Research Online at MacEwan :: Browsing by Author "Cobzas, Dana"

Browsing by Author "Cobzas, Dana"

Now showing 1 - 20 of 26

496 Capstone: AR.t
(2020) Driedger, Andre; Ansorger, Anneliese; Galay, Chance; Lafitte, Chanelle; Cobzas, Dana
Original artwork is often very expensive; being able to see how a painting will look on a wall before you buy is advantageous. As a collaborative project between the MacEwan Computer Science and Design departments, we set out to do develop an AR app that can be used by by consumers to shop for art on the walls of their homes and offices. Existing mobile AR applications cannot identify vertical surfaces, such as walls. Our solution is to implement a target image that can be posted onto vertical surfaces to be detected by our app. We developed an OpenCV prototype to test this method of using object-detection to set a starting point for subsequent tracking. The prototype was successful in rendering 3d objects, true to scale, onto walls. Next, we developed an Android version utilizing Google's ARCore toolkit. This also delivered good results. Ultimately, we were successful in showcasing art on walls using smartphones in real-time.
An analysis of electroencephalogram (EEG) with machine learning
(2024) Emery, Jesse; Phan, Nhi; Jime, Isra; Cobzas, Dana; Hassall, Cameron D.
Our capstone project was done in collaboration with Dr. Cameron Hassall from the Psychology department at MacEwan University. Our data was based on one of Dr. Hassall’s papers on “Task-level value affects trial-level reward processing” (Hassal, C, 2022), where he wanted to determine if the Anterior Cingulate Cortex was responsible or involved in decision making. To determine this, a task sequence was carried out 427 times using 12 participants over a 52 minute period. While the participants completed these tasks, brain activity was being measured using an electroencephalogram (EEG). For our project, the goal was to train a machine learning model to accurately classify an EEG event after training on past events. In greater detail, we focus on the brain signal when the participant hit the left or right button in response to the stimulus which are colored shapes.
An analysis of electroencephalogram (EEG) with machine learning
(2024) Jime, Isra; Emery, Jesse; Phan, Nhi; Cobzas, Dana
Our capstone project was done in collaboration with Dr. Cameron Hassall from the Psychology department at MacEwan University. Our data was based on one of Dr. Hassall’s papers on “Task-level value affects trial-level reward processing” (Hassal, C, 2022), where he wanted to determine if the Anterior Cingulate Cortex was responsible or involved in decision making. To determine this, a task sequence was carried out 427 times using 12 participants over a 52 minute period. While the participants completed these tasks, brain activity was being measured using an electroencephalogram (EEG). For our project, the goal was to train a machine learning model to accurately classify an EEG event after training on past events. In greater detail, we focus on the brain signal when the participant hit the left or right button in response to the stimulus which are colored shapes.
Android app demo
(2020) Driedger, Andre; Ansorger, Anneliese; Galay, Chance; Lafitte, Chanelle; Cobzas, Dana
For the app, we developed an Android version utilizing Google's ARCore toolkit. The Design students prototyped screens for user profiles, buying art, as well as filtering and browsing functionality. This functionality has not yet been implemented, and we instead chose to focus on the AR screens. The user can browse through and preview different paintings and frames.
AR.T deliver report
(2020) Lafitte, Chanelle; Galay, Chance; Cobzas, Dana
Original artwork is often very expensive; being able to see how a painting will look on a wall before you buy is advantageous. As a collaborative project between the MacEwan Computer Science and Design departments, we set out to do develop an AR app that can be used by by consumers to shop for art on the walls of their homes and offices. Existing mobile AR applications cannot identify vertical surfaces, such as walls. Our solution is to implement a target image that can be posted onto vertical surfaces to be detected by our app. We developed an OpenCV prototype to test this method of using object-detection to set a starting point for subsequent tracking. The prototype was successful in rendering 3d objects, true to scale, onto walls. Next, we developed an Android version utilizing Google's ARCore toolkit. This also delivered good results. Ultimately, we were successful in showcasing art on walls using smartphones in real-time.
