Research Projects

The United Nations and World Economic Forum have estimated that the cumulative loss on the global economy due to non-communicable diseases (NCDs) could reach USD$47 trillion by 2030, should matters remain status quo. Most NCDs perturb the human musculoskeletal system and can have a debilitating impact on quality of life. Musculoskeletal disorders (MSDs) are conditions that can affect muscles, bones and joints, leading to pain and disability. Medical imaging plays an unequivocal and irreplaceable role in the management of MSDs. Advances in medical image acquisition are well adapted in clinical practices in the treatment of MSDs, however advances in medical image post-processing have not yet been exploited in the treatments, decision making and diagnostic processes for MSDs.This sub-domain of image post-processing has seen the confluence of advances from computer science, including machine learning, big data analytics, and artificial intelligence. These have provided the theoretical underpinning and practical data access to develop models that learn directly from data associations across subjects, time, modalities, resolutions, etc. This would be beneficial to clinicians and researchers managing the scourge of MSDs by greatly enhancing the informational value of existing clinical imaging techniques. Applications of these emergent techniques in the domain of imaging-based clinical practices are scarce – mostly due to the paucity of applications directly focused on MSDs, as well as difficulties faced in validating such applications for their clinical utility. The emergence of phenomenological data-driven models based on machine learning could revolutionize image post-processing workflows and provide a critical rethinking and transformation of current MSDs clinical practices. This grant proposes to build an ambitious transformative technology premised on a holistic approach, a robust medical image dataset, data-driven machine learning statistical models, deep learning networks, and intuitive information workflows between the models and clinical practices by developing a virtual statistical multi-domain, multi-scale musculoskeletal human modelling framework (VSM³-HUMAN). The technology development will occur via three-way approach by 1) creating a unique, large, ethnically Indian, gender specific, multi-domain imaging dataset of the entire musculoskeletal system, 2) developing data-driven statistical models of the entire human musculoskeletal system using two advanced and novel machine learning approaches (Statistical modeling and deep learning) and extensively validating them, and 3) illustrating a seamless transition of the technological framework in targeted clinical practices. The project will be led Dr. Borotikar (Symbiosis International (Deemed University)) who is a renowned expert on the clinical management of MSDs using translational research in computational modelling and currently heading Symbiosis Centre for Medical Image Analysis.