Hamed Azarnoush
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hamed Azarnoush has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
Alexander Winkler-Schwartz
Neurosurgical Simulation and Artificial Intelligence Learning Centre, Department of Neurology & Neurosurgery, Montreal Neurological Institute and Hospital, McGill University, Montreal, Quebec, Canada
4 shared publicationsRolando F. Del Maestro
Neurosurgical Simulation and Artificial Intelligence Learning Centre, Department of Neurosurgery, Montreal Neurological Institute and Hospital, McGill University, Montreal, Canada
3 shared publicationsBenoit Boulet
Centre for Intelligent Machines, McGill University, Montreal, Quebec, Canada
2 shared publicationsGuy Lamouche
National Research Council Canada, Boucherville, Quebec, Canada
2 shared publications- Khalid Bajunaid
Department of Surgery, Faculty of Medicine, University of Jeddah, Jeddah, Saudi Arabia
2 shared publications - Saeid Rashidi
Faculty of Medical Sciences & Technologies, Science & Research Branch Islamic Azad University Tehran Iran
2 shared publications
Latest Publications
- Open Access
- 8 September 2023
- Published by Springer Nature in Research Square
Learning Fast Diffeomorphic Registration for Cardiac Motion Estimation in 3D Echocardiography
Echocardiography is a well-established technique for diagnosing and monitoring cardiovascular diseases. Myocardial regional motion analysis has the potential to offer a comprehensive understanding of cardiac health. Accurate and efficient quantification of cardiac motion is crucial for clinical tasks related to cardiac diagnosis and prognosis. Although various methods have been proposed for cardiac motion tracking, they often suffer from long inference times or require numerous adjustable parameters. In this study, we propose a diffeomorphic registration network (DRN) to take advantage of deep neural networks’ capability for registration purposes: their ability to learn complex representations and predict the desired output in a single step. Diffeomorphic image registration offers distinct advantages, such as generating invertible and topology-preserving deformation fields, which are key attributes in the context of cardiac motion. This approach enhances the accuracy and realism of deformation field estimation. The DRN framework employs a neural network to estimate a stationary velocity field, from which the deformation field is derived through the Scaling and Squaring method. Evaluation of methods on a synthetic echocardiography dataset with ground truth displacement vectors demonstrates the superiority of our approach in terms of accuracy. Importantly, it maintains a practical inference time of 316.63 ms per frame, making it suitable for clinical applications. Notably, DRN trained with segmentation labels achieves the best results, with a mean error of 0.81 mm for global tracking error.
- 8 September 2023
- Published by Springer Nature in Research Square
Open AccessLearning Fast Diffeomorphic Registration for Cardiac Motion Estimation in 3D Echocardiography
Echocardiography is a well-established technique for diagnosing and monitoring cardiovascular diseases. Myocardial regional motion analysis has the potential to offer a comprehensive understanding of cardiac health. Accurate and efficient quantification of cardiac motion is crucial for clinical tasks related to cardiac diagnosis and prognosis. Although various methods have been proposed for cardiac motion tracking, they often suffer from long inference times or require numerous adjustable parameters. In this study, we propose a diffeomorphic registration network (DRN) to take advantage of deep neural networks’ capability for registration purposes: their ability to learn complex representations and predict the desired output in a single step. Diffeomorphic image registration offers distinct advantages, such as generating invertible and topology-preserving deformation fields, which are key attributes in the context of cardiac motion. This approach enhances the accuracy and realism of deformation field estimation. The DRN framework employs a neural network to estimate a stationary velocity field, from which the deformation field is derived through the Scaling and Squaring method. Evaluation of methods on a synthetic echocardiography dataset with ground truth displacement vectors demonstrates the superiority of our approach in terms of accuracy. Importantly, it maintains a practical inference time of 316.63 ms per frame, making it suitable for clinical applications. Notably, DRN trained with segmentation labels achieves the best results, with a mean error of 0.81 mm for global tracking error.