Automatic deep learning segmentation of the hippocampus on high resolution diffusion MRI and its application to the healthy lifespan
(2024) Efird, Cory; Neumann, Samuel; Solar, Kevin; Beaulieu, Christian; Cobzas, Dana; Miller, Dylan
Diffusion tensor imaging (DTI) can provide unique contrast and insight into microstructural changes with age or disease of the hippocampus, although it is difficult to measure the hippocampus because of its comparatively small size, location, and shape. This has been markedly improved by the advent of a clinically feasible 1-mm isotropic resolution 6-min DTI protocol at 3 T of the hippocampus with limited brain coverage of 20 axial-oblique slices aligned along its long axis. However, manual segmentation is too laborious for large population studies, and it cannot be automatically segmented directly on the diffusion images using traditional T1 or T2 image-based methods because of the limited brain coverage and different contrast. An automatic method is proposed here that segments the hippocampus directly on high-resolution diffusion images based on an extension of well-known deep learning architectures like UNet and UNet++ by including additional dense residual connections. The method was trained on 100 healthy participants with previously performed manual segmentation on the 1-mm DTI, then evaluated on typical healthy participants (n = 53), yielding an excellent voxel overlap with a Dice score of ~ 0.90 with manual segmentation; notably, this was comparable with the inter-rater reliability of manually delineating the hippocampus on diffusion magnetic resonance imaging (MRI) (Dice score of 0.86). This method also generalized to a different DTI protocol with 36% fewer acquisitions. It was further validated by showing similar age trajectories of volumes, fractional anisotropy, and mean diffusivity from manual segmentations in one cohort (n = 153, age 5–74 years) with automatic segmentations from a second cohort without manual segmentations (n = 354, age 5–90 years). Automated high-resolution diffusion MRI segmentation of the hippocampus will facilitate large cohort analyses and, in future research, needs to be evaluated on patient groups.
Creative, interdisciplinary undergraduate research: an educational cell biology video game designed by students for students
(2020) Sperano, Isabelle; Shaw, Ross W.; Andruchow, Robert; Cobzas, Dana; Efird, Cory; Brookwell, Brian; Deng, William
In a three-year, practice-based, creative research project, the team designed a video game for undergraduate biology students that aimed to find the right balance between educational content and entertainment. The project involved 7 faculty members and 14 undergraduate students from biological science, design, computer science, and music. This nontraditional approach to research was attractive to students. Working on an interdisciplinary practice-based research project required strategies related to timeline, recruitment, funding, team management, and mentoring. Although this project was time-consuming and full of challenges, it created meaningful learning experiences not only for students but also for faculty members.
A deep level set method for image segmentation
(2017) Tang, Min; Valipour, Sepehr; Zhang, Zichen; Cobzas, Dana; Jagersand, Martin
This paper proposes a novel image segmentation approach that integrates fully convolutional networks (FCNs) with a level set model. Compared with a FCN, the integrated method can incorporate smoothing and prior information to achieve an accurate segmentation. Furthermore, different than using the level set model as a post-processing tool, we integrate it into the training phase to fine-tune the FCN. This allows the use of unlabeled data during training in a semi-supervised setting. Using two types of medical imaging data (liver CT and left ventricle MRI data), we show that the integrated method achieves good performance even when little training data is available, outperforming the FCN or the level set model alone.
Developmental hip dysplasia diagnosis at three-dimensional US: a multicenter study
(2018) Zonoobi, Dornoosh; Hareendranathan, Abhilash; Mostofi, Emanuel; Mabee, Myles; Pasha, Saba; Cobzas, Dana; Rao, Padma; Dulai, Sukhdeep K.; Kapur, Jeevesh; Jaremko, Jacob L.
Purpose: To validate accuracy of diagnosis of developmental dysplasia of the hip (DDH) from geometric properties of acetabular shape extracted from three-dimensional (3D) ultrasonography (US).
Discriminative analysis of regional evolution of iron and myelin/calcium in deep gray matter of multiple sclerosis and healthy subjects
(2018) Elkady, Ahmed M.; Cobzas, Dana; Sun, Hongfu; Blevins, Gregg; Wilman, Alan H.
