About Project OrthoVis 2.0
OrthoVis 2.0 is an initiative to modernise and enhance a specialised software tool used for assessing joint motion (kinematics) through dynamic fluoroscopy (video X-ray). Originally developed over 15 years ago in MATLAB, the current version of OrthoVis, while highly accurate, is too slow for practical clinical use—taking hours to process just a few seconds of imaging data. Additionally, its segmentation process still requires significant manual input, further delaying results.
This project aims to leverage modern advancements in computer vision and machine learning to drastically improve processing speed, automate segmentation, and enhance usability for clinicians and researchers. By transitioning the software to a more efficient and scalable architecture, the team will develop expertise in image processing, software development, and AI-driven medical applications.
Team members aim to gain hands-on experience in programming (C++, Python, Java), machine learning, and medical imaging. Working closely with clinical and engineering experts, students will contribute to open-source medical software that improves patient care and research outcomes.
OrthoVis 2.0 Student Team
Australian National University - 2025
Our team is made up of seven enthusiastic members from differing academic backgrounds, with unique skillsets, and interests. We are all excited to be working on a project that gives us an opportunity to apply our technical skills in a practical application in OrthoVis 2.0.
Hanna Truong
Bachelor of Computing
I have experience in UI and frontend development and I am fluent in Python. I'm passionate about designing intuitive user interfaces and creating meaningful software solutions, especially those that contribute to the medical field.
Murph Shaw
Bachelor of Software Engineering (H)
My study has focused on practical engineering applications of software in fields such as mechatronics, hardware engineering, computer vision, and robotics. I am excited about working on a project with practical outcomes, alongisde stakeholders who care deeply about the project. In particular, I am motivated by the opportunity to apply advanced software techniques to real-world challenges, especially in fields that intersect with biomichanical engineering and computer vision.
Punit Deshwal
Bachelor of Advanced Computing (H)
I’m currently in my final year of a Bachelor of Advanced Computing (Honours), specializing in machine learning. I have experience in NLP and computer vision, I’m also majoring in cybersecurity. I am comfortable with systems and assembly-level programming. I enjoy approaching problems creatively and from multiple perspectives, and creating the most innovative solutions.
Aung Moe Thet
Bachelor of Advanced Computing (H)
I have a strong interest in coding and software development as well as cybersecurity in general. I have acquired some knowledge in these fields through self-study and self-driven learning.
Avery Xu
Master of Machine Learning and Computer Vision
Coming from a physics background, I'm thrilled to work a project that aims to deepen biomechanical understanding in research and clinical settings. As part of the team, I hope to research and implement state-of-art image processing techniques and potentially contribute to a better solution for healthcare delivery.
Zhiyuan Hou
Master of Computing
My skills include Python coding, Unity development, PyTorch for deep learning, and Gazebo simulator for robotics simulation. I'm particularly interested in the fields of machine learning and software development.
Ruohua Li (Roxy)
Master of Computing
My skills include Python programming, 3D modeling using Meshlab, UI design, and Java development. I have a foundation in human-computer interaction (HCI) and computer graphics, which helps me create intuitive and engaging user interfaces. My interests focus on exploring the intersection of AI and user experience, particularly in improving usability and enhancing interaction between humans and technology.
Project Resources
Please click below to navigate to our project GitHub repository. Here you can find all of the code that we have been working on, as well as important project documentation. Our documentation also incudes various links to papers that explore the fundamental concepts that underpin the original version of OrthoVis.
Work Hours
Throughout 2025, we will be working in The Hive, located in Building 108 at the ANU between the hours of 8AM and 8PM on Wednesday, every week. Please come find us if you want to have a chat and learn more about the project!