Amin Komeili

Headshot of Amin
Adjunct Professor
School of Engineering
Phone number: 
(519) 824-4120 ext. 54741
THRN 1509
Seeking academic or industry partnerships in the area(s) of: 
Veterinary disease diagnosis, Beef and cattle productivity monitoring.
Available positions for grads/undergrads/postdoctoral fellows: 
Please refer to my personal website for open positions

Education and Employment Background

Dr. Amin Komeili received his PhD from the University of Alberta. Between 2014 and 2015 he held a position as a Postdoctoral Researcher at the University of Alberta. From 2015 to 2018 he was a Postdoctoral Researcher at the University of Calgary. Komeili joined the School of Engineering at the University of Guelph in 2018 where he is now an Assistant Professor.

Research Themes 

Komeili’s research focuses on multiscale soft tissue mechanics, with an emphasis on joint function and fracture mechanics. He uses theoretical and experimental approaches in his research toward understanding the mechanobiology of tissues, such as cartilage. He also applies machine learning techniques on the clinical images, such as CT scans, to diagnose soft tissue diseases. Key areas of focus include:

  1. Artificial Intelligence Finite Element (FE) analysis. Despite recent advancements in computational techniques, gaining deep knowledge to find correlations between soft tissue structure and mechanobiological responses is a daunting task due to both complexity of the material structure itself and the convoluted geometric features of an organ. Employment of machine learning techniques in FE analysis may build a reliable framework to tackle the challenges in predicting tissue mechanical and biological responses. We applied this idea in the prediction of pavement lifetime in response to climate change. A neural network was trained using a FE algorithm to predict pavement damage. The algorithm predicted the pavement crack with over 95% accuracy. With this promising result, we are now confident that machine learning algorithms have great potentials to enhance the performance of FE models of soft tissues with complex material behaviours.
  2. Knee biomechanics. Komeili and his team are also creating a detailed FE model of the human knee joint that includes fibre-reinforced cartilage, bone, and ligaments under physiological loading conditions. This model will be used to study tissue growth, fracture mechanics, and disease progression such as osteoarthritis. The next steps involve a multiscale simulation of the knee cartilage to account for the biological response of the tissue in the analysis.
  3. Image Processing. Developing patient-specific FE models in joint and tissue scales involves image segmentation and processing. A manual image segmentation approach is time-consuming by viewing spatial and temporal profiles and examining many series of enhanced pixels. Komeili and his team are exploring the application of AI in biomedical image segmentation. They work on different image modalities such as CT, MRI, and radiographs. In animal hospitals and veterinary clinics, radiographs are taken by veterinary technicians and are often sent for a teleradiology consult by radiologists who are not present on-site. Automated segmentation of biological organs would help diagnose diseases and reduce the turn-around times for these studies that may range from one hour to two to three days.


  • Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery grant, 2020
  • Natural Sciences and Engineering Research Council of Canada (NSERC) Alliance grant, 2021
  • National Research Council Canada (NRC) grant, 2021
  • CARE-AI seed grant, 2021
  • Editorial Review Board, ECRONICON Orthopaedics Journal, 2021