Combined R2* and quantitative susceptibility (QS) has been previously used in cross‐sectional multiple sclerosis (MS) studies to distinguish deep gray matter (DGM) iron accumulation and demyelination. We propose and apply discriminative analysis of regional evolution (DARE) to define specific changes in MS and healthy DGM. Longitudinal (baseline and 2‐year follow‐up) retrospective study. Twenty‐seven relapsing‐remitting MS (RRMS), 17 progressive MS (PMS), and corresponding age‐matched healthy subjects . Field Strength/Sequence: 4.7T 10‐echo gradient‐echo acquisition. Automatically segmented caudate nucleus (CN), thalamus (TH), putamen (PU), globus pallidus, red nucleus (RN), substantia nigra, and dentate nucleus were retrospectively analyzed to quantify regional volumes, bulk mean R2*, and bulk mean QS. DARE utilized combined R2* and QS localized changes to compute spatial extent, mean intensity, and total changes of DGM iron and myelin/calcium over 2 years. We used mixed factorial analysis for bulk analysis, nonparametric tests for DARE (α = 0.05), and multiple regression analysis using backward elimination of DGM structures (α = 0.05, P = 0.1) to regress bulk and DARE measures with the follow‐up Multiple Sclerosis Severity Score (MSSS). False detection rate correction was applied to all tests. Bulk analysis only detected significant (Q ≤ 0.05) interaction effects in RRMS CN QS (η = 0.45; Q = 0.004) and PU volume (η = 0.38; Q = 0.034). DARE demonstrated significant group differences in all RRMS structures, and in all PMS structures except the RN. The largest RRMS effect size was CN total R2* iron decrease (r = 0.74; Q = 0.00002), and TH mean QS myelin/calcium decrease for PMS (r = 0.70; Q = 0.002). DARE iron increase using total QS demonstrated the highest correlation with MSSS (r = 0.68; Q = 0.0005). DARE enabled discriminative assessment of specific DGM changes over 2 years, where iron and myelin/calcium changes were the primary drivers in RRMS and PMS compared to age‐matched controls, respectively. Specific DARE measures of MS DGM correlated with follow‐up MSSS, and may reflect complex disease pathology.
Disentangling hippocampal shape variations: A study of neurological disorders using mesh variational autoencoder with contrastive learning
(2025) Rabbi, Jakaria; Kiechle, Johannes; Beaulieu, Christian; Ray, Nilanjan; Cobzas, Dana
This paper presents a comprehensive study focused on disentangling hippocampal shape variations from diffusion tensor imaging (DTI) datasets within the context of neurological disorders. Leveraging a Mesh Variational Autoencoder (VAE) enhanced with Supervised Contrastive Learning, our approach aims to improve interpretability by disentangling two distinct latent variables corresponding to age and the presence of diseases. In our ablation study, we investigate a range of VAE architectures and contrastive loss functions, showcasing the enhanced disentanglement capabilities of our approach. This evaluation uses synthetic 3D torus mesh data and real 3D hippocampal mesh datasets derived from the DTI hippocampal dataset. Our supervised disentanglement model outperforms several state-of-the-art (SOTA) methods like attribute and guided VAEs in terms of disentanglement scores. Our model distinguishes between age groups and disease status in patients with Multiple Sclerosis (MS) using the hippocampus data. Our Mesh VAE with Supervised Contrastive Learning shows the volume changes of the hippocampus of MS populations at different ages, and the result is consistent with the current neuroimaging literature. This research provides valuable insights into the relationship between neurological disorder and hippocampal shape changes in different age groups of MS populations using a Mesh VAE with Supervised Contrastive loss.
End-to-end detection-segmentation network with ROI convolution
(2018) Zhang, Zichen; Tang, Min; Cobzas, Dana; Zonoobi, Dornoosh; Jagersand, Martin; Jaremko, Jacob L.
We propose an end-to-end neural network that improves the segmentation accuracy of fully convolutional networks by incorporating a localization unit. This network performs object localization first, which is then used as a cue to guide the training of the segmentation network. We test the proposed method on a segmentation task of small objects on a clinical dataset of ultrasound images. We show that by jointly learning for detection and segmentation, the proposed network is able to improve the segmentation accuracy compared to only learning for segmentation.
