Dr. Eranga Ukwatta Profile

Dr. Eranga Ukwatta

Assistant Professor at Univ of Guelph

SPIE Involvement:

Author

Area of Expertise:

Medical image segmentation

Publications (32)

Proceedings Article | 3 April 2024 Poster + Paper

Radiomics feature based benign vs. malignant characterization of solid renal masses on MRI

Rohini Gaikar, Azar Azad, Nicola Schieda, Eranga Ukwatta

Proceedings Volume 12927, 1292730 (2024) https://doi.org/10.1117/12.3006838

KEYWORDS: Magnetic resonance imaging, Radiomics, Tumor growth modeling, Solids, Feature extraction, Machine learning, Education and training, Artificial neural networks, Image classification, Cross validation

Read Abstract +

SPIE Journal Paper | 1 March 2024

Machine learning based prediction of image quality in prostate MRI using rapid localizer images

Abdullah Al-Hayali, Amin Komeili, Azar Azad, Paul Sathiadoss, Nicola Schieda, Eranga Ukwatta

JMI, Vol. 11, Issue 02, 026001, (March 2024) https://doi.org/10.1117/12.10.1117/1.JMI.11.2.026001

KEYWORDS: Image quality, Magnetic resonance imaging, Image segmentation, Diffusion weighted imaging, Prostate, Analog to digital converters, Rectum, Radiomics, Machine learning, Education and training

Read Abstract +

SPIE Journal Paper | 14 November 2023

Automated aortic segmentation and quantification of hemodynamic parameters from 4D flow MRI using deep learning techniques

Jenita Manokaran, Julio Garcia Flores, Eranga Ukwatta

JMI, Vol. 10, Issue 06, 066001, (November 2023) https://doi.org/10.1117/12.10.1117/1.JMI.10.6.066001

KEYWORDS: Image segmentation, Aorta, Magnetic resonance imaging, 3D modeling, Hemodynamics, Electroluminescence, Blood circulation, Deep learning, Education and training, Data modeling

Read Abstract +

PurposeTo develop an automated method for aortic segmentation using deep learning techniques and further analyze the hemodynamic parameters in patients with bicuspid aortic valve (BAV). Since four-dimensional (4D) flow magnetic resonance imaging (MRI) imaging helps in analyzing and quantifying the blood flow changes that occur in aortic valve-related problems, such as BAV, 4D flow MRI images are considered.ApproachOur dataset consisted of 91 patients who had referral indications of BAV and 30 healthy volunteers who had no known cardiovascular disease. A U-Net++ with pretrained ResNet-34 encoders was trained for aortic segmentation using manual segmentation by an expert as the ground truth. In the first stage, the model was evaluated on 21 test cohorts using overlay and distance-based metrics, such as Dice score, Hausdorff distance, and absolute volume difference. In the second stage, the hemodynamic parameters, such as wall shear stress (WSS), viscous energy loss, and vorticity, were calculated to quantify the blood flow irregularities that occur in BAV patients. The segmentation and the flow parameters generated by the algorithm were compared with those generated using the manual segmentations. Paired t-test with alpha value of 0.05 was used for statistical significance testing.ResultsAs for overlap and distance-based metrics, the developed algorithm reported a Dice score coefficient of 0.90 ± 0.03, absolute volume difference of 1683 ± 1139 mm3, and Hausdorff distance of 3.2 ± 1.18 mm on test cohorts. The hemodynamic parameters calculated between automated and manual methods resulted in a mean difference of 6.62% for WSS with p-value of 0.94, 17.35% for mean viscous energy loss with p-value of 0.78, and 7.59% for vorticity with p-value of 0.97.ConclusionsA fast and accurate segmentation tool was developed for aortic segmentation using a dataset taken at clinical and blood flow parameters that were calculated based on the segmented aorta. These results will assist the clinicians to analyze the blood flow patterns and commence distinguished treatment in BAV patients.

