Research Projects
Real-time Detection and Analysis of Spinal Morphology in Natural Scenes

Contents:
Spinal deformities and malalignment are common yet often under-monitored problems that affect adolescents, working adults and the elderly, leading to pain, poor function and reduced quality of life. At present, assessment of spinal morphology still takes place almost exclusively in the clinic, either by examination of the unclothed back or by standing full-spine radiographs. These methods are important for diagnosis, but they are snapshot-based, clinic-bound and unsuitable for frequent, long-term use at home: they cannot capture how the spine behaves during real everyday activities such as walking, sitting at a desk, carrying a schoolbag or doing rehabilitation exercises, and radiographs also involve ionising radiation and cost. With the rapid development of computer vision and artificial intelligence, it has become technically possible to estimate human posture from ordinary video cameras in natural scenes (for example, a simple smart camera in a living room or rehab centre), yet there is still no dedicated dataset or validated framework focusing on spinal morphology in such environments, especially for patients with spinal deformities. This project aims to bridge this gap by creating a spine-focused natural-scene dataset and an AI system that can monitor spinal posture and shape in real time from everyday video, paving the way for safe, radiation-free, home-based and clinic-adjacent monitoring of spinal health.

Overall Aim:
To develop and validate an AI-based system for real-time monitoring and analysis of spinal morphology in natural scenes, through the creation of a synthetic natural-scene video dataset, an AI framework for spinal posture estimation, and its integration and testing on an active monitoring camera platform in typical everyday environments.

Specific Objectives

1. To construct a natural-scene activity synthetic video dataset, paired with relevant assessments as reference for true spinal morphology and alignment.
2. To develop an AI framework for spinal shape and posture estimation from videos captured in natural scenes, covering both static posture and dynamic movement.
3. To integrate the AI framework into an existing active monitoring camera system to enable real-time inference and intuitive visualisation.
4. To conduct technical and scenario-based validation of the system in typical environments (e.g. simulated home, exercise, and workplace settings).
   
    

Professor T Zhang, Department of Orthopaedics and Traumatology

Professor Teng Grace Zhang is a biomedical engineer with a medical background. Most of Grace’s research combines both disciplines by focusing on the modelling of medical systems with direct clinical applications, including telemedicine, auto-diagnosis, surgical planning and tracking to facilitate real-time feedback with minimal radiation.

Grace founded the Digital Health and Intelligent Medicine Laboratory at HKU in 2018 (https://aimed.hku.hk/). Previously, Grace has worked for nearly seven years as a Scientific Officer at the St George Clinical School of the University of New South Wales (UNSW, Sydney, Australia). All Grace’s tertiary education, including her PhD (Australian Postgraduate Award), was completed at UNSW. Grace also has experience in running multiple instruments and drug trials funded by Medtronic and Sigma. She’s experienced in managing a new system developed as she worked in Kunovus Australia for two years as a system engineer prior to coming to the University of Hong Kong. Senior Members of IEEE, EMBS, ABEC etc. The current ongoing projects include HMRF08192266 on light-based AI-driven malalignment quantification, HMRF19200911 on AIS digital health, PRP/078/21FX for surgical planning, AOSpine for automated spine malalignment screening, MRP/038/20X for non-radiation AI diagnosis and ITS/329/19 for anti-migration bone screws.  

Biography
Lab Homepage
ORCID
tgzhang@hku.hk

For more information or to express interest for this project, please email the supervisor or the specified contact point in the project description.  Interested candidates are advised to enclose with your email:

1. your CV,
2. a brief description of your research interest and experience, and
3. two reference letters (not required for HKUMed UG students seeking MRes[Med]/URIS projects).

Information on the research programme, funding support and admission documentations could be referenced online at the Research Postgraduate Admissions website. General admission enquiries should be directed to rpgmed@hku.hk.

HKUMed MBBS students interested in the Master of Research in Medicine (MRes[Med]) programme may visit the programme website for more information.  

HKUMed UG students interested in the Undergraduate Research Internship Scheme (URIS) may visit the scheme’s website for more information.