Evaluation of automated computed tomography segmentation to assess body composition and mortality associations in cancer patients
(2020) Cespedes Feliciano, Elizabeth M.; Popuri, Karteek; Cobzas, Dana; Baracos, Vickie E.; Beg, Mirza Faisal; Khan, Arafat Dad; Ma, Cydney; Chow, Vincent; Chow, Vincent; Prado, Carla M.; Xiao, Jingjie; Liu, Vincent; Chen, Wendy Y.; Meyerhardt, Jeffrey; Albers, Kathleen B.; Caan, Bette J.
Background Body composition from computed tomography (CT) scans is associated with cancer outcomes including surgical complications, chemotoxicity, and survival. Most studies manually segment CT scans, but Automatic Body composition Analyser using Computed tomography image Segmentation (ABACS) software automatically segments muscle and adipose tissues to speed analysis. Here, we externally evaluate ABACS in an independent dataset. Methods Among patients with non‐metastatic colorectal (n = 3102) and breast (n = 2888) cancer diagnosed from 2005 to 2013 at Kaiser Permanente, expert raters annotated tissue areas at the third lumbar vertebra (L3). To compare ABACS segmentation results to manual analysis, we quantified the proportion of pixel‐level image overlap using Jaccard scores and agreement between methods using intra‐class correlation coefficients for continuous tissue areas. We examined performance overall and among subgroups defined by patient and imaging characteristics. To compare the strength of the mortality associations obtained from ABACS's segmentations to manual analysis, we computed Cox proportional hazards ratios (HRs) and 95% confidence intervals (95% CI) by tertile of tissue area. Results Mean ± SD age was 63 ± 11 years for colorectal cancer patients and 56 ± 12 for breast cancer patients. There was strong agreement between manual and automatic segmentations overall and within subgroups of age, sex, body mass index, and cancer stage: average Jaccard scores and intra‐class correlation coefficients exceeded 90% for all tissues. ABACS underestimated muscle and visceral and subcutaneous adipose tissue areas by 1–2% versus manual analysis: mean differences were small at −2.35, −1.97 and −2.38 cm2, respectively. ABACS's performance was lowest for the <2% of patients who were underweight or had anatomic abnormalities. ABACS and manual analysis produced similar associations with mortality; comparing the lowest to highest tertile of skeletal muscle from ABACS versus manual analysis, the HRs were 1.23 (95% CI: 1.00–1.52) versus 1.38 (95% CI: 1.11–1.70) for colorectal cancer patients and 1.30 (95% CI: 1.01–1.66) versus 1.29 (95% CI: 1.00–1.65) for breast cancer patients. Conclusions In the first study to externally evaluate a commercially available software to assess body composition, automated segmentation of muscle and adipose tissues using ABACS was similar to manual analysis and associated with mortality after non‐metastatic cancer. Automated methods will accelerate body composition research and, eventually, facilitate integration of body composition measures into clinical care.
Explaining anatomical shape variability: supervised disentangling with a variational graph autoencoder
(2023) Kiechle, Johannes; Miller, Dylan; Slessor, Jordan; Pietrosanu, Matthew; Kong, Linglong; Beaulieu, Christian; Cobzas, Dana
This work proposes a modular geometric deep learning framework that isolates shape variability associated with a given scalar factor (e.g., age) within a population (e.g., healthy individuals). Our approach leverages a novel graph convolution operator in a variational autoencoder to process 3D mesh data and learn a meaningful, low-dimensional shape descriptor. A supervised disentanglement strategy aligns a single component of this descriptor with the factor of interest during training. On a toy synthetic dataset and a high-resolution diffusion tensor imaging (DTI) dataset, the proposed model is better able to disentangle the learned latent space with a simulated factor and patient age, respectively, relative to other state-of-the-art methods. The relationship between age and shape estimated in the DTI analysis is consistent with existing neuroimaging literature.
Five year iron changes in relapsing-remitting multiple sclerosis deep gray matter compared to healthy controls
(2019) Elkady, Ahmed M.; Cobzas, Dana; Sun, Hongfu; Seres, Peter; Blevins, Gregg; Wilman, Alan H.
