Enamundram Naga Karthik

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 , hiking , or reading .

news

Jul 19, 2024	Our paper “SCIsegV2: A Universal Tool for Segmentation of Intramedullary Lesions in Spinal Cord Injury” was accepted at MICCAI Applications of Medical Artificial Intelligence (AMAI) Workshop 2024 in Marrakech, Morocco! 🇲🇦
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 Grant 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 !
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!

selected publications

MIDL Short

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

Bib PDF Code

@inproceedings{karthik2024contrastagnostic,
  title = {Contrast-agnostic Spinal Cord Segmentation: A Comparative Study of ConvNets and Vision Transformers},
  author = {Karthik, Enamundram Naga and Bedard, Sandrine and Valosek, Jan and Chandar, Sarath and Cohen-Adad, Julien},
  booktitle = {Medical Imaging with Deep Learning},
  year = {2024},
  url = {https://openreview.net/forum?id=n6D25aqdV3},
}

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

Bib PDF Code

@article{Naga Karthik2024.01.03.24300794,
  author = {Karthik*, Enamundram Naga and Valosek*, Jan and Smith, Andrew C. and Pfyffer, Dario and Schading-Sassenhausen, Simon and Farner, Lynn and II, Kenneth A. Weber and Freund, Patrick and Cohen-Adad, Julien},
  title = {SCIseg: Automatic Segmentation of T2-weighted Intramedullary Lesions in Spinal Cord Injury},
  elocation-id = {2024.01.03.24300794},
  year = {2024},
  doi = {10.1101/2024.01.03.24300794},
  publisher = {Cold Spring Harbor Laboratory Press},
  url = {https://www.medrxiv.org/content/early/2024/04/21/2024.01.03.24300794},
  journal = {medRxiv},
  note = {*shared first authorship}
}

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

Bib PDF Code

@misc{bédard2023contrastagnostic,
  title = {Towards contrast-agnostic soft segmentation of the spinal cord},
  author = {Bédard*, Sandrine and Enamundram*, Naga Karthik and Tsagkas, Charidimos and Pravatà, Emanuele and Granziera, Cristina and Smith, Andrew and II, Kenneth Arnold Weber and Cohen-Adad, Julien},
  year = {2023},
  eprint = {2310.15402},
  archiveprefix = {arXiv},
  primaryclass = {eess.IV},
  note = {*shared first authorship}
}