SPIE Journal Paper | 25 July 2023

Automatic classification of symmetry of hemithoraces in canine and feline radiographs

Peyman Tahghighi, Nicole Norena, Eran Ukwatta, Ryan B. Appleby, Amin Komeili

JMI, Vol. 10, Issue 04, 044004, (July 2023) https://doi.org/10.1117/12.10.1117/1.JMI.10.4.044004

KEYWORDS: Radiography, Image segmentation, Spine, Education and training, Lung, Feature extraction, Contour modeling, Performance modeling, Machine learning, Histograms

Read Abstract +

SPIE Journal Paper | 5 June 2023

Automated fatty liver disease detection in point-of-care ultrasound B-mode images

Miriam Naim Ibrahim, Raul Blázquez-García, Adi Lightstone, Fankun Meng, Mamatha Bhat, Ahmed El Kaffas, Eranga Ukwatta

JMI, Vol. 10, Issue 03, 034505, (June 2023) https://doi.org/10.1117/12.10.1117/1.JMI.10.3.034505

KEYWORDS: Liver, Education and training, Image segmentation, Diseases and disorders, Ultrasonography, Point-of-care devices, Cross validation, Diagnostics, Tissues, Data modeling

Read Abstract +

Proceedings Article | 10 April 2023 Presentation + Paper

Fully automated aortic segmentation of 3D phase-contrast magnetic resonance angiography images using deep learning techniques

Jenita Manokaran, Julio Garcia Flores, Eranga Ukwatta

Proceedings Volume 12468, 1246809 (2023) https://doi.org/10.1117/12.2653344

KEYWORDS: Image segmentation, Aorta, Magnetic resonance imaging, Deep learning, Angiography

Read Abstract +

Proceedings Article | 10 April 2023 Presentation + Paper

Automated segmentation and measurement of the levator hiatus in 3D transperineal ultrasound

Zachary Szentimrey, Golafsoun Ameri, Rachel Y. Cheung, Ahmed Eltahawi, Eranga Ukwatta

Proceedings Volume 12468, 124680Y (2023) https://doi.org/10.1117/12.2653149

KEYWORDS: Image segmentation, 3D image processing, 3D modeling, Ultrasonography, Performance modeling, Education and training, Data modeling, Diseases and disorders, Deep learning, 3D metrology

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

Fully automated cascaded approach for renal mass detection on T2 weighted MRI images

Rohini Gaikar, Azar Azad, Nicola Schieda, Eranga Ukwatta

Proceedings Volume 12465, 124651M (2023) https://doi.org/10.1117/12.2653286

KEYWORDS: Kidney, Magnetic resonance imaging, Image segmentation, Cancer detection, Performance modeling, Tumor growth modeling, Data modeling, Deep learning

Read Abstract +

SPIE Journal Paper | 20 March 2023

Deep-learning-based ensemble method for fully automated detection of renal masses on magnetic resonance images

Anush Agarwal, Gaikar Rohini, Schieda Nicola, Elfaal Mohamed WalaaEldin, Ukwatta Eranga

JMI, Vol. 10, Issue 02, 024501, (March 2023) https://doi.org/10.1117/12.10.1117/1.JMI.10.2.024501

KEYWORDS: Kidney, Image segmentation, Magnetic resonance imaging, Cancer detection, Data modeling, Solids, Education and training, Tumor growth modeling, Tissues, 3D modeling

Read Abstract +

SPIE Journal Paper | 16 June 2022

Transfer learning-based approach for automated kidney segmentation on multiparametric MRI sequences

Rohini Gaikar, Fatemeh Zabihollahy, Mohamed Elfaal, Azar Azad, Nicola Schieda, Eranga Ukwatta

JMI, Vol. 9, Issue 03, 036001, (June 2022) https://doi.org/10.1117/12.10.1117/1.JMI.9.3.036001

KEYWORDS: Kidney, Image segmentation, Data modeling, Magnetic resonance imaging, 3D modeling, Performance modeling, Statistical modeling, 3D image processing, Tumor growth modeling, 3D acquisition

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Paper

Automated myocardial segmentation of extra-cellular volume mapping cardiac magnetic resonance images using fully convolutional neural networks

Nadia Farrag, Sathvik Bhagavan, David Sebben, Poojani Ruwanpura, James White, Eranga Ukwatta

Proceedings Volume 12036, 1203629 (2022) https://doi.org/10.1117/12.2626738

KEYWORDS: Image segmentation, Cardiovascular magnetic resonance imaging, Convolutional neural networks, Magnetic resonance imaging, Image processing algorithms and systems, Analytical research

