Clarence ZunHyan Rieu

Medical AI Deep Learning Researcher at NEUROPHET Research Institute, specializing in Brain MRI analysis, with a Bachelor of Science in Electrical Engineering. Currently leads Algorithm Research Team 1 in the development and publication of an AI-based medical segmentation tool, securing FDA 510(k) clearance within three months. Possesses a strong foundation in industrial automation, machine vision, and applied AI, with a dedicated focus on advancing neuroimaging for brain disease diagnosis and biomarker discovery. Committed to translating cutting-edge AI technologies into clinical practice to enhance diagnostic precision and improve patient outcomes.

Neurophet / Research Institute / Senior AI Researcher (June 2020 – Current)

Amyloid-related Imaging Abnormalities (ARIA) segmentation in T2-FLAIR MRI using Deep Learning-Based Neural Networks (2023-2024)

Leading the research and development of Neurophet's ARIA software, including ARIA-E, ARIA-H, and Superficial Siderosis. Responsible for managing technical validation procedures for FDA and CE-MDR compliance.

Multiple Sclerosis (MS) segmentation in T2-FLAIR MRI using deep learning-based neural networks (2022-2024)

Leading the research and development work of Neurophet’s MS software, performing technical validation procedures with an in-house developed neural network for FDA Premarket Notification 510(k) compliance.

Automation of the Fazekas scale in Radiology, utilizing a combination of deep learning and rule-based algorithms (2020-2022).

Developed and validated an automated Fazekas scale in radiology, leveraging in-house WMH segmentation and rule-based algorithms. The automation achieved comparable results to human raters, and the findings were published in an SCI journal.

White Matter Hyperintensity segmentation in T2-FLAIR MRI using deep learning-based neural networks (2020-2022)

Developed an in-house WMH segmentation with various novelties and validated it using multiple open-source tools. Subsequently, the findings were published in an SCI journal.

Brain tissue segmentation in adult T1-weighted MRI using deep learning-based neural networks (2020-2024)

Leading the research and development work of Neurophet's T1w MRI tissue segmentation, along with its segmentation engine.

Brain tissue segmentation in pediatric T2w MRI using deep learning based neural networks (2019-2020)

Led research initiatives on multi-brain region segmentation in pediatric and fetal brain MRI images, investigating developmental disorders.

Automated artifact detection in Brain MRI using deep learning based neural networks (2019-2020)

Designed the pipeline for automating artifact detection in brain MRI images, employing classification techniques to address issues arising from various factors in medical settings.

HyVision System / Research Lab / Associate Research Engineer (May 2017 - May 2020)

Development of in-house deep learning training Platform (2018-2019)

Conducted research and development of an in-house deep learning platform, simultaneously validating its performance through an AOI project.

Lumentum Time-of-Flight 3D Depth Sensor Calibration Machine Automation Project (2019)

Developed calibration equipment for VCSEL-related customer reference, alongside researching internal optics and correlation for tester equipment.

Research on Optical Character Recognition on Airport Baggage Demo (2019)

Researched and developed deep learning-based baggage tag OCR for Chinese airports, enhancing accuracy through machine vision preprocessing techniques.

Research on Object Classification on Battery Manufacturing Facilities Research (2018)

Explored deep learning object detection for challenging battery exterior features and developed a custom high-speed network for real-time application.

Object Detection on Low-Contrast Blemish of Mobile Screen Research (2018)

Investigated deep learning object detection for low-contrast blemishes on mobile screens, integrating Python-based PGM with MFC for complete control.

Development of Apple iPhone VCSEL Calibration & Manufacturing Machine Automation Project (2018-2019)

Developed VCSEL calibration tester equipment for iPhone, researching and developing sequences and machine vision algorithms for tester equipment.

Development of Apple iPad Calibration Machine Manufacturing Automation Project (2017-2018)

Developed various panel calibration equipment for iPads, conducting optics selection, and training local personnel on-site.

• Nomination of Top 5 algorithm for MICCAI 2021 Feta Segmentation Challenge, Was responsible for developing the fetal tissue segmentation algorithm for the Fetal Segmentation Challenge 2021. During this process, the algorithm was nominated as one of the top 5 algorithms in the challenge.
• A Finalist of Cornell Cup USA 2013, Led the Seattle Pacific University engineering team to become a finalist in a national-level engineering competition. Competed with 30 teams from 18 institutions throughout the country.
• A Finalist of UW Business Plan Competition 2013, Led the Seattle Pacific University engineering team to become a finalist in a national-level engineering competition. Competed with 30 teams from 18 institutions throughout the country.
• A Winner of Erickson Conference 2013, Presented the finished product of NIA Wheel. Competed with 36 teams of science and engineering students from SPU and received first place in the design's category.
• A Grand Prize Winner of Social Venture Business Plan 2013, Presented NIA Wheel and its marketing strategy at the competition; won a $2,500 grand prize and a $500 people’s choice award.

DEVICE AND METHOD FOR DETERMINING QUALITY OF IMAGE, 1020200187934, 10/12/21

• MDPI – Brain Sciences, Rieu, Z., Kim, J., Kim, R. E., Lee, M., Lee, M. K., Oh, S. W., ... & Kim, D. (2021). Semi-supervised learning in medical MRI segmentation: brain tissue with white matter hyperintensity segmentation using FLAIR MRI. Brain Sciences, 11(6), 720.
• IMR Press – Journal of Integrative Neuroscience, Rieu, Z., Kim, R. E., Lee, M., Kim, H. W., Kim, D., Yong, J., ... & Kim, J. (2023). A fully automated visual grading system for white matter hyperintensities of T2-fluid attenuated inversion recovery magnetic resonance imaging. Journal of Integrative Neuroscience, 22(3), 57.
• IMR Press – Journal of Integrative Neuroscience, Lee, S., Rieu, Z., Kim, R. E., Lee, M., Yen, K., Yong, J., & Kim, D. (2023). Automatic segmentation of white matter hyperintensities in T2-FLAIR with AQUA: A comparative validation study against conventional methods. Brain Research Bulletin, 205, 110825.

TensorFlow, PyTorch, scikit-learn, Computer vision, medical image segmentation, object detection, Python, C, C++, Java, MATLAB, Windows, Linux, GitHub, Docker, CUDA, Automated calibration and manufacturing systems for VCSEL and ToF sensors, Medical MRI segmentation and analysis