Relapsing-Remitting MS (RRMS) Deep Grey Matter (DGM) 5 year changes were examined using MRI measures of volume, transverse relaxation rate (R2*) and quantitative magnetic susceptibility (QS). By applying Discriminative Analysis of Regional Evolution (DARE), R2* and QS changes from iron and non-iron sources were separated. 25 RRMS and 25 age-matched control subjects were studied at baseline and 5-year follow-up. Bulk DGM mean R2* and QS of the caudate nucleus, putamen, thalamus and globus pallidus were analyzed using mixed factorial analysis (α = 0.05) with sex as a covariate, while DARE employed non-parametric analysis to study regional changes. Regression/correlation analysis was performed with disease duration and MS Severity Score (MSSS). No significant change in Extended Disability Status Score was found over 5 years (baseline = 2.4 ± 1.2; follow-up = 2.8 ± 1.3). Significant time effects were found for R2* in the caudate (Q = 0.000008; η2 = 0.36), putamen (Q = 0.0000007; η2 = 0.43), and globus pallidus (Q = 0.0000007; η2 = 0.43), while significant longitudinal effects were only found for QS in the putamen (Q = 0.002; η2 = 0.22). Significant bulk interaction was only found for thalamus volume (Q = 0.02; η2 = 0.20). Iron decrease was the only detected significant effect using DARE, and the highest significant DARE effect size was mean thalamus R2* iron decrease (Q = 0.002; η2 = 0.26). No significant correlations or regressions were demonstrated with clinical measures. Thalamic atrophy was the only bulk effect that demonstrated different rates of changes over 5 years compared to age-matched controls. DARE Iron decrease in regions of the caudate, putamen, and thalamus were prominent features in stable RRMS over 5 years.
Hippocampus segmentation on high resolution dffusion MRI
(2021) Efird, Cory; Neumann, Samuel; Solar, Kevin G.; Beaulieu, Christian; Cobzas, Dana
We introduce the first hippocampus segmentation method for a novel high resolution (1×1×1mm3) diffusion tensor imaging (DTI) protocol acquired in 5.5 minutes at 3T. A new augmentation technique uses subsets of the DTI dataset to create mean diffusion weighted images (DWI) with plausible noise and contrast variations. The augmented DWI along with fractional anisotropy (FA) and mean diffusivity (MD) maps are used as inputs to a powerful convolutional neural network architecture. The method is evaluated for robustness using a second diffusion protocol.
Low-rank plus sparse decomposition of fMRI data with application to Alzheimer's disease
(2022) Tu, Wei; Fu, Fangfang; Kong, Linglong; Jiang, Bei; Cobzas, Dana; Huang, Chao
Studying functional brain connectivity plays an important role in understanding how human brain functions and neuropsychological diseases such as autism, attention-deficit hyperactivity disorder, and Alzheimer's disease (AD). Functional magnetic resonance imaging (fMRI) is one of the most popularly used tool to construct functional brain connectivity. However, the presence of noises and outliers in fMRI blood oxygen level dependent (BOLD) signals might lead to unreliable and unstable results in the construction of connectivity matrix. In this paper, we propose a pipeline that enables us to estimate robust and stable connectivity matrix, which increases the detectability of group differences. In particular, a low-rank plus sparse (L + S) matrix decomposition technique is adopted to decompose the original signals, where the low-rank matrix L recovers the essential common features from regions of interest, and the sparse matrix S catches the sparse individual variability and potential outliers. On the basis of decomposed signals, we construct connectivity matrix using the proposed novel concentration inequality-based sparse estimator. In order to facilitate the comparisons, we also consider correlation, partial correlation, and graphical Lasso-based methods. Hypothesis testing is then conducted to detect group differences. The proposed pipeline is applied to rs-fMRI data in Alzheimer's disease neuroimaging initiative to detect AD-related biomarkers, and we show that the proposed pipeline provides accurate yet more stable results than using the original BOLD signals.
OpenCV laptop demo
(2020) Driedger, Andre; Ansorger, Anneliese; Galay, Chance; Lafitte, Chanelle; Cobzas, Dana
When we started the project, we had decided to make a program that would use feature matching to recognize a specific image (eg. a poster or sticker), find it’s orientation, and then display some kind of useful AR artifacts in the 3D space of our recognized image. We have implemented this in OpenCV, to show that we have an in-depth understanding of how AR works.
