Computed tomography reconstruction using deep image prior and learned reconstruction methods

Baguer, Daniel Otero; Leuschner, Johannes; Schmidt, Maximilian

doi:10.1088/1361-6420/aba415

Cited by 152 publications

(117 citation statements)

References 41 publications

Supporting

Mentioning

115

Contrasting

Order By: Relevance

“…This is further an indicator of the large quantity of data needed for the fully learned approach to work well. Similar observations are made by Baguer et al: 94 in their overview, they show that a fully learned approach only performs well with large amounts of data, which explains in parts the poor performance in this limited data setting.…”

Section: Reconstructions: Robustness and Generalizationsupporting

confidence: 84%

Deep learning in photoacoustic tomography: current approaches and future directions

2020

View full text Add to dashboard Cite

Biomedical photoacoustic tomography, which can provide high-resolution 3D soft tissue images based on optical absorption, has advanced to the stage at which translation from the laboratory to clinical settings is becoming possible. The need for rapid image formation and the practical restrictions on data acquisition that arise from the constraints of a clinical workflow are presenting new image reconstruction challenges. There are many classical approaches to image reconstruction, but ameliorating the effects of incomplete or imperfect data through the incorporation of accurate priors is challenging and leads to slow algorithms. Recently, the application of deep learning (DL), or deep neural networks, to this problem has received a great deal of attention. We review the literature on learned image reconstruction, summarizing the current trends and explain how these approaches fit within, and to some extent have arisen from, a framework that encompasses classical reconstruction methods. In particular, it shows how these techniques can be understood from a Bayesian perspective, providing useful insights. We also provide a concise tutorial demonstration of three prototypical approaches to learned image reconstruction. The code and data sets for these demonstrations are available to researchers. It is anticipated that it is in in vivo applications-where data may be sparse, fast imaging critical, and priors difficult to construct by hand-that DL will have the most impact. With this in mind, we conclude with some indications of possible future research directions. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

Section: Reconstructions: Robustness and Generalizationsupporting

confidence: 84%

Deep learning in photoacoustic tomography: current approaches and future directions

2020

View full text Add to dashboard Cite

show abstract

“…The loss function (A1) can also be combined with classical regularization. Baguer et al [34] add a weighted anisotropic total variation (TV) term and apply their approach to low-dose CT measurements. The method DIP + TV is also used for this comparison.…”

Section: Deep Image Prior With Tv Denoisingmentioning

confidence: 99%

Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications

et al. 2021

Self Cite

View full text Add to dashboard Cite

The reconstruction of computed tomography (CT) images is an active area of research. Following the rise of deep learning methods, many data-driven models have been proposed in recent years. In this work, we present the results of a data challenge that we organized, bringing together algorithm experts from different institutes to jointly work on quantitative evaluation of several data-driven methods on two large, public datasets during a ten day sprint. We focus on two applications of CT, namely, low-dose CT and sparse-angle CT. This enables us to fairly compare different methods using standardized settings. As a general result, we observe that the deep learning-based methods are able to improve the reconstruction quality metrics in both CT applications while the top performing methods show only minor differences in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). We further discuss a number of other important criteria that should be taken into account when selecting a method, such as the availability of training data, the knowledge of the physical measurement model and the reconstruction speed.

show abstract

“…In total, the dataset features more than 40000 sample pairs from over 800 different patients. This amount of data and variability can be necessary to successfully train deep neural networks 25 . It also qualifies the dataset for transfer learning.…”

Section: Background and Summarymentioning

confidence: 99%

“…a sparser setup with 200 angles was already used by Baguer et al . 25 . Super-resolution experiments can be mimicked, by artificially binning the projection data into larger pixels.…”

Section: Usage Notesmentioning

confidence: 99%

LoDoPaB-CT, a benchmark dataset for low-dose computed tomography reconstruction

et al. 2021

Self Cite

View full text Add to dashboard Cite

Deep learning approaches for tomographic image reconstruction have become very effective and have been demonstrated to be competitive in the field. Comparing these approaches is a challenging task as they rely to a great extent on the data and setup used for training. With the Low-Dose Parallel Beam (LoDoPaB)-CT dataset, we provide a comprehensive, open-access database of computed tomography images and simulated low photon count measurements. It is suitable for training and comparing deep learning methods as well as classical reconstruction approaches. The dataset contains over 40000 scan slices from around 800 patients selected from the LIDC/IDRI database. The data selection and simulation setup are described in detail, and the generating script is publicly accessible. In addition, we provide a Python library for simplified access to the dataset and an online reconstruction challenge. Furthermore, the dataset can also be used for transfer learning as well as sparse and limited-angle reconstruction scenarios.

show abstract

Computed tomography reconstruction using deep image prior and learned reconstruction methods

Cited by 152 publications

References 41 publications

Deep learning in photoacoustic tomography: current approaches and future directions

Deep learning in photoacoustic tomography: current approaches and future directions

Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications

LoDoPaB-CT, a benchmark dataset for low-dose computed tomography reconstruction

Contact Info

Product

Resources

About