Data scientist with a background in physics and medical image analysis.
- Medical Image Analysis
- Deep Learning for Biomedical Data
- Interpretable & Trustworthy Machine Learning
Data scientist with a background in physics and medical image analysis.
Master thesis β unsupervised deep clustering of MALDI-MSI ion images, University of Padova 2024
Supervised topological data analysis for MALDI-MSI data β persistence transformation for spectral feature extraction and classification, applied to public and proprietary clinical datasets.
Noise2Void self-supervised denoising applied to proprietary fluorescence microscopy data from INT Milan β training directly on single noisy images without clean targets.
A practical project on detecting and addressing domain shift in medical image classification using uncertainty estimation, entropy-based OOD detection, and domain adaptation.
Jupyter Notebook
Ensemble learning for chest X-ray classification using DenseNet, CovidNet, and Attention ResNet trained from scratch.
Jupyter Notebook
Systematic study of the Information Bottleneck theory of deep learning; comparing Tanh vs ReLU, SGD vs BGD, and Binning vs KDE mutual information estimation across multiple CNN and feedforward arch...
Jupyter Notebook