Juan Felipe Pérez-Juste Abascal, Ph.D.
Researcher in medical imaging, image processing, inverse problems and deep learning
Current position at AMIDS Solutions, Lyon, France
juanabascal78 at gmail.com
Past positions
2021 Research & Development, Carestream dental, Croissy-Beaubourg, France
2016 Marie Skłodowska-Curie fellow - CREATIS (CNRS UMR 5220 – INSERM U1206 – Université Lyon 1 – INSA Lyon), France
Team 4 - Tomographic imaging and therapy with radiation
2011 Post-doc at Departamento de Bioingeniería e Ingeniería Aeroespacial, Universidad Carlos III de Madrid, Spain
Research group: Laboratorio de Imagen Médica, Unidad de Medicina y Cirugía Experimental, Hospital General Universitario Gregorio Marañón, Madrid, Spain
2009 Post-doc, Unidad de Medicina y Cirugía Experimental, Hospital General Universitario Gregorio Marañón, Madrid, Spain
2008 Research & Development, Alten Ingenieria, Madrid, Spain
2007 Post-doc, Laboratoire des Signaux et Systèmes, Ecole Superieure d'Electricite (SUPÉLEC), Gif-sur-Yvette, France
Supervision
Supervision of three MSc students in several topics: Deep learning (Valeriya Pronina), Spectral CT (Suzanne Bussod), Synchrotron nano-CT (Claude Goubet).
Co-supervision of two PhD students in compressed sensing MRI (Paula Montesinos, Cristina Chavarrias) and a PhD student on deep learning for spectral CT (Suzanne Bussod).
Download CV:
Education
2007 Ph.D., Medical Physics & Bioengineering, University College London, UK
-
Thesis title: Improvements in reconstruction algorithms for electrical impedance tomography of brain function
-
Supervisors: Simon Arridge, David Holder and Richard Bayford
2003 M.Sc., Applied Mathematics, The University of Manchester, UK
-
Thesis title: The anisotropic inverse conductivity problem
-
Supervisor: Bill Lionheart
2002 B.Sc. & M.Sc., Theoretical Physics, Universidad Autónoma de Madrid, Spain
Other courses
Deployment and MLOps
-
Deploying Machine Learning Models in Production (MLOps), Coursera
-
TensorFlow: Data and Deployment Specialization, Coursera
-
Browser-based Models with TensorFlow.js
-
Device-based Models with TensorFlow Lite
-
Data Pipelines with TensorFlow Data Services
-
Advanced Deployment Scenarios with TensorFlow
-
NLP and LLMs
-
ChatGPT for Developers, DeepLearning.AI
-
LangChain: Chat with Your Data, DeepLearning.AI
Deep learning
-
Deep Learning Specialization, Coursera
-
Convolutional Neural Networks
-
Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
-
Structuring Machine Learning Projects
-
Sequence Models (RNN, LSTM, Transformer, NLP)
-
-
Deep Generative Models, Udemy
-
Autoregressive models, VAE, GAN, Diffusion models
-
-
Generative Adversarial Networks (GANs) Specialization, Coursera
-
Build Basic Generative Adversarial Networks
-
Build Better Generative Adversarial Networks
-
Machine learning
-
Probabilistic Graphical Models Specialization, Coursera
-
Probabilistic Graphical Models 1: Representation
-
Some hobbies and interests
Bouldering: indoors climbing.
Capoeira: a Brazilian art form that combines elements of martial arts, dance, acrobatics, music and spirituality.
Canoe polo: a sport that combines many different skills - a real fun game. An introduction video.
After discovering canoe polo at the ULU swimming pool, in London, I joined the ULU team for three years. Having fun, training hard and building team work, we brought the team to the second position at the British University Competition. Among all tournaments my favorite one was the 26 hours Canoe Polo Cancer Challenge 2006. During my stay in France, I joined Canoë kayak Gennevilliers, in Paris, playing tournaments around the region, and then trained during few months with Grenoble Kayak Polo. Last, with Canoa Kayak Las Rozas, Madrid (pictures below), I participated in tournaments in Spain and Portugal.