Research & Projects

A selection of research projects I have contributed to across medical imaging, robotics and automation, and applied AI. Use the category and tag filters below to explore by area of interest. Expand any card to see key outcomes, publications, and patents.

Active Aug 2024 — Present

AI-Enabled Imaging Biomarkers for Alzheimer's Disease

Commonwealth Scientific and Industrial Research Organisation (CSIRO) · Melbourne, Australia

Austin Health, The Florey Institute, Edith Cowan University, University of Pittsburgh, Eli Lilly & Company

Developing clinically deployable AI-driven PET/MR imaging biomarkers to support early detection, treatment monitoring, and evidence-based clinical decision-making in Alzheimer's disease.

PET MRI Deep Learning Neuroimaging Alzheimer's

Key Outcomes

• Designed shorter amyloid-PET acquisition protocols, cutting scan time up to 50% and uptake time by 20–40% at repeat-scan accuracy
• Led a tracer comparison study with AI-enabled quantification, achieving a lower positivity threshold of 15 CL vs 46 CL
• Deployed containerised 3D U-Net segmentation on HPC/GPU for reproducible cohort-scale processing
• Operationalised end-to-end imaging pipelines across ADNI/AIBL/OASIS-3 datasets, securing $100k+ external funding

Publications

Journal Articles

1. M.A. Yücel, R. Luke, R. C. Mesquita, A. von Lühmann, et al., "fNIRS reproducibility varies with data quality, analysis pipelines, and researcher experience," Communications Biology, 2025. IF: 5.8

Completed Jun 2016 — Dec 2019

AR-Based Smart Human-Machine Interface for MRO

Singapore University of Technology and Design (SUTD) · Singapore

A*STAR, Nanyang Technological University (NTU), Singapore

Prototyped and delivered an augmented reality-based smart human-machine interface for maintenance, repair, and overhaul (MRO) tasks of jet engines, enhancing operator guidance and workflow efficiency.

Augmented Reality Human-Machine Interface Automation Industry 4.0

Key Outcomes

• Developed an AR-based interface for maintenance, repair, and overhaul of jet engines
• Joint project with A*STAR and NTU to improve operator guidance in industrial MRO settings
• Integrated real-time visual overlays to assist technicians during complex maintenance procedures

Completed Feb 2020 — Feb 2024

Objective Neuroimaging Measures for Infant Language Development

Bionics Institute / Monash University · Melbourne, Australia

Prof. Yan Wong, Prof. Colette McKay, Dr. Darren Mao

PhD research developing objective fNIRS-based functional connectivity measures to investigate how the brain's language networks develop in early childhood, enabling early identification of language-related difficulties in infants with hearing impairment.

fNIRS Neuroimaging Signal Processing Functional Connectivity Paediatrics

Key Outcomes

• Revealed that language networks exhibit topological differences between resting and steady states in normal-hearing infants
• Demonstrated that connections between spatially distant primary language regions strengthen with age during infancy
• Developed short-channel correction methods to reduce false discoveries in resting-state functional connectivity
• Investigated the effect of data length on frequency-domain fNIRS functional connectivity measures

Publications

Journal Articles

1. I. Paranawithana, D. Mao, C. M. McKay, & Y. T. Wong, "Language networks of normal-hearing infants exhibit topological differences between resting and steady states: An fNIRS functional connectivity study," Human Brain Mapping, 2024. IF: 4.4
2. I. Paranawithana, D. Mao, C. M. McKay, and Y. T. Wong, "Connections between spatially distant primary language regions strengthen with age during infancy, as revealed by resting-state fNIRS," Journal of Neural Engineering, 2023. IF: 5.043
3. I. Paranawithana, D. Mao, Y. T. Wong, and C. M. McKay, "Reducing false discoveries in resting-state functional connectivity using short channel correction: an fNIRS study," Neurophotonics, 2022. IF: 4.212
4. K. Stute, L. K. Gossé, S. Montero-Hernandez, G. A. Perkins, et al., "The fNIRS glossary project: a consensus-based resource for functional near-infrared spectroscopy terminology," Neurophotonics, 2025. IF: 4.212

Conference Papers

1. I. Paranawithana, D. Mao, C. M. McKay, and Y. T. Wong, "Investigating the effect of data length on the performance of frequency-domain fNIRS functional connectivity measures," IEEE EMBC 2023, Sydney, Australia, 2023.

