Nikhil Kurian

Nikhil Kurian

Researcher, AIML

About Me

I am Nikhil Cherian Kurian, a post-doctoral research staff at the Australian Institute of Machine Learning (AIML) , University of Adelaide. Prior to this I was a senior AI researcher at Fujitsu Research of India Pvt Ltd (FRIPL). I completed my PhD in May 2023 from the Department of Electrical Engineering at the Indian Institute of Technology, Bombay. My PhD research was focused on introducing a range of novel deep learning based algorithms that automatically analyse cancerous tissue in H&E histology images. My expertise lies in developing robust supervision techniques for large scale medical image analysis. During my PhD, I was associated with MeDAL (Medical Imaging, Deep Learning, and Artificial Intelligence Lab) and worked under the supervision of Prof. Amit Sethi. Earlier, I obtained my Master's degree from the department of electrical engineering at IIT Gandhinagar under the supervision of Prof. Nithin V George, where I developed novel information-theoretic learning algorithms for various signal processing applications.

During my research, I was fortunate to work and communicate with various collaborators from the perspective of broad interdisciplinary research during my PhD. In my PhD I mainly focussed on analysing and quantifying intra-tumour heterogeneity in breast cancer tissues under the mentorship of Prof Peter Gann, University of Illinois, Chicago. Earlier in my PhD, I also got the opportunity to work with Prof. Anita Grigoriadis of Kings College London, and Prof Swapnil Rane, Tata Memorial Centre, Mumbai where we worked on solving robust pathological feature segmentation using novel deep learning pipelines to analyse breast cancer lymph nodes. I also had research assosciations with Nvidia Corporation Mumbai for exploratory and accelerated research in large scale histopathology problems.


I maintain a list of my publications under the Research tab and my full Resume is attached the CV Tab.

Recent Updates

  1. A paper entitled “Magnification Invariant Medical Image Analysis: A Comparison of Convolutional Networks, Vision Transformers, and Token Mixers”, got accepted in BIOIMAGING 2023, Rome, Italy - December 2023.
  2. Our work “WSSAMNet : Weakly Supervised Semantic Attentive medical Image Registration Network” will appear as a book chapter in “Branlesion: Giloma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries” Book by Springer Publication. -December 2023.
  3. A paper entitled “Robust Semi-Supervised Learning for Histopathology Images through Self-Supervision Guided Out-of-Distribution Scoring”, got accepted in the 23rd IEEE International Conference on Bioinformatics and Bioengineering (BIBE) Conference. - November 2023.
  4. I joined as a post-doctoral research staff at the Australian institute for machine learning, Adelaide, Australia - Nov,2023
  5. One paper entitled “Improved Multi-Step, Multi-Variate, and Spatiotemporal 5G Data Usage Forecasting Without Deploying Data Imputation Techniques” got accepted in IEEE Globecom conference 2023. This is our first publication from Fujitsu Research India - August 2023
  6. A paper entitled “Heterogeneous graphs model spatial relationships between biological entities for breast cancer diagnosis” got accepted in MICCAI workshops - August 2023.
  7. Successfully defended my PhD thesis entitled “Cautious and Robust Deep Learning Algorithms for Medical Image Analysis”, Department of Electrical Engineering, IIT Bombay - May 2023.
  8. The Journal of Pathology has recently accepted a paper titled “Multiscale deep learning framework captures systemic immune features in lymph nodes predictive of triple negative breast cancer outcome in large-scale studies.” This publication is the result of collaborative efforts between our team and researchers from Kings College London, as well as other institutions representing seven different countries - April 2023.
  9. A journal entitled “Efficient Quality Control of Whole Slide Pathology Images with Human-in-the-Loop Training” has been accepted in the Journal of Pathology Informatics. Congratulations to all co-authors! - March 2023.
  10. Our paper “Improving Mitosis Detection Via UNet-based Adversarial Domain Homogenizer” won the best paper award in BIOIMAGING 2023, Lisbon Portugal. Congratulations to all co-authors - March 2023.