Suprosanna Shit

Research Interests

• Physics Motivated Deep Learning: Deep learning to solve inverse problems in pysics.
• Medical Image Analysis: Analysis of 4D flow MRI.
• Generative Modelling: Adversarial learning to model physical processes.
• Baysian Deep learning: Uncertainty quantification in deep learning.

Student Projects

We are inviting applications for several exciting research opportunities for Master students with our group. Please also feel free to reach out if you are interested in a Bachelor thesis, research project, etc. The projects are intended for students in Informatics, Electrical Engineering, or related fields. Currently, active projects include but not limited to:

• Available from August 2021 Organs at Risk Detection and Localization for Radiation Therapy Planning using Transformers
• Currently Running 3D vessel tracking using transformer
• Currently Open Mesh CNN for vessel annomaly detection
• Completed March 2020 Graph synthesis for medical applications
• Completed November 2019 Neural solver for PDEs
• Completed September 2019 Inverse Problems in PDE-driven Processes Using Deep Learning

Publications

2021
	S. Shit, J. Paetzold, I. Ezhov, A. Sekuboyina, B. Menze clDice - a Novel Connectivity-Preserving Loss Function for Vessel Segmentation IEEE Conference on Computer Vision and Pattern Recognition, Nashville, Tennessee, United States, June 2021. Shit and Paetzold share first authorship. (bib)
2020
	O. Gerl, J. Paetzold, , I. Ezhov, S. Shit, F. Kofler, , G. Tetteh, V. Ntziachristos, B. Menze A distance-based loss for smooth and continuous skin layer segmentation in optoacoustic images. International Conference on Medical Image Computing and Computer Assisted Intervention 2020 (MICCAI) Gerl and Paetzold share first authorship. (bib)
	M.I.Todorov, J. Paetzold, O. Schoppe, G. Tetteh, S. Shit, , B. Menze, A. Ertuerk Machine learning analysis of whole mouse brain vasculature. Nature Methods volume 17, pages 442 to 449, (2020). Todorov and Paetzold share first authorship. (bib)
2019
	J. Paetzold, S. Shit, I. Ezhov, G. Tetteh, A. Ertuerk, B. Menze clDice-a Novel Connectivity-Preserving Loss Function for Vessel Segmentation Medical Imaging Meets NeurIPS? 2019 (Workshop), Vancouver, Canada, December 2019. (bib)
	F. Navarro, S. Shit, I. Ezhov, J. Paetzold, A. Gafita, J. Peeken, S. Combs, B. Menze Shape-Aware Complementary-Task Learning for Multi-Organ Segmentation Proceedings of the 10th International Workshop on Machine Learning in Medical Imaging (MLMI 2019), Shenzhen, China, October 2019. (bib)
	I. Ezhov, J. Lipkova, S. Shit, F. Kofler, N. Collomb, B. Lemasson, E. Barbier, B. Menze Neural parameters estimation for brain tumor growth modeling Proceedings of the 22th International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI), Shenzhen, China, October 2019. (bib)