Completed Oct 2014 — Mar 2015

Automating IVF Procedures with Computer Vision

SUTD-MIT International Design Centre · Singapore

Massachusetts Institute of Technology (MIT), USA

Designed a vision-based workflow for automatic detection and tracking of blastomeres and micropipettes during Preimplantation Genetic Diagnosis (PGD) of IVF procedures, enabling continuous visual guidance during embryo biopsy.

Computer Vision Cell Tracking Biomedical Automation IVF

Key Outcomes

• Built a workflow to auto-detect/track blastomeres and micropipettes using cell segmentation and robust feature-based visual tracking
• Demonstrated reliable multi-frame tracking under variable lighting and partial occlusions
• Enabled steadier cell handling and fewer re-acquisitions during embryo biopsy

Publications

Conference Papers

1. I. Paranawithana, W.X. Yang, and U.-X. Tan, "Tracking extraction of blastomere for embryo biopsy," IEEE ROBIO 2015, Zhuhai, China, 2015.

Completed Jun 2015 — Mar 2016

SSVEP-Based Brain-Computer Interface for Emergency Healthcare

University of Moratuwa · Sri Lanka

Final-year undergraduate project developing a brain-computer interface by decoding steady-state visually evoked potentials (SSVEP) to assist individuals with locked-in syndromes to communicate basic daily needs.

BCI EEG Signal Processing Assistive Technology Neurotechnology

Key Outcomes

• Developed a BCI system decoding visually-evoked potentials for communication assistance
• Designed a system to help people with locked-in syndromes express basic daily needs to caretakers
• Conducted an in-depth study of SSVEP signals against stimulus frequency and distance

Publications

Conference Papers

1. S. Pathiranage, I. Paranawithana, M. Perera, and A.C. De Silva, "An in-depth study of SSVEP signals against stimulus frequency and distance to the stimulus," MERCon 2018, Moratuwa, Sri Lanka, 2018.

Completed Jun 2016 — Dec 2019

Ultrasound-Guided Motion Compensation for Kidney Stone Surgery

Singapore University of Technology and Design (SUTD) · Singapore

Changi General Hospital, Singapore

Developed a robot-assisted ultrasound guidance workflow for PCNL surgery that tracks kidney stones in real time during patient breathing, achieving near real-time tracking with ≈1 frame error and probe-skin force within 0.2 N.

Ultrasound Surgical Robotics Image Registration Control Systems Human-Robot Interaction

Key Outcomes

• Built a surgical assistance procedure via pre-operative anatomical modelling, intra-operative image registration, and image-guided needle insertion
• Designed a two-step ultrasound out-of-plane tracking workflow achieving visual tracking error of ≈1 frame
• Established compliant human-robot operation by variable-admittance and adaptive control for ultrasound probe handling
• Maintained safe probe-tissue contact via position-based control, keeping force deviation below 0.2 N
• Patent licensed to Creative Medtech Solutions Pte Ltd for commercialisation

Patent

Motion compensation platform for image-guided percutaneous access to bodily organs and structures (US Patent Application 16/958,587)
Licensed to Creative Medtech Solutions Pte Ltd, Singapore