Progressive iron accumulation across multiple sclerosis phenotypes revealed by sparse classification of deep gray matter
(2017) Elkady, Ahmed M.; Cobzas, Dana; Sun, Hongfu; Blevins, Gregg; Wilman, Alan H.
Purpose: To create an automated framework for localized analysis of deep gray matter (DGM) iron accumulation and demyelination using sparse classification by combining quantitative susceptibility (QS) and transverse relaxation rate (R2*) maps, for evaluation of DGM in multiple sclerosis (MS) phenotypes relative to healthy controls. Materials and Methods: R2*/QS maps were computed using a 4.7T 10-echo gradient echo acquisition from 16 clinically isolated syndrome (CIS), 41 relapsing-remitting (RR), 40 secondary-progressive (SP), 13 primary-progressive (PP) MS patients, and 75 controls. Sparse classification for R2*/QS maps of segmented caudate nucleus (CN), putamen (PU), thalamus (TH), and globus pallidus (GP) structures produced localized maps of iron/myelin in MS patients relative to controls. Paired t-tests, with age as a covariate, were used to test for statistical significance (P ≤ 0.05).Results: In addition to DGM structures found significantly different in patients compared to controls using whole region analysis, singular sparse analysis found significant results in RRMS PU R2* (P = 0.03), TH R2* (P = 0.04), CN QS (P = 0.04); in SPMS CN R2* (P = 0.04), GP R2* (P = 0.05); and in PPMS CN R2* (P = 0.04), TH QS (P = 0.04). All sparse regions were found to conform to an iron accumulation pattern of changes in R2*/QS, while none conformed to demyelination. Intersection of sparse R2*/QS regions also resulted in RRMS CN R2* becoming significant, while RRMS R2* TH and PPMS QS TH becoming insignificant. Common iron-associated volumes in MS patients and their effect size progressively increased with advanced phenotypes. Conclusion: A localized technique for identifying sparse regions indicative of iron or myelin in the DGM was developed. Progressive iron accumulation with advanced MS phenotypes was demonstrated, as indicated by iron-associated sparsity and effect size.
Progressive iron accumulation across multiple sclerosis phenotypes revealed by sparse classification of deep gray matter
(2017) Elkady, Ahmed M.; Cobzas, Dana; Sun, Hongfu; Blevins, Gregg; Wilman, Alan H.
To create an automated framework for localized analysis of deep gray matter (DGM) iron accumulation and demyelination using sparse classification by combining quantitative susceptibility (QS) and transverse relaxation rate (R2*) maps, for evaluation of DGM in multiple sclerosis (MS) phenotypes relative to healthy controls.R2*/QS maps were computed using a 4.7T 10‐echo gradient echo acquisition from 16 clinically isolated syndrome (CIS), 41 relapsing‐remitting (RR), 40 secondary‐progressive (SP), 13 primary‐progressive (PP) MS patients, and 75 controls. Sparse classification for R2*/QS maps of segmented caudate nucleus (CN), putamen (PU), thalamus (TH), and globus pallidus (GP) structures produced localized maps of iron/myelin in MS patients relative to controls. Paired t‐tests, with age as a covariate, were used to test for statistical significance (P ≤ 0.05).In addition to DGM structures found significantly different in patients compared to controls using whole region analysis, singular sparse analysis found significant results in RRMS PU R2* (P = 0.03), TH R2* (P = 0.04), CN QS (P = 0.04); in SPMS CN R2* (P = 0.04), GP R2* (P = 0.05); and in PPMS CN R2* (P = 0.04), TH QS (P = 0.04). All sparse regions were found to conform to an iron accumulation pattern of changes in R2*/QS, while none conformed to demyelination. Intersection of sparse R2*/QS regions also resulted in RRMS CN R2* becoming significant, while RRMS R2* TH and PPMS QS TH becoming insignificant. Common iron‐associated volumes in MS patients and their effect size progressively increased with advanced phenotypes.A localized technique for identifying sparse regions indicative of iron or myelin in the DGM was developed. Progressive iron accumulation with advanced MS phenotypes was demonstrated, as indicated by iron‐associated sparsity and effect size.

Browsing by Author "Cobzas, Dana"

Results Per Page

Sort Options