- 20 February 2023
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 169
Explosive synchronization dependence on initial conditions: The minimal Kuramoto model
- 20 February 2023
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 169
Explosive synchronization dependence on initial conditions: The minimal Kuramoto model
- 5 January 2023
- Published by Springer Nature in Iranian Journal of Science and Technology, Transactions of Electrical Engineering
- Vol. 47 (3) , 859-869
Design and Implementation of Brain Surgery Bipolar Electrocautery Simulator Using Haptic Technology
- 5 January 2023
- Published by Springer Nature in Iranian Journal of Science and Technology, Transactions of Electrical Engineering
- Vol. 47 (3) , 859-869
Design and Implementation of Brain Surgery Bipolar Electrocautery Simulator Using Haptic Technology
- 15 November 2022
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 152, 106286
Utilizing artificial intelligence and electroencephalography to assess expertise on a simulated neurosurgical task
- 15 November 2022
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 152, 106286
Utilizing artificial intelligence and electroencephalography to assess expertise on a simulated neurosurgical task
- 24 January 2022
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 16 (7) , 1773-1781
Deep active contours using locally controlled distance vector flow
- 24 January 2022
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 16 (7) , 1773-1781
Deep active contours using locally controlled distance vector flow
- 5 January 2022
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 142, 105219
Stain transfer using Generative Adversarial Networks and disentangled features
- 5 January 2022
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 142, 105219
Stain transfer using Generative Adversarial Networks and disentangled features
- 1 May 2020
- Published by Elsevier in Journal of Surgical Education
- Vol. 77 (3) , 643-651
Tremor Assessment during Virtual Reality Brain Tumor Resection
- 1 May 2020
- Published by Elsevier in Journal of Surgical Education
- Vol. 77 (3) , 643-651
Tremor Assessment during Virtual Reality Brain Tumor Resection
- 11 April 2020
- Published by Springer Nature in Medical & Biological Engineering & Computing
- Vol. 58 (6) , 1357-1367
Machine learning distinguishes neurosurgical skill levels in a virtual reality tumor resection task
This study outlines the first investigation of application of machine learning to distinguish “skilled” and “novice” psychomotor performance during a virtual reality (VR) brain tumor resection task. Tumor resection task participants included 23 neurosurgeons and senior neurosurgery residents as the “skilled” group and 92 junior neurosurgery residents and medical students as the “novice” group. The task involved removing a series of virtual brain tumors without causing injury to surrounding tissue. Originally, 150 features were extracted followed by statistical and forward feature selection. The selected features were provided to 4 classifiers, namely, K-Nearest Neighbors, Parzen Window, Support Vector Machine, and Fuzzy K-Nearest Neighbors. Sets of 5 to 30 selected features were provided to the classifiers. A working point of 15 premium features resulted in accuracy values as high as 90% using the Supprt Vector Machine. The obtained results highlight the potentials of machine learning, applied to VR simulation data, to help realign the traditional apprenticeship educational paradigm to a more objective model, based on proven performance standards. Using several scenarios of virtual reality neurosurgical tumor resection together with machine learning classifiers to distinguish skill level
- 11 April 2020
- Published by Springer Nature in Medical & Biological Engineering & Computing
- Vol. 58 (6) , 1357-1367
Machine learning distinguishes neurosurgical skill levels in a virtual reality tumor resection task
This study outlines the first investigation of application of machine learning to distinguish “skilled” and “novice” psychomotor performance during a virtual reality (VR) brain tumor resection task. Tumor resection task participants included 23 neurosurgeons and senior neurosurgery residents as the “skilled” group and 92 junior neurosurgery residents and medical students as the “novice” group. The task involved removing a series of virtual brain tumors without causing injury to surrounding tissue. Originally, 150 features were extracted followed by statistical and forward feature selection. The selected features were provided to 4 classifiers, namely, K-Nearest Neighbors, Parzen Window, Support Vector Machine, and Fuzzy K-Nearest Neighbors. Sets of 5 to 30 selected features were provided to the classifiers. A working point of 15 premium features resulted in accuracy values as high as 90% using the Supprt Vector Machine. The obtained results highlight the potentials of machine learning, applied to VR simulation data, to help realign the traditional apprenticeship educational paradigm to a more objective model, based on proven performance standards. Using several scenarios of virtual reality neurosurgical tumor resection together with machine learning classifiers to distinguish skill level
- 26 April 2019
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 64 (9) , 095011
Intravascular optical coherence tomography to validate finite-element simulation of angioplasty balloon inflation
Concrete methods are lacking to examine angioplasty simulation results. For the first time, we explored the application of intravascular optical coherence tomography (IVOCT) to experimentally validate results obtained from finite-element simulation of angioplasty balloon deployment. In order to simulate each experimental scenario, IVOCT images were used to create initial geometrical models for the balloon and the phantoms. The study comprised three scenarios. The first scenario involved experimentally monitoring as well as simulating free expansion of the balloon. The second scenario involved experimentally monitoring as well as simulating balloon inflation inside three artery phantoms with different mechanical properties. The third scenario involved experimentally monitoring as well as simulating balloon unfolding and inflation inside a multilayer phantom. Using the first scenario, a constitutive model was developed for the balloon and was tuned to fit the IVOCT balloon inflation monitoring results. This model was used to simulate the balloon’s response in simulations involving phantoms corresponding to the second and third scenarios. Diameter values were calculated both from images and simulation results. These values were then compared for each scenario. The obtained results highlight the potentials of IVOCT monitoring to validate simulation procedures.