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Presentation + Paper

Transfer learning based fully automated kidney segmentation on MR images

Rohini Gaikar, Fatemeh Zabihollahy, Nadia Farrag, Mohamed Elfaal, Nicola Schieda, Eranga Ukwatta

Proceedings Volume 12036, 120361M (2022) https://doi.org/10.1117/12.2607526

KEYWORDS: Kidney, Image segmentation, Magnetic resonance imaging, 3D modeling, Data modeling, 3D image processing, Tumor growth modeling, Algorithm development, Tissues, Cancer

Read Abstract +

SPIE Journal Paper | 23 August 2021 Open Access

Detection of COVID-19 from chest x-ray images using transfer learning

Jenita Manokaran, Fatemeh Zabihollahy, Andrew Hamilton-Wright, Eranga Ukwatta

JMI, Vol. 8, Issue S1, 017503, (August 2021) https://doi.org/10.1117/12.10.1117/1.JMI.8.S1.017503

Read Abstract +

DOWNLOAD PAPER

SPIE Journal Paper | 4 March 2021

Fully automated estimation of the mean linear intercept in histopathology images of mouse lung tissue

Marissa Lithopoulos, Sina Salsabili, Shreyas Sreeraman, Arul Vadivel, Bernard Thébaud, Adrian D. Chan, Eranga Ukwatta

JMI, Vol. 8, Issue 02, 027501, (March 2021) https://doi.org/10.1117/12.10.1117/1.JMI.8.2.027501

KEYWORDS: Image segmentation, Lung, Lawrencium, Tissues, Binary data, Biological research, Visualization, Blood vessels, Blood, Feature extraction

Read Abstract +

Purpose: The mean linear intercept (MLI) score is a common metric for quantification of injury in lung histopathology images. The automated estimation of the MLI score is a challenging task because it requires accurate segmentation of different biological components of the lung tissue. Therefore, the most widely used approaches for MLI quantification are based on manual/semi-automated assessment of lung histopathology images, which can be expensive and time-consuming. We describe a fully automated pipeline for MLI estimation, which is capable of producing results comparable to human raters. Approach: We use a convolutional neural network based on U-Net architecture to segment the diagnostically relevant tissue segments in the whole slide images (WSI) of the mouse lung tissue. The proposed method extracts multiple field-of-view (FOV) images from the tissue segments and screen the FOV images, rejecting images based on presence of certain biological structures (i.e., blood vessels and bronchi). We used color slicing and region growing for segmentation of different biological structures in each FOV image. Results: The proposed method was tested on ten WSIs from mice and compared against the scores provided by three human raters. In segmenting the relevant tissue segments, our method obtained a mean accuracy, Dice coefficient, and Hausdorff distance of 98.34%, 98.22%, and 109.68 μm, respectively. Our proposed method yields a mean precision, recall, and F1-score of 93.37%, 83.47%, and 87.87%, respectively, in screening of FOV images. There was substantial agreement found between the proposed method and the manual scores (Fleiss Kappa score of 0.76). The mean difference between the calculated MLI score between the automated method and average rater’s score was 2.33 ± 4.13 (4.25 % ± 5.67 % ). Conclusion: The proposed pipeline for automated calculation of the MLI score demonstrates high consistency and accuracy with human raters and can be a potential replacement for manual/semi-automated approaches in the field.

Proceedings Article | 15 February 2021 Presentation + Paper

Automatic deep learning-based segmentation of neonatal cerebral ventricles from 3D ultrasound images

Zachary Szentimrey, Sandrine de Ribaupierre, Aaron Fenster, Eranga Ukwatta

Proceedings Volume 11600, 116000R (2021) https://doi.org/10.1117/12.2581749

KEYWORDS: Image segmentation, 3D image processing, 3D modeling, Ultrasonography, Performance modeling

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Deep learning-based detection of COVID-19 from chest x-ray images

Jenita Manokaran, Fatemeh Zabihollahy, Andrew Hamilton-Wright, Eran Ukwatta

Proceedings Volume 11600, 116000O (2021) https://doi.org/10.1117/12.2581314

KEYWORDS: Chest imaging, Data modeling, Polymers, Image classification, Diagnostics

Read Abstract +

Proceedings Article | 18 March 2019 Presentation + Paper

Machine learning-based approach for fully automated segmentation of muscularis propria from histopathology images of intestinal specimens

