To learn more about our research visit

The post Building and Designing Assistive Technology Lab appeared first on Centre for Health Innovation.

When everything is working properly, humans can perform high-demand activities of daily living for more than 100 years. This rarely happens. One of the ���˴�Ƭ barriers to realizing this potential is pathology of the musculoskeletal system. Joints are critical elements for enabling complex movements between segments, and they are remarkable in their ability to facilitate motion while transmitting forces; however, changes due to disease and injury interfere with mechanical function. Clinical interventions aim to alter joint mechanics; however, a lack of information on how healthy joints function during dynamic loading and whether interventions effectively alter joint mechanics as intended limit the ability to optimize treatments. 

The purpose of this work is to use biplanar videoradiography to directly measure a person’s specific anatomy in motion while they perform high-demand activities. Precise information describing the motion of the skeletal system coupled with full-body musculoskeletal modeling approaches may provide insights into joint function and health.

For more information go to

Human Mobility Research Laboratory

Work in the Human Mobility Research Centre’s (HMRC) state-of the-art facility involves unique methods to measure the mechanical factors of joint loading, orientation, and neuromuscular function during activities of daily living, as well as high-demand recreational and occupational tasks.

The research has produced transformative assistive technologies, including energy-returning prosthetic feet, end-user-designed rehabilitative devices, and energy-harvesting backpacks. With the emergence of biosensors and integration algorithms, the group is rapidly moving biomechanical and bioengineering research from the lab into real-world environments and biomedical research into hospitals and communities. 

Bio-Mechatronics and Robotics Laboratory

To fully understand the interactions between a user and an external device, a multidisciplinary approach, including modeling/simulation, design optimization, and human experiments, is required.   Bio-Mechatronics and Robotics Laboratory (BMRL) uses these strategies in designing biomechanical energy harvesters and exoskeletons, studying load carriage, and developing inertial sensor-based algorithms for human movement analysis.   

The post Human Performance Analysis appeared first on Centre for Health Innovation.

Dr. Brian Amsden’s research focus is on the creation of effective biodegradable and biocompatible polymers for biomedical applications. These applications include localized growth factor delivery for therapeutic angiogenesis and for stem cell differentiation, scaffolds for soft connective tissue engineering, and ocular drug delivery. Polymer systems being developed include biodegradable elastomers, electrospun crimped fibre scaffolds, injectable thermoplastics, and mechanically enhanced hydrogels. We are interested in elucidating the mechanisms of degradation of the polymers in vivo to better design these materials for given applications, determining the mechanisms governing drug release, the role polymer biomaterial mechanical properties play in mediating cell proliferation and differentiation, and in controlling polymer surface properties to improve cellular interactions. The work is multidisciplinary and we collaborate routinely with orthopaedic and cardiovascular surgeons, and colleagues in mechanical engineering and cell biology.

For more information go to

The post Advanced Biomaterials Laboratory (ABiL) appeared first on Centre for Health Innovation.

Colorectal cancer is the second leading cause of cancer-related mortality in the United States. More than 50% of patients with colorectal cancer will develop liver metastases in their lifetime with a dismal <10% surviving past three years. Our goal is to leverage all information contained in CT imaging of patients with colorectal liver metastases (CRLM) to better understand the disease course and treatment response as a necessary step toward improving patient outcomes.

Our large interdisciplinary team of experts, combined with the largest clinical experience in CRLM in the western world makes this project a unique and unrivaled opportunity to define radiomics of CRLM. In the future, integration into existing clinical workflows means that small medical centers without highly specialized radiology groups would benefit from predictive algorithms developed at two high-volume centers via a low-cost software update. Successful completion of our aims will provide validated prognostic imaging markers with a pathway to routine clinical use, which are of paramount importance to improving patient survival of this deadly disease.

Project Aims

The objectives of this project are to develop and validate robust imaging features by standardizing image acquisition, to improve automated tools for clinical trial use, and to validate the predictive power of imaging features with external data. To pursue these goals, we have assembled an interdisciplinary team of experts in surgery, medical oncology, pathology, radiology, biostatistics, and image analysis, from Memorial Sloan Kettering Cancer Center (MSK), University of Texas MD Anderson Cancer Center (MDA), Rensselaer Polytechnic Institute, GE Research, and Queen’s University.

