Our team is funded to perform multidisciplinary research focusing on developing deep learning technology to develop the novel diagnosis methods and implants for spine disorders.
mskalign: AI-Powered Spine Analysis and Management Platform
We have developed an AI-powered mobile app that enables spine deformity screening, non-surgical management for adolescent idiopathic scoliosis (AIS), and follow-up monitoring. With an auto-detection and spine pathology prediction AI engine, patients can have real-time feedback on their spine conditions using this app. Further, we provide personalized musculoskeletal training plans for users with AIS while allowing clinicians to track their compliance during follow-up. Mobile applications (AlignPro and AlignProCARE) are available at App Store and Google Play, free for downloading.
3D Quantitative Analysis & Surgical Planning
We have developed an AI-driven pipeline for the quantitative analysis of the spine. We have established an unsupervised deep learning framework called MRI-SegFlow for the segmentation of multiple spinal tissues in spinal MRI, which achieved comparable performance with the state-of-art supervised methods and without relying on any manually masked ground truth.
Medical Image Registration and Navigation
In this project, we aim to investigate and develop novel image registration techniques for medical imaging analysis. We explore different registration methods, including intensity-based, feature-based, and learning-based, and evaluate their performance on various medical imaging modalities, such as CT, MR, optical imagery etc.
The outcomes of this project will have significant implications for the clinical use of medical imaging technologies. The developed image registration algorithms can be used to improve the accuracy and efficiency of clinical decision-making and treatment planning, leading to better patient outcomes.
Privacy-preserving and Efficient Distributed Deep Learning in Healthcare
The project aims to enable secure collaboration and deep learning among healthcare institutions while protecting patient privacy. By implementing advanced protocols like homomorphic encryption, the project ensures that individual patient information remains confidential in the local medical instituions. Additionally, the project aims to optimize the training process, reduce computational resources and communication overhead, and improve scalability to enhance the efficiency of model deve-lopment in healthcare. Ultimately, the project seeks to balance the need for data-driven medical advancements with the imperative to maintain strict privacy standards.
Multi-View Mark-Less Surgical Navigation System
Advancements in spinal surgery have been made with the use of screw-based fixation devices. To enhance the precision of interventions such as screw insertion, we would propose a multi-view mark-less surgical navigation system. This system provides real-time tracking of surgical instruments and accurate registration of preoperative CT images. The benefits include improved accuracy, reduced invasiveness, decreased radiation exposure, and potentially more effective procedures.
Wukong: Light-based Disease Analysis and Follow-up
Conventional body appearance analysis lack of quantitative appearance measurements and the conventional X-ray diagnosis for spine deformities involves in radiation exposure. We use depth sensing and AI technologies for accurate body geometry detections and spine curvature generations at our Body and Motion Analysis Laboratory, which is radiation free, portable, and fast with consistent results.
Diseases Classifications and Progress Predictions
Our team has established a large dataset with follow-up spine MRIs and clinical labels. And based on the dataset, several deep learning based methods have been developed for automated disease detection and pathology progression prediction, which can significantly improve clinical efficiency and help radiologists to produce more consistent and objective diagnoses.
Orthopaedic Biomechanics and Implant Design
We have demonstrated that trabecular microarchitecture (TraMicroArcht) can vary the apparent modulus (E), yield strength of trabecular bone accurately. Micro-finite element analysis can quantify the effects of TraMicroArcht on mechanical properties. MicroCT images can be converted directly into digital models via our in-house developed new system and simulate virtual loading effects. Our new system can also have significant application in fast implant design and optimization.
Machine-learning Modeling & Magnetic Monitoring for Scoliosis Correction (M4Sc)
M4Sc uses AI technology and intelligent theater to reduce risks and complications while improving treatment success and patient survival. The project benefits include increasing surgical planning efficiency, providing real-time risk warnings, and reducing radiation exposure and patient discomfort. It also offers accessible and frequent tracking of corrections and low-cost equipment without compromising accuracy. The project aims to improve patients’ quality of life and reduce the impact of scoliosis on their health.