medical image segmentation system. By reading documentation, studying open-source code, and participating in developer communities, I gained valuable hands-on experience and learned how to complete a research project even with limited resources.
This session focuses on real-world insights such as “how to get started with AI through open-source,” “the challenges and lessons learned from building my first project,” and “common mistakes beginners should avoid.” I hope my experience will encourage more students and developers who are curious about AI but have not yet taken the first step: you do not need to build everything from scratch. By making the most of open-source resources, you can go farther—and do so with greater confidence—on your AI journey.