Conor McKeen, Fatemeh Zabihollahy, Jinu Kurian, Adrian D. Chan, Dina El Demellawy, Eranga Ukwatta

Proceedings Volume 10956, 109560P (2019) https://doi.org/10.1117/12.2512970

KEYWORDS: Image segmentation, Colon, Convolutional neural networks, Network architectures, Machine learning

Read Abstract +

Proceedings Article | 15 March 2019 Presentation + Paper

Deep learning based approach for fully automated detection and segmentation of hard exudate from retinal images

F. Zabihollahy, A. Lochbihler, E. Ukwatta

Proceedings Volume 10953, 1095308 (2019) https://doi.org/10.1117/12.2513034

KEYWORDS: Image segmentation, Convolutional neural networks, Image processing algorithms and systems, Macula, Detection and tracking algorithms, Optical discs, Machine learning

Read Abstract +

Proceedings Article | 15 March 2019 Presentation + Paper

Semi-automated myocardial segmentation in native T1-mapping CMR using deformable non-rigid registration of CINE images

Nadia Farrag, James White, Eranga Ukwatta

Proceedings Volume 10953, 109531C (2019) https://doi.org/10.1117/12.2513054

KEYWORDS: Image segmentation, Image registration, Cardiovascular magnetic resonance imaging, Image processing algorithms and systems, Expectation maximization algorithms, Tissues, Magnetism, Blood, Image processing, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 13 March 2019 Paper

Fully automated segmentation of left ventricular myocardium from 3D late gadolinium enhancement magnetic resonance images using a U-net convolutional neural network-based model

Fatemeh Zabihollahy, James White, Eranga Ukwatta

Proceedings Volume 10950, 109503C (2019) https://doi.org/10.1117/12.2512146

KEYWORDS: Image segmentation, 3D image processing, 3D modeling, Magnetic resonance imaging, Resonance enhancement, Tissues, Gadolinium, Machine learning

Read Abstract +

Proceedings Article | 13 March 2019 Paper

Fully-automated segmentation of optic disk from retinal images using deep learning techniques

F. Zabihollahy, E. Ukwatta

Proceedings Volume 10950, 1095032 (2019) https://doi.org/10.1117/12.2512239

KEYWORDS: Image segmentation, Image processing algorithms and systems, Optical discs, Eye, Convolutional neural networks, Algorithm development, Machine learning

Read Abstract +

Proceedings Article | 13 March 2019 Presentation + Paper

An ensemble of U-Net architecture variants for left atrial segmentation

C. Wang, M. Rajchl, A. D. Chan, E. Ukwatta

Proceedings Volume 10950, 109500M (2019) https://doi.org/10.1117/12.2512905

KEYWORDS: Image segmentation, Magnetic resonance imaging, Atrial fibrillation, Composites, 3D image processing, Machine learning

Read Abstract +

Proceedings Article | 12 March 2018 Presentation + Paper

3D scar segmentation from LGE-MRI using a continuous max-flow method

Fatma Usta, Wail Gueaieb, James White, Eranga Ukwatta

Proceedings Volume 10578, 105780U (2018) https://doi.org/10.1117/12.2294406

KEYWORDS: Image segmentation, 3D image processing, Heart, 3D modeling, Magnetic resonance imaging

Read Abstract +

Proceedings Article | 12 March 2018 Presentation + Paper

Comparison of myocardial scar geometries from 2D and 3D LGE-MRI

Fatma Usta, Wail Gueaieb, James White, Conor McKeen, Eranga Ukwatta

Proceedings Volume 10578, 105780K (2018) https://doi.org/10.1117/12.2293961

KEYWORDS: 3D image processing, 3D modeling, Image segmentation, 3D acquisition, Magnetic resonance imaging, Fractal analysis, 3D image reconstruction, Statistical analysis, Shape analysis

Read Abstract +

Proceedings Article | 27 February 2018 Paper

Myocardial scar segmentation from magnetic resonance images using convolutional neural network

Fatemeh Zabihollahy, James White, Eranga Ukwatta

Proceedings Volume 10575, 105752Z (2018) https://doi.org/10.1117/12.2293518

KEYWORDS: 3D image processing, Convolutional neural networks, Image processing algorithms and systems, Algorithm development, Magnetic resonance imaging, Image segmentation

