Xingjian Zhang

About me

I am a PhD student in the Hydrodynamics Laboratory of École Polytechnique (LADHYX) and the Information Processing and Communications Laboratory of Télécom Paris (LTCI).

My research aims to quantify cellular nuclear deformations on microgroove substrates using deep learning, supervised by Prof. Abdul Barakat and Prof. Elsa Angelini.

I am interested in artificial intelligence for biomedical research and its applications across other data-driven research domains.

You can download a PDF copy of my CV [HERE].

Publications

Peer-reviewed

• M.C. Yagüe, X. Zhang, M. Volpatti, Y. Wei, G. Lebedev, J. Gamby, and A.I. Barakat, "Noninvasive real-time monitoring of cellular spatiotemporal dynamics via machine learning-enhanced electrical impedance spectroscopy," Science Advances, 2025. [PDF]

• A. Hauguel, K. Kasani, V. Chevance, X. Zhang, A.I. Barakat, S. Haulon, and A. Azarine , "Changes in ascending aorta and aortic arch secondary flow patterns following endovascular repair of the descending thoracic aorta", European Journal of Vascular and Endovascular Surgery, 2025. [PDF]

• C. Leclech, G. Cardillo, B. Roellinger, X. Zhang, J. Frederick, K. Mamchaoui, C. Coirault, and A.I. Barakat, "Micro-scale topography triggers dynamic 3D nuclear deformations," Advanced Science, 2025. [PDF]

• B. Asadipour, E. Beaurepaire, X. Zhang, A. Chessel, P. Mahou, W. Supatto, M.C. Schanne-Klein, and C. Stringari, "Modeling and predicting second harmonic generation from protein molecular structure," Physical Review X, 2024. [PDF]

• X. Zhang, C. Leclech, B. Roellinger, C. Coirault, E.D. Angelini, and A.I. Barakat, "Myoblast mutation classification via microgroove-induced nuclear deformations," Medical Imaging with Deep Learning, 2024. [PDF]

• G. Pogudin, X. Zhang, "Interpretable exact linear reductions via positivity," Computational Methods in Systems Biology, 2021. [PDF]

Pre-prints

• B. Asadipour, R. Ronzano, J. Morizet, X. Zhang, A. Chessel, P. Mahou, M. Aigrot, B. Stankoff, A. Desmazieres, E. Beaurepaire, and C. Stringari, "Label-free non-linear microscopy probes cellular metabolism and myelin dynamics in live brain tissue," 2024.

• S. Lim, X. Zhang, E. Beaurepaire, and A. Chessel, "BioImageLoader: Easy Handling of Bioimage Datasets for Machine Learning," 2023. [PDF]

Projects

BioimageLoader

Load bioimages for machine learning applications

bioimageloader is a python library to make it easy to load bioimage datasets for machine learning and deep learning.

Bioimages come in numerous and inhomogeneous forms. bioimageloader attempts to wrap them in unified interfaces, so that you can easily concatenate, perform image augmentation, and batch-load them.

bioimageloader provides:

• collections of interfaces for popular and public bioimage datasets
• image augmentation using albumentations, which is popular and powerful image augmentation library (for 2D images)
• compatibility with pytorch
• and with others such as scikit-learn and tensorflow

Contact

Email: xingjian.zhang@polytechnique.edu | xingjian.zhang@telecom-paris.fr

Office: Batiment 104, Bd des Maréchaux, 91120, Palaiseau