The project can be broken down into three aims:

1. Development and validation of imaging features and models that are predictive of treatment response and recurrence of CRLM when undergoing chemotherapy or hepatic resection. These models will be developed and validated using 2450 retrospectively acquired CT images from both MSK and MDA, the two largest liver cancer centers in the United States.
2. Systematic analysis of the repeatability and reproducibility of radiomic imaging features across CT imaging protocols through the prospective collection of test-retest imaging data. CT images are being collected at multiple time points and reconstructed with a variety of parameters in order to determine which radiomic features are robust to variations in CT acquisition protocol, and thus suitable for use across centers.
3. Recapturing even more data from CRLM imaging by developing “rawdiomics” models that fully utilize CT sinogram data. Reconstruction algorithms that transform the raw sinogram data collected by scanners into human-readable images lose information in the process. By operating on the raw data, rawdiomics models will be able to better leverage the complete data collected by CT scanners. Raw sinogram data is being prospectively collected at both MSK and Queen’s University.

In support of these studies we are developing a number of software tools including an automated segmentation pipeline using state of the art machine learning, a tool for remote viewing and editing of model-produced segmentations, and a radiomic feature extraction pipeline.

Publications

• Fan F, Xiong J, Wang G. Universal approximation with quadratic deep networks. Neural networks: the official journal of the International Neural Network Society. 2020 April;124:383-392. PubMed PMID: 32062373; PubMed Central PMCID: PMC7076904; DOI: 10.1016/j.neunet.2020.01.007.
• Fan F, Xiong J, Wang G. Universal approximation with quadratic deep networks. Neural networks: the official journal of the International Neural Network Society. 2020 April;124:383-392. PubMed PMID: 32062373; PubMed Central PMCID: PMC7076904; DOI: 10.1016/j.neunet.2020.01.007.
• Fan F, Xiong J, Wang G. Universal approximation with quadratic deep networks. Neural networks: the official journal of the International Neural Network Society. 2020 April;124:383-392. PubMed PMID: 32062373; PubMed Central PMCID: PMC7076904; DOI: 10.1016/j.neunet.2020.01.007.
• Fan F, Shan H, Kalra MK, Singh R, Qian G, Getzin M, Teng Y, Hahn J, Wang G. Quadratic Autoencoder (Q-AE) for Low-Dose CT Denoising. IEEE transactions on medical imaging. 2020 June;39(6):2035-2050. PubMed PMID: 31902758; PubMed Central PMCID: PMC7376975; DOI: 10.1109/TMI.2019.2963248.
• Fan F, Shan H, Kalra MK, Singh R, Qian G, Getzin M, Teng Y, Hahn J, Wang G. Quadratic Autoencoder (Q-AE) for Low-Dose CT Denoising. IEEE transactions on medical imaging. 2020 June;39(6):2035-2050. PubMed PMID: 31902758; PubMed Central PMCID: PMC7376975; DOI: 10.1109/TMI.2019.2963248.
• Fan F, Shan H, Kalra MK, Singh R, Qian G, Getzin M, Teng Y, Hahn J, Wang G. Quadratic Autoencoder (Q-AE) for Low-Dose CT Denoising. IEEE transactions on medical imaging. 2020 June;39(6):2035-2050. PubMed PMID: 31902758; PubMed Central PMCID: PMC7376975; DOI: 10.1109/TMI.2019.2963248.
• Lyu Q, Shan H, Steber C, Helis C, Whitlow C, Chan M, Wang G. Multi-Contrast Super-Resolution MRI Through a Progressive Network. IEEE transactions on medical imaging. 2020 September;39(9):2738-2749. PubMed PMID: 32086201; PubMed Central PMCID: PMC7673259; DOI: 10.1109/TMI.2020.2974858.
• Creasy JM, Cunanan KM, Chakraborty J, McAuliffe JC, Chou J, Gonen M, Kingham VS, Weiser MR, Balachandran VP, Drebin JA, Kingham TP, Jarnagin WR, D’Angelica MI, Do RKG, Simpson AL. Differences in Liver Parenchyma are Measurable with CT Radiomics at Initial Colon Resection in Patients that Develop Hepatic Metastases from Stage II/III Colon Cancer. Annals of surgical oncology. 2021 April;28(4):1982-1989. PubMed PMID: 32954446; PubMed Central PMCID: PMC7940539; DOI: 10.1245/s10434-020-09134-w.
• Pulvirenti A, Yamashita R, Chakraborty J, Horvat N, Seier K, McIntyre CA, Lawrence SA, Midya A, Koszalka MA, Gonen M, Klimstra DS, Reidy DL, Allen PJ, Do RKG, Simpson AL. Quantitative Computed Tomography Image Analysis to Predict Pancreatic Neuroendocrine Tumor Grade. JCO clinical cancer informatics. 2021 June; 5:679-694. PubMed PMID: 34138636; DOI: 10.1200/CCI.20.00121.

