Enamundram Naga Karthik

prof_pic.jpg

Hi there! I’m Naga, a fourth-year PhD student at NeuroPoly, Polytechnique Montréal. I’m also affiliated to Mila - Québec AI Institute. My research focuses on developing deep learning-based methods for medical image analysis, with a particular interest in spinal cord imaging using real-world clinical data. My current projects include contrast-agnostic segmentation of the spinal cord and the segmentation of lesions in spinal cord injury and multiple sclerosis (MS). I have also experimented with generative modelling, in particular, training GANs for cross-modality MR-CT synthesis and diffusion models for synthesizing spinal cord lesions. In the past, I have also worked on the application of continual/lifelong learning methods for the segmentation of brain MS lesions.

When I am not working, you’ll find me either running :running:, hiking :mountain:, or reading :book:.

news

Apr 27, 2024 Our spin-off project comparing different DL architectures for contrast-agnostic spinal cord segmentation was accepted at the MIDL 2024 Short Paper Track!
Mar 7, 2024 I was awarded the DAAD Short-term Research Grants for a 4-month research stay at the Technical University of Munich, Germany!
Feb 2, 2024 Our recent works on contrast-agnostic spinal cord segmentation and segmentation of spinal cord injury lesions were accepted for Oral Presentations at the 2024 ISMRM & ISMRT Annual Meeting & Exhibition in Singapore :singapore: !
Nov 22, 2023 I gave a talk on Automatic Segmentation of Brain and Spinal Cord Lesions across Pathologies at the UNIQUE Fellows Get-Together, held at Mila!
Aug 8, 2023 I gave a talk on Continual Learning for Medical Image Segmentation at the Chandar Lab Symposium, held at Mila!

selected publications

  1. MIDL
    Contrast-agnostic Spinal Cord Segmentation: A Comparative Study of ConvNets and Vision Transformers
    Enamundram Naga Karthik, Sandrine Bedard, Jan Valosek, Sarath Chandar, and Julien Cohen-Adad
    In Medical Imaging with Deep Learning, 2024
  2. medRxiv
    SCIseg: Automatic Segmentation of T2-weighted Intramedullary Lesions in Spinal Cord Injury
    Enamundram Naga Karthik*, Jan Valosek*, Andrew C. Smith, Dario Pfyffer, Simon Schading-Sassenhausen, Lynn Farner, Kenneth A. Weber II, Patrick Freund, and Julien Cohen-Adad
    medRxiv, 2024
    *shared first authorship
  3. arXiv
    Towards contrast-agnostic soft segmentation of the spinal cord
    Sandrine Bédard*, Naga Karthik Enamundram*, Charidimos Tsagkas, Emanuele Pravatà, Cristina Granziera, Andrew Smith, Kenneth Arnold Weber II, and Julien Cohen-Adad
    2023
    *shared first authorship