Scattnet-MR

Scattnet-MR is a machine learning framework for accelerated MRI reconstruction that integrates wavelet scattering transforms with neural implicit representations to achieve robust and interpretable reconstructions.

The research was carried out at the Laboratorio Avanzado de Procesamiento de Imágenes (LAPI), Facultad de Ingeniería, UNAM, where the focus was on combining physically grounded feature extraction with deep learning models to improve stability under noise and distribution shifts, addressing key limitations of black-box approaches in medical imaging.

The project focuses on combining physically grounded feature extraction with deep learning models to improve stability under noise and distribution shifts, addressing key limitations of black-box approaches in medical imaging.

This work has been submitted to the journal Computers in Biology and Medicine and is currently under review.

Preprint: Download PDF