Dr. Eran Ukwatta is an Associate Professor in Biomedical Engineering at the University of Guelph. He joined the University of Guelph as an Assistant Professor in 2018 and was promoted to Associate Professor in 2022. His research focuses on developing robust image analysis methodologies for patient-specific modeling of cardiovascular structure and function, addressing the growing need for precise and individualized computational tools in healthcare. His research interests include machine learning for medical imaging, deep learning, medical image analysis, image segmentation and registration, myocardial tissue characterization, analysis of digital histopathology images, and computational modeling of the heart. Prior to his appointment at Guelph, Dr. Ukwatta served as an Assistant Professor at Carleton University from 2016 to 2018 and continues as an Adjunct Professor there. He also completed a multi-center postdoctoral fellowship in Biomedical Engineering at Johns Hopkins University (2013–2015) and Sunnybrook Research Institute (2014–2015). He was a recipient of the NSERC Postdoctoral Fellowship, JHU BME Centennial Postdoctoral Fellowship, and MITACS Elevate Postdoctoral Fellowship. In addition to his research, he is actively involved in teaching and mentoring students, with expertise in machine learning and biomedical imaging.

Zachary obtained his undergraduate degree at the University of Guelph in Biomedical Engineering. He completed his MASc at the University of Guelph in 2021 and continued into his PhD. He was always interested in image analysis and signal processing throughout his undergraduate degree and pursued that interest in his graduate work. Zachary’s research currently revolves around identifying organs and regions of interest from ultrasound images. In his MASc, he investigated neonatal intracranial hemorrhage. His project involved developing deep learning models to identify the cerebral ventricles of neonates and evaluate whether hemorrhaging is present. He continued this work into his PhD by developing leaner and more accurate models using semi-supervised learning. He then partnered with Cosm Medical to help build models that identify female pelvic floor anatomical structures and make measurements to help evaluate pelvic floor prolapse. Zachary’s final PhD project included work with Oncoustics (Toronto) to identify fatty liver disease in point-of-care ultrasound images. The team not only segmented liver tissue but also used those segmentations to determine image quality.

Mohammadreza is an incoming PhD student in Biomedical Engineering at the University of Guelph (starting Fall 2025). He holds an MASc in Systems and Computing from the University of Guelph and an MSc in Electrical Engineering (Control Engineering) from Khajeh Nasir Toosi University of Technology in Iran, along with a BSc in Electrical Engineering (Electronics). With an interdisciplinary foundation spanning control systems, computing, electronics, and medical AI—and a strong, advanced background in mathematics, statistics, and machine learning/deep learning—his work bridges classical systems theory with state-of-the-art computational approaches in medical imaging. During his master’s studies, Mohammadreza conducted research in medical image segmentation with a focus on deep learning, privacy-preserving AI, and clinical robustness. His work included developing a 3D TransUNet-based model for multi-modal brain tumor segmentation—featuring advanced preprocessing, registration-based augmentation, hybrid loss functions, and multi-GPU optimization—which achieved strong performance on the BraTS benchmark. He also built end-to-end centralized, federated, adversarial, and differentially private learning pipelines for MRI brain segmentation using PyTorch, Flower, MONAI, and Opacus. At the University of Guelph, Mohammadreza serves as the College of Engineering Steward for CUPE 3913, representing graduate teaching personnel and supporting members through communications, orientation leadership, and event organization. He also serves as the International Affairs Officer for the Graduate Engineering Student Society (GESS), following his previous role as Vice President (External) for the same organization. Additionally, he works as an AI Developer for the College of Computational, Mathematical, and Physical Sciences, where he developed a Retrieval-Augmented Generation (RAG) chatbot that delivers instant, accurate academic support and transforms complex AI technologies into practical educational tools.

Puja is a MASc student in Computer Engineering at the University of Guelph, specializing in privacy-preserving AI, federated learning, and 3D medical image segmentation. She is also a Data Scientist at mlHealth360, where she focuses on developing AI technologies to optimize and enhance radiology workflows. During her master’s research, Puja developed an Adaptive Differentially Private Federated Learning (ADP-FL) approach to minimize privacy–utility trade-offs in DP-FL for medical image segmentation. ADP-FL demonstrated substantial improvements across benchmark datasets, including KiTS23, BraTS24, HAM10K, and FeTS24, achieving significant Dice score gains, enhanced convergence stability, and improved learning efficiency compared with conventional DP-FL at the same privacy budget. Evaluation on real institutional datasets such as FeTS24 highlights its potential for collaborative AI development across hospitals while maintaining robustness and supporting sustainable model refinement. At mlHealth360, Puja contributes to the development of the AI-enabled Radiology Assistant by designing deep learning pipelines for X-ray, CT, and MRI data, supporting disease detection and automated report generation to improve efficiency in hospitals. Her research interests include optimization, multimodal AI, decentralized learning, AI security, and generative AI for healthcare.

Zinah is a MASc Student in Computer Engineering at the University of Guelph, specializing in AI-driven medical imaging. She is also pursuing the Collaborative Specialization in Artificial Intelligence (CSAI) through the Vector Institute. Her work lies at the intersection of artificial intelligence, radiology, and clinical decision support, with a focus on developing multimodal deep learning systems that can interpret both medical images and text-based reports. She is passionate about designing AI models that align with clinical reasoning and improve diagnostic efficiency. Zinah is particularly interested in interpretable machine learning, multimodal fusion, and medical imaging applications that enhance disease understanding and reporting. Beyond her research, Zinah serves as the President of the Graduate Engineering Student Society (GESS) for the year 2025, where she leads initiatives to strengthen community engagement and professional development among graduate students in the College of Engineering. She also serves as Co-Chair of the Student Committee for the Imaging Network Ontario (ImNO) 2026 conference, helping foster collaboration and knowledge exchange among emerging researchers in medical imaging and healthcare innovation. Outside of academics, she enjoys staying active through walks and runs, baking, volunteering, learning new languages, photography, and exploring local cafés — pursuits that help her maintain a thoughtful balance between leadership, research, and creativity.

Aishwarya is a MASc student in Biomedical Engineering starting in Fall 2025. She recently completed her undergraduate degree in Biomedical Engineering at the University of Guelph. Her research interests focus on applying AI to develop and improve resources in medical diagnoses. Her current work involves collaborating with the Ontario Veterinary College (OVC) to develop a generative AI tool that assists veterinary radiologists in generating complete radiology reports. In the future, she hopes to apply AI and medical imaging technologies to real-world clinical and industry settings.

Pramit is a MASc student in Computer Engineering with a Specialization in Artificial Intelligence at the University of Guelph. He earned his B.Sc. in Electronics and Telecommunication Engineering from the Chittagong University of Engineering and Technology. His research interests center on multimodal and generative AI, with experience spanning hybrid feature extraction and self-supervised learning frameworks in medical imaging. Much of his work bridges the gap between algorithmic design and real-world clinical data, with the aim of developing systems that can assist in decision-making while minimizing reliance on labeled data. His research focuses on developing vision–language models (VLMs) for medical imaging. He explores how large pretrained models can be adapted to clinical data to improve interpretability and domain robustness, particularly through improved domain adaptation techniques that bridge the gap between general and medical datasets. He works on integrating visual features from CT scans with language-based clinical information to enhance diagnostic insight and support clinical decision-making.