Read Abstract +

Proceedings Article | 20 March 2015 Paper

Image-based reconstruction of 3D myocardial infarct geometry for patient specific applications

Eranga Ukwatta, Martin Rajchl, James White, Farhad Pashakhanloo, Daniel Herzka, Elliot McVeigh, Albert Lardo, Natalia Trayanova, Fijoy Vadakkumpadan

Proceedings Volume 9413, 94132W (2015) https://doi.org/10.1117/12.2082113

KEYWORDS: Image segmentation, 3D image reconstruction, 3D image processing, Heart, Image resolution, Binary data, 3D modeling, Resonance enhancement, 3D acquisition, Magnetism

Read Abstract +

Proceedings Article | 12 March 2014 Paper

Distribution of guidance models for cardiac resynchronization therapy in the setting of multi-center clinical trials

Martin Rajchl, Kamyar Abhari, John Stirrat, Eranga Ukwatta, Diego Cantor, Feng Li, Terry Peters, James White

Proceedings Volume 9036, 90361V (2014) https://doi.org/10.1117/12.2042810

KEYWORDS: Lead, Image segmentation, Data modeling, Human-machine interfaces, CRTs, Clinical trials, Visual process modeling, Visualization, Cardiovascular magnetic resonance imaging, Magnetic resonance imaging

Read Abstract +

Proceedings Article | 13 March 2013 Paper

Efficient convex optimization-based curvature dependent contour evolution approach for medical image segmentation

Eranga Ukwatta, Jing Yuan, Wu Qiu, Martin Rajchl, Aaron Fenster

Proceedings Volume 8669, 866902 (2013) https://doi.org/10.1117/12.2006313

KEYWORDS: Image segmentation, Medical imaging, Image processing algorithms and systems, Ultrasonography, MATLAB, Medical research, Data modeling, Image enhancement, Resonance enhancement, Graphics processing units

Read Abstract +

Proceedings Article | 13 March 2013 Paper

Prostate segmentation in 3D TRUS using convex optimization with shape constraint

Wu Qiu, Jing Yuan, Eranga Ukwatta, David Tessier, Aaron Fenster

Proceedings Volume 8669, 866943 (2013) https://doi.org/10.1117/12.2006836

KEYWORDS: Image segmentation, Prostate, 3D image processing, Convex optimization, Biopsy, 3D modeling, Algorithm development, Ultrasonography, Distance measurement, Silicon

Read Abstract +

Proceedings Article | 6 April 2012 Paper

Semi-automated segmentation of carotid artery total plaque volume from three dimensional ultrasound carotid imaging

D. Buchanan, I. Gyacskov, E. Ukwatta, T. Lindenmaier, A. Fenster, G. Parraga

Proceedings Volume 8317, 83170I (2012) https://doi.org/10.1117/12.912880

KEYWORDS: Arteries, Image segmentation, 3D image processing, Ultrasonography, 3D metrology, 3D image reconstruction, Clinical trials, 3D acquisition, Evolutionary algorithms, Medical research

Read Abstract +

Proceedings Article | 23 February 2012 Paper

Three-dimensional semi-automated segmentation of carotid atherosclerosis from three-dimensional ultrasound images

E. Ukwatta, J. Awad, D. Buchanan, G. Parraga, A. Fenster

Proceedings Volume 8315, 83150O (2012) https://doi.org/10.1117/12.912365

KEYWORDS: Image segmentation, Laser induced breakdown spectroscopy, 3D image processing, Arteries, Image processing algorithms and systems, Ultrasonography, Algorithm development, Image filtering, 3D metrology, Clinical research

Read Abstract +

Proceedings Article | 4 March 2011 Paper

Segmentation of the lumen and media-adventitia boundaries of the common carotid artery from 3D ultrasound images

E. Ukwatta, J. Awad, A. Ward, J. Samarabandu, A. Krasinski, G. Parraga, A. Fenster

Proceedings Volume 7963, 79630G (2011) https://doi.org/10.1117/12.877722

KEYWORDS: Image segmentation, 3D image processing, Arteries, 3D metrology, Ultrasonography, Image processing algorithms and systems, Image filtering, Medical research, Speckle, Simulation of CCA and DLA aggregates

Read Abstract +

Showing 5 of 32 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years