- 26 April 2019
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 64 (9) , 095011
Intravascular optical coherence tomography to validate finite-element simulation of angioplasty balloon inflation
Concrete methods are lacking to examine angioplasty simulation results. For the first time, we explored the application of intravascular optical coherence tomography (IVOCT) to experimentally validate results obtained from finite-element simulation of angioplasty balloon deployment. In order to simulate each experimental scenario, IVOCT images were used to create initial geometrical models for the balloon and the phantoms. The study comprised three scenarios. The first scenario involved experimentally monitoring as well as simulating free expansion of the balloon. The second scenario involved experimentally monitoring as well as simulating balloon inflation inside three artery phantoms with different mechanical properties. The third scenario involved experimentally monitoring as well as simulating balloon unfolding and inflation inside a multilayer phantom. Using the first scenario, a constitutive model was developed for the balloon and was tuned to fit the IVOCT balloon inflation monitoring results. This model was used to simulate the balloon’s response in simulations involving phantoms corresponding to the second and third scenarios. Diameter values were calculated both from images and simulation results. These values were then compared for each scenario. The obtained results highlight the potentials of IVOCT monitoring to validate simulation procedures.
- 1 July 2017
- Published by Journal of Neurosurgery Publishing Group (JNSPG) in Journal of Neurosurgery
- Vol. 127 (1) , 171-181
The force pyramid: a spatial analysis of force application during virtual reality brain tumor resection
OBJECTIVE: Virtual reality simulators allow development of novel methods to analyze neurosurgical performance. The concept of a force pyramid is introduced as a Tier 3 metric with the ability to provide visual and spatial analysis of 3D force application by any instrument used during simulated tumor resection. This study was designed to answer 3 questions: 1) Do study groups have distinct force pyramids? 2) Do handedness and ergonomics influence force pyramid structure? 3) Are force pyramids dependent on the visual and haptic characteristics of simulated tumors?METHODS: Using a virtual reality simulator, NeuroVR (formerly NeuroTouch), ultrasonic aspirator force application was continually assessed during resection of simulated brain tumors by neurosurgeons, residents, and medical students. The participants performed simulated resections of 18 simulated brain tumors with different visual and haptic characteristics. The raw data, namely, coordinates of the instrument tip as well as contact force values, were collected by the simulator. To provide a visual and qualitative spatial analysis of forces, the authors created a graph, called a force pyramid, representing force sum along the z-coordinate for different xy coordinates of the tool tip.RESULTS: Sixteen neurosurgeons, 15 residents, and 84 medical students participated in the study. Neurosurgeon, resident and medical student groups displayed easily distinguishable 3D “force pyramid fingerprints.” Neurosurgeons had the lowest force pyramids, indicating application of the lowest forces, followed by resident and medical student groups. Handedness, ergonomics, and visual and haptic tumor characteristics resulted in distinct well-defined 3D force pyramid patterns.CONCLUSIONS: Force pyramid fingerprints provide 3D spatial assessment displays of instrument force application during simulated tumor resection. Neurosurgeon force utilization and ergonomic data form a basis for understanding and modulating resident force application and improving patient safety during tumor resection.
- 1 July 2017
- Published by Journal of Neurosurgery Publishing Group (JNSPG) in Journal of Neurosurgery
- Vol. 127 (1) , 171-181
The force pyramid: a spatial analysis of force application during virtual reality brain tumor resection
OBJECTIVE: Virtual reality simulators allow development of novel methods to analyze neurosurgical performance. The concept of a force pyramid is introduced as a Tier 3 metric with the ability to provide visual and spatial analysis of 3D force application by any instrument used during simulated tumor resection. This study was designed to answer 3 questions: 1) Do study groups have distinct force pyramids? 2) Do handedness and ergonomics influence force pyramid structure? 3) Are force pyramids dependent on the visual and haptic characteristics of simulated tumors?METHODS: Using a virtual reality simulator, NeuroVR (formerly NeuroTouch), ultrasonic aspirator force application was continually assessed during resection of simulated brain tumors by neurosurgeons, residents, and medical students. The participants performed simulated resections of 18 simulated brain tumors with different visual and haptic characteristics. The raw data, namely, coordinates of the instrument tip as well as contact force values, were collected by the simulator. To provide a visual and qualitative spatial analysis of forces, the authors created a graph, called a force pyramid, representing force sum along the z-coordinate for different xy coordinates of the tool tip.RESULTS: Sixteen neurosurgeons, 15 residents, and 84 medical students participated in the study. Neurosurgeon, resident and medical student groups displayed easily distinguishable 3D “force pyramid fingerprints.” Neurosurgeons had the lowest force pyramids, indicating application of the lowest forces, followed by resident and medical student groups. Handedness, ergonomics, and visual and haptic tumor characteristics resulted in distinct well-defined 3D force pyramid patterns.CONCLUSIONS: Force pyramid fingerprints provide 3D spatial assessment displays of instrument force application during simulated tumor resection. Neurosurgeon force utilization and ergonomic data form a basis for understanding and modulating resident force application and improving patient safety during tumor resection.