hello there! ✨

I'm Ekaterina Antipushina

PhD student in Computational and Data Science, currently studying quantization techniques, foundation model development, multimodality integration, data fusion approaches, and generative AI applications in neuroimaging to advance computational methods for brain imaging analysis

Ekaterina Antipushina, PhD student at Applied AI Institute specializing in AI research and neuroimaging

located at Applied AI Institute

About Me

Currently pursuing my PhD at Applied AI Institute & Center for Bio- and Medical Technologies. My research focuses on developing AI frameworks for medical applications, particularly in neuroimaging and neurofeedback systems. I specialize in multimodal data fusion approaches, foundation model development with neural quantization techniques, and generative AI methods (VAEs, GANs, Neural Optimal Transport) for analyzing brain signals like EEG and fMRI.

fun fact: outside the lab, you'll find me in Moscow's cozy cafés seeking inspiration.

My Research Interests

Generative AI

  • Foundation models with temporal encoding
  • Neural quantization for continuous-to-discrete conversion
  • Cross-modal learning from 1D to 4D neural signals
  • Self-supervised learning for multichannel data

Medical AI & Neuroimaging

  • EEG, fMRI analysis
  • EEG-to-fMRI problem solutions using deep learning
  • Data analysis for schizophrenia prediction
  • Pharmacological biomarker discovery in brain pathologies

Professional Journey

explore my background...

My Journey

the path that led me here...

PhD in Computational and Data Science
Applied AI Institute & Center for Bio- and Medical Technologies
2024 - present
Diving deep into MLOps, foundation models, and quantization. Working on multimodal data analysis for reliable prediction of localized neuronal activity in real-time.

currently living here! 📚

ML Research Engineer
BIMAI-lab, University of Sharjah
June 2024 - June 2025
- Formulated and statistically tested hypotheses based on experimental conditions and biological processes
- Conducted EDA, feature selection, and clustering to identify trends, reduce dimensionality, and segment data by cell behavior and treatment responses
- Built and validated machine learning models using cross-validation within integrated statistical-ML pipelines
Master's in Medical AI
Skoltech, Biomedically-Informed AI Lab
2022 - 2024
Thesis: "Interpretable machine learning models for multimodal neuroimaging and biomedical data using data fusion methods in schizophrenia diagnosis." Developed data fusion techniques for schizophrenia diagnostic marker discovery, achieving F1 score of 0.87 (13% improvement over previous SOTA of 0.77).

where the magic started! ✨

Researcher
Neuroimaging and Cognitive Neuroscience Lab
June - December 2024
Designed Python-based architecture for real-time fMRI neurofeedback training. Built user-friendly FastAPI servers that make complex neuroscience accessible.
Bachelor's in Biomedical Engineering
Moscow Aviation Institute
2018 - 2022
Built a strong foundation in engineering principles applied to healthcare technology. This is where I first fell in love with the intersection of technology and human wellbeing.

the beginning! 🚀

Curriculum Vitae

CV Document

Your browser doesn't support PDF viewing.

Open CV in New Tab

Professional Resume

Resume Document

Your browser doesn't support PDF viewing.

Open Resume in New Tab

Research Hub

explore my research journey...

Projects

Rest2Task
2023
Generative framework that transforms resting-state fMRI scans into task-based brain activity patterns.
VAE GAN Optimal Transport

dreaming up brain states! 🌙

CSTNet
2024
Deep learning framework that translates EEG signals to high-resolution ECoG mappings using optimal transport theory.
PyTorch Optimal Transport Neural Networks

bridging brain signals! ⚡

pyOpenNFT
2024
Open-source Python framework for real-time fMRI neurofeedback with machine learning integration.
Python FastAPI NumPy

real-time brain magic! ⚡

Publications

pyOpenNFT: an open-source Python framework for ML-based real-time fMRI and EEG-fMRI neurofeedback
Antipushina E., Davydov N., De Feo R., et al.
MICCAI 2025
A* Conference
CSTNet: A Generative Framework for EEG-to-ECoG Translation via Optimal Transport
Kalimullin R., Antipushina E., et al.
MICCAI 2025
A* Conference
Interpretable AI models for predicting distant metastasis development based on genetic data: kidney cancer example
Boyko M., Antipushina E., et al.
BIO Web of Conferences, 2024
Medical AI Application

Posters & Presentations

Rest2Task: generative modeling for task-based fMRI prediction

Rest2Task: generative modeling for task-based fMRI prediction

Sber RnD Day 2024 Poster Session

View PDF
The application of machine learning methods for multimodal neuroimaging data in the diagnosis of schizophrenia

The application of machine learning methods for multimodal neuroimaging data in the diagnosis of schizophrenia

LIFT Conference 2024

View PDF

Research Talks

AI in Neuroimaging Talk

Bridge Between Time and Space: How Generative AI Turns EEG into fMRI

DataFest 2025 (ODS), March 2025

The report is devoted to the application of generative models for the transformation of neuroimaging data with high temporal resolution (EEG) into functional and spatial representations (fMRI), combining their strengths. Modern algorithms, architectural solutions and examples of use in diagnostics and brain research are considered

Watch Recording / Presentation

Let's Connect!

I love connecting with fellow researchers, collaborators, and anyone passionate about making AI solutions!

coffee chats welcome! ☕

Whether you want to discuss research ideas, explore collaboration opportunities, or just share thoughts about the future of AI in healthcare, I'd love to hear from you.

Email Me

ekantipushina@gmail.com

best way to reach me! 📧

LinkedIn

katherine-antipushina

let's connect professionally! 💼

GitHub

utoprey

code & collaborations! 💻

📍 Based in Moscow, Russia

Working from Applied AI Center

always up for meeting fellow researchers in Moscow! 🇷🇺