Model-Based Learning for Accelerated, Limited-View 3-D Photoacoustic Tomography

By Andreas Hauptmann, Felix Lucka, Marta M. Betcke, Nam Huynh, Jonas Adler, B. Cox, Paul C. Beard, Sébastien Ourselin, Simon Robert Arridge. IEEE Transactions on Medical Imaging, 2017

328 citations recorded by the source corpus.

Recent advances in deep learning for tomographic reconstructions have shown great potential to create accurate and high quality images with a considerable speed up. In this paper, we present a deep neural network that is specifically designed to provide high resolution 3-D images from restricted photoacoustic measurements. The network is designed to represent an iterative scheme and incorporates gradient information of the data fit to compensate for limited view artifacts. Due to the high complexity of the photoacoustic forward operator, we separate training and computation of the gradient information. A suitable prior for the desired image structures is learned as part of the training. The resulting network is trained and tested on a set of segmented vessels from lung computed tomography scans and then applied to in-vivo photoacoustic measurement data.

Subfields: Biomedical Engineering, Mechanics of Materials, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/1005bbd9eca1bc36f9b9ed5b751c677c45e4b6f3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Carola-Bibiane Schönlieb
2. Ozan Öktem
3. Simon Robert Arridge
4. Andreas Hauptmann
5. Sarah Jane Hamilton
6. Peter Maass
7. Shuhao Cao

In Mechanics of Materials

1. Simon Robert Arridge
2. Carola-Bibiane Schönlieb
3. Peter Maass
4. Ozan Öktem

In Radiology, Nuclear Medicine and Imaging

1. Simon Robert Arridge
2. Carola-Bibiane Schönlieb
3. Andreas Hauptmann
4. Peter Maass
5. Ozan Öktem

Citations in the corpus

• Solving inverse problems using data-driven models (2019, methodology): “The deep gradient descent (DGD) method (Hauptmann et al. 2018) for PAT is an example of a learned iterative method (see Section 5.”
• Deep D-Bar: Real-Time Electrical Impedance Tomography Imaging With Deep Neural Networks (2017, background): “This is in contrast to the studies in [13]–[17], where the authors learn a residual update to the initial reconstruction.”