Publications

Journal Articles

1. H.-Y. Li, A. G. Dharmawan, I. Paranawithana, L. Yang, and U.-X. Tan, "A control scheme for physical human-robot interaction coupled with an environment of unknown stiffness," Journal of Intelligent & Robotic Systems, 2020. IF: 3.129
2. H. Li et al., "Stable and compliant motion of physical human-robot interaction coupled with a moving environment using variable admittance and adaptive control," IEEE Robotics and Automation Letters, 2018. IF: 4.321

Conference Papers

1. H.-Y. Li, I. Paranawithana, L. Yang, and U.-X. Tan, "Variable admittance control with robust adaptive velocity control for dynamic physical interaction between robot, human and environment," IEEE CASE 2021, Lyon, France, 2021.
2. H.-Y. Li, I. Paranawithana, L. Yang, and U.-X. Tan, "Towards a robotic assisted system for percutaneous nephrolithotomy," IEEE/RSJ IROS 2018, Madrid, Spain, 2018.
3. I. Paranawithana, H.-Y. Li et al., "Ultrasound-guided involuntary motion compensation of kidney stones in percutaneous nephrolithotomy surgery," IEEE CASE 2018, Munich, Germany, 2018.
4. H.-Y. Li, I. Paranawithana, L. Yang, and U.-X. Tan, "Physical human-robot interaction coupled with a moving environment or target: contact and track," IEEE CASE 2018, Munich, Germany, 2018.

Completed Jun 2016 — Dec 2019

Low-Cost Vision-Guided Robotic Micromanipulation

Singapore University of Technology and Design (SUTD) · Singapore

Massachusetts Institute of Technology (MIT), USA; National Institute of Education (NIE), Singapore

Developed a calibration-less, self-initialising robotic micromanipulation system with sub-pixel tool-tip localisation, confidence-weighted hybrid tracking, and autonomous refocusing — enabling portable, plug-and-play cell handling on low-cost microscopes.

Computer Vision Micromanipulation Visual Tracking Cell Handling Automation

Key Outcomes

• Delivered sub-pixel tool-tip localisation with a low-cost and portable microscope setup
• Designed tool-tip auto-focus algorithm, moving tip 95.3% closer to the focal plane
• Built self-initialisation and recovery algorithm improving localisation from >50% error to <10% of specimen size
• Implemented confidence-weighted hybrid tracking with visual and motion data fusion, reducing error by 18%
• Achieved 97.7% cell detection accuracy and <1-pixel average visual-servo error

Publications

Journal Articles

1. L. Yang, I. Paranawithana, K. Youcef-Toumi, and U. X. Tan, "Confidence-based hybrid tracking to overcome visual tracking failures in calibration-less vision-guided micromanipulation," IEEE Transactions on Automation Science and Engineering, 2020. IF: 6.636
2. L. Yang, I. Paranawithana, K. Youcef-Toumi, and U. X. Tan, "Automatic vision-guided micromanipulation for versatile deployment and portable setup," IEEE Transactions on Automation Science and Engineering, 2018. IF: 6.636

Conference Papers

1. I. Paranawithana, Z.H. Chau, L. Yang, Z. Chen, K. Youcef-Toumi and U.-X. Tan, "Automatic targeting of plant cells via cell segmentation and robust scene-adaptive tracking," IEEE ICRA 2019, Montreal, Canada, 2019.
2. Z.H. Chau, I. Paranawithana, L. Yang, and U.-X. Tan, "Plant cell segmentation with adaptive thresholding," M2VIP 2018, Stuttgart, Germany, 2018.
3. I. Paranawithana, L. Yang, Z. Chen, K. Youcef-Toumi, and U.-X. Tan, "Scene-adaptive fusion of visual and motion tracking for vision-guided micromanipulation in plant cells," IEEE CASE 2018, Munich, Germany, 2018.
4. L. Yang, I. Paranawithana, K. Youcef-Toumi, and U.-X. Tan, "Self-initialization and recovery for uninterrupted tracking in vision-guided micromanipulation," IEEE/RSJ IROS 2017, Vancouver, Canada, 2017.

No projects match the selected filters.