Abstracts

• Raney F, Do RK, Simpson AL. Toward Generalizable Semantic Medical Image Segmentation. Proceedings of the 18th Annual Symposium Imaging Network Ontario. 18th Annual Symposium Imaging Network Ontario; 2020 March 26.
• Hamghalam, M., Frangi, A. F., Lei, B., & Simpson, A. L. (2021, September). Modality Completion via Gaussian Process Prior Variational Autoencoders for Multi-modal Glioma Segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 442-452). Springer, Cham.

People

Advisors

Chun, Yun Shin

De Man, Bruno

Do, Richard Kinh Gian

Simpson, Amber

Wang, Ge

Contributors

Current

• Gangai, Natalie
• Hamghalam, Mohammad
• Lasso, Andras
• Peoples, Jacob
• Tran, Anh
• Ungi, Tamas
• Williams, Travis

Former

• Ayhan, Miranda
• Cong, Wenxiang
• Haneda, Eri
• James, Imani
• Kang, Hyuns
• Lorraine, Peter
• Lyu, Qing
• Meng, Bob
• Niu, Chuang
• O’Grady, Brandon Blake
• Raney, Fraser
• Shan, Hongming
• Zhang, Yaoting

Downloads

Code Repositories

DICOM Segmentation Conversion

Code to convert segmentation label maps with associated DICOM CT images into standard DICOM Segmentation objects is available on Github:

Shared Datasets

TCIA Collection: Colorectal Liver Metastases, MSKCC

We have collected preoperative hepatic CT scans, clinicopathologic data, and recurrence/survival data, from a large, single-institution series of patients (n=198) who underwent hepatic resection of CRLM. For each patient, we also created segmentations of the liver, vessels, tumors, and future liver remnant. The largest of its kind, this dataset is a resource that may aid in the development of quantitative imaging biomarkers, and machine learning models, for the prediction of post-resection hepatic recurrence of CRLM.

This data set is being shared, in standard DICOM format, through The Cancer Imaging Archive (TCIA) under collection name “Colorectal Liver Metastases, MSKCC”.

Supporting Grant: This work is partly funded through the NIH supported grant R01CA233888.

The post Development and Validation of Prognostic Radiomic Markers of Response and Recurrence for Patients with Colorectal Liver Metastases appeared first on Centre for Health Innovation.

Researchers from the Department of Surgery, School of Computing and Biomedical and Molecular Sciences have advanced this technology with the development of the NaviKnife, a next-generation imaging and software navigation system that can reduce the need for additional surgeries and significantly improve outcomes for cancer patients. The NaviKnife can achieve a complete tumor resection with minimal tissue loss. NaviKnife builds on novel multiparametric ultrasound imaging to accurately target the cancer prior to resection, and novel real-time metabolomic tissue typing to identify and trace the tumor boundary during resection while guided by a simple robotic arm.  While current research using this image-guided tool is directed at breast and brain cancer tumours, the broader vision includes integration into vascular and neurosurgery in addition to other kinds of oncosurgical areas. The NaviKnife is one example of how our clinician-scientists are working with industries to commercialize tools for global health.

Related Links

The post The Intelligent Knife (iKnife) Team appeared first on Centre for Health Innovation.

Teams are using AI to predict cancer metastases, detect cancer at the cellular signalling level, and predict biomarkers to better select patients for optimal treatment while reaching rates of 99% accuracy for detecting and labelling cancer across various organs.  One cancer researcher team, led by Dr. Amber Smith, the Director of the CHI and the Canada Research Chair in Biomedical Computing and Informatics, are using natural language processing to solve fundamental problems. Computers are programmed to first process and analyze large amounts of language data from interactions between humans and computers, and then applied to CT scans to predict where cancer could spread. Using AI to detect cancer metastasis means that knowledge of every cancer patient, not only those involved in clinical trials, can be brought to bear for individual patient diagnoses and treatment plans.

This is only one way that large amounts of digital health data are being utilized for transformative research endeavors. While AI and informatics are key technologies for managing next-generation data, specialized training in the digital health context is equally vital.   Dr. Parvin Mousavi is leading another team of experts in computing, machine learning, medical and imaging informatics, data analytics, software systems, and surgery to help train Canada’s future data scientists in medical informatics. The end results will see highly qualified graduates who can build, use, and leverage medical informatics for digital health that can be deployed to hospital, government, industry, and entrepreneurial roles.

