Portrait of Nichula Sathmith Wasalathilaka

Nichula Sathmith Wasalathilaka

Final-year Electrical and Electronic Engineering Undergraduate

University of Peradeniya, Sri Lanka

Visiting Research Student at MBZUAI, Abu Dhabi — working with Prof. Imran Razzak on trustworthy medical AI

I am a final-year Electrical and Electronic Engineering undergraduate at the University of Peradeniya, Sri Lanka, and a visiting research student at Mohamed bin Zayed University of Artificial Intelligence.

My research centres on a single question: how do we make machine learning systems that scientists and clinicians can actually trust? In remote sensing, that means building models that are robust to sensor and domain shift and that generalise reliably across geographic distributions. In medical imaging, it means detecting when a deployed model is operating outside its training distribution — and producing explanations over named anatomical structures rather than uninterpretable pixel-level heatmaps. In scientific computing, it means generating reproducible, simulation-ready geometry that can be audited and varied in a principled way. These threads converge on a broader programme: uncertainty-aware, distribution-robust AI for high-stakes scientific imaging.

I am actively seeking PhD positions for Fall 2027 to pursue this direction at depth.

Remote Sensing Medical AI Computer Vision Signal Processing Trustworthy AI Scientific Machine Learning

Selected Publications

  1. MICCAI 2026 First Author
    Graph-of-Differences: Anatomy-Structured Difference Alignment for Medical Image Re-Identification

    Nichula Wasalathilaka, Abhijit Das, Imran Razzak, Dwarikanath Mahapatra

  2. MICCAI 2026
    PROTON: Prototype-based Test-time Online OOD Detection for Medical Vision-Language Models

    Abhijit Das, Nichula Wasalathilaka, Yifan Lu, Adinath Dukre, Dwarikanath Mahapatra, Shadab Khan, Imran Razzak

  3. IEEE J-STARS Published
    Mamba-FCS: Joint Spatio-Frequency Feature Fusion, Change-Guided Attention, and SeK Inspired Loss for Enhanced Semantic Change Detection in Remote Sensing

    Buddhi Wijenayake, Athulya Ratnayake, Praveen Sumanasekara, Roshan Godaliyadda, Parakrama Ekanayake, Vijitha Herath, Nichula Wasalathilaka

View all 7 publications →

Updates ...

  • Jun. 2026: Two papers were accepted to MICCAI 2026, Strasbourg, France:
    1. Graph-of-Differences: Anatomy-Structured Difference Alignment for Medical Image Re-Identification 2. PROTON: Prototype-based Test-time Online OOD Detection for Medical Vision-Language Models
  • Jun. 2026: Paper accepted to IEEE Mercon 2026:
    1. RespGeomLib: A Reproducible Parametric Engine for Generating Analysis-Ready Human Airway Lumen Geometry
  • Mar. 19, 2026: Two papers were accepted to IGARSS 2026, Washington, D.C., USA:
    1. Mitigating Long-Tail Bias in LoveDA via Prompt-Controlled Diffusion Augmentation 2. A Controlled Benchmark of Visual State-Space Backbones with Domain-Shift and Boundary Analysis for Remote-Sensing Segmentation
  • Feb. 2026: Our paper Mamba-FCS: Joint Spatio-Frequency Feature Fusion, Change-Guided Attention, and SeK Loss for Enhanced Semantic Change Detection in Remote Sensing was published in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.
  • Jan. 2026: Our paper Precision Spatio-Temporal Feature Fusion for Robust Remote Sensing Change Detection was published in the IEEE ICIIS 2025 proceedings, Faculty of Engineering, University of Peradeniya, Peradeniya, Sri Lanka.
  • Nov. 25, 2025: Received the Best Oral Presentation Award in the Artificial Intelligence and Data Science track at ICIET 2025, Faculty of Technology, University of Sri Jayewardenepura, Sri Lanka for Automated Slum Detection from High-Resolution Satellite Imagery.

Contact

I expect to graduate in late 2026 and am actively seeking PhD positions for Fall 2027 in trustworthy AI, medical imaging, or remote sensing. I am happy to discuss research fit and potential collaboration.

Email: e20425@eng.pdn.ac.lk