skip to content

Researcher: Angelica Aviles Rivero, Veronica Corona, Noémie Debroux, Carola-Bibiane Schönlieb

However, in most recent years, there has been a great interest for improving medical image reconstruction by using what is called multi-tasking models (also known as joint models). The central idea of this perspective is that by sharing representation between tasks and carefully intertwining them, one can create synergies across challenging problems and reduce error propagation, which results in boosting the accuracy of the outcomes whilst achieving better generalisation capabilities. In this project, we aim to develop computationally tractable and mathematically well-motivated  multi-task frameworks for improving image reconstruction. To do this, we investigate how reconstruction can be improved when other close related tasks are used– for example, image registration (motion estimation) and super-resolution. 

Related Publications 

Compressed sensing plus motion (CS + M): A new perspective for improving undersampled MR image reconstruction
AI Aviles-Rivero, N Debroux, G Williams, MJ Graves, C-B Schönlieb – CoRR (2020) abs/1810.10828, 101933
Learning optical flow for fast MRI reconstruction
T Schmoderer, AI Aviles-Rivero, V Corona, N Debroux, CB Schönlieb – Inverse Problems (2021) 37, 095007
Rethinking medical image reconstruction via shape prior, going deeper and faster: Deep joint indirect registration and reconstruction
J Liu, AI Aviles-Rivero, H Ji, C-B Schönlieb – Medical image analysis (2020) 68, 101930
Variational multi-task MRI reconstruction: Joint reconstruction, registration and super-resolution
V Corona, AI Aviles-Rivero, N Debroux, CL Guyader, C-B Schönlieb – Medical Image Analysis (2020) 68, 101941
Multi-tasking to Correct: Motion-Compensated MRI via Joint Reconstruction and Registration
V Corona, AI Aviles-Rivero, N Debroux, M Graves, C Le Guyader, CB Schönlieb, G Williams – SCALE SPACE AND VARIATIONAL METHODS IN COMPUTER VISION, SSVM 2019 (2019) 11603, 263