The post Applied Artificial Intelligence (AI) and Machine Learning appeared first on Centre for Health Innovation.

The research goal of the Bone and Joint Research Laboratory is to understand the human musculo-skeletal system better, in order to aid the development of biomechanical and safe solutions for the prevention, care and treatment of diseased or injured systems. Dr. Ploeg’s research applies both experimental and computational methods to investigate the human subject over a wide range of scales from musculoskeletal biomechanics down to bone microstructures. The creation of advanced prevention and treatment strategies requires an understanding of their effects on the tissue structures of the body. Biomechanical models that replicate the physical and physiological behavior of tissue structures are an enabling technology for assessing this interaction.

/ploeg-bone-joint-research

The post The Bone and Joint Biomechanics Lab appeared first on Centre for Health Innovation.

Insights into the biophysical environment of human tissue and how an individual’s tissue specifically responds to its stimuli can only be achieved through multidisciplinary approaches and the combination of computer simulations and physical experiments. The creation of advanced prevention and treatment strategies undeniably requires an understanding of their effects on the tissue structures of the body. Biomechanical models that replicate the physical and physiological behavior of tissue structures are an enabling technology for assessing this interaction. Dr. Ploeg and Dr. Rainbow have combined their expertise to research the biological processes responsible for tissue adaptation to mechanical and biochemical stimuli while providing a diverse training environment for students by drawing on skills from subfields of bioengineering, including cellular/tissue engineering, biomechanics, bioreactor design, computer modelling and biomaterials.

Biomechanical data on musculoskeletal alignment, kinematics and kinetics, and tissue density are commonly quantified with motion analysis and imaging tools; however, these data have yet to be combined into a simulation tool. This team of researchers have built a modular bioreactor for co-culturing musculoskeletal tissues as a platform for studying multiple mechanical and biochemical factor interactions of tissues during growth and adaptation. By combining ex vivo tissue culture experiments with computer simulations, this multidisciplinary approach will allow the PIs to quantify the cellular metabolic and morphological responses of tissues to mechanical and biochemical stimuli and use the data to develop computer algorithms to predict growth and adaption in tissues.

Ultimately the goals of this work are to understand tissue growth and adaptation to mechanical and biochemical stimuli, understand the role of neighbouring tissues during musculoskeletal morphogenesis, and establish technology that integrates these mechanisms to engineer functional load-bearing tissues and patient-centric treatment strategies. This will lead to the development of a tool that physicians can use for comprehensive clinical analyses, both pre and post treatment.

The post Regenerative Engineering Laboratory appeared first on Centre for Health Innovation.

Under the leadership of KHSC’s Innovation Lead Dr. Elizabeth Eisenhauer, a team with expertise in Project Management and Data Science are pursuing specific innovation projects aligned with the priority themes in the Portfolio. The projects focus on implementation and evaluation of evidence-based innovations to improve care as well as developing infrastructure for the future.

There are numerous projects underway under the Innovation Portfolio – the following are three examples:

Central Referral and Triage Using Digital Tools – Axing the FAX

As Part of the Digital Health and Elimination of Wait Times themes, Ocean eReferral and Novari eRequest is being implemented in four pilot specialties at KHSC to centralize and digitize how referrals are received with an overarching goal of creating a single, paperless, integrated system for new referral management. Plans are underway to onboard additional specialties over the coming months.

Pathways for Primary Care Management of Common, Non-Urgent Consults

As part of the Initiative to Eliminate Wait Times theme, a working group, comprised of primary care physicians, specialists, and patient experience advisors, has focused on the development of easy-to-follow primary care management pathways for common, non-urgent conditions for which long wait times exist. Evidence to support this work comes from the Calgary Division of Gastroenterology & Hepatology, where significant positive impact was seen on their routine wait list. Launched pathways can be found by visiting: .

Data Science, Digital Health, and Analytics

In partnership with the Centre for Health Innovation, there are increasing opportunities for collaboration by utilizing KHSC’s data (from clinical systems) to develop solutions to system challenges. For example, a project is underway with stakeholders from the Emergency Department (ED) to analyze their intake data to consider how innovative solutions can address ED utilization and patient flow challenges.

Related Links

The post Innovation at Kingston Health Sciences Centre appeared first on Centre for Health Innovation.