Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications.
Johannes Leuschner,Maximilian Schmidt,Poulami Somanya Ganguly,Vladyslav Andriiashen,Sophia Bethany Coban,Alexander Denker,Dominik F. Bauer,Amir Hadjifaradji,Kees Joost Batenburg,Peter Maass,Maureen van Eijnatten +10 more
Reads0
Chats0
TLDR
In this article, the authors present the results of a data challenge that they 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.Abstract:
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.read more
Citations
More filters
Journal ArticleDOI
Deep Learning in Medical Image Analysis.
TL;DR: In this paper, deep learning has established itself as a powerful tool across a broad spectrum of domains in imaging, such as image classification, image segmentation, and image classification and classification.
Journal ArticleDOI
Conditional Invertible Neural Networks for Medical Imaging.
TL;DR: In this article, the authors apply generative flow-based models based on invertible neural networks to two challenging medical imaging tasks, i.e., low-dose computed tomography and accelerated medical resonance imaging.
Journal ArticleDOI
PatchNR: learning from very few images by patch normalizing flow regularization
Fabian Altekrüger,Alexander Denker,Paul Hagemann,Johannes Hertrich,Peter Maass,Gabriele Steidl +5 more
TL;DR: In this article , a patch normalizing flow regularizer (patchNR) is proposed for the variational modeling of inverse problems in imaging, which is independent of the considered inverse problem such that the same regularizer can be applied for different forward operators acting on the same class of images.
Journal ArticleDOI
LRR-CED: low-resolution reconstruction-aware convolutional encoder–decoder network for direct sparse-view CT image reconstruction
TL;DR: This work presents a novel method that uses information from both sinogram and low-resolution scout images for sparse-view CT image reconstruction, in the direction of exploring deep learning across the various stages of the image reconstruction pipeline involving data correction, domain transfer and image improvement.
Journal ArticleDOI
An Educated Warm Start for Deep Image Prior-Based Micro CT Reconstruction
TL;DR: In this article , the authors proposed a two-stage learning paradigm: (i) perform a supervised pretraining of the network on a simulated dataset; (ii) fine-tune the network's parameters to adapt to the target reconstruction task.
References
More filters
Journal ArticleDOI
Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
Qingsong Yang,Pingkun Yan,Yanbo Zhang,Hengyong Yu,Yongyi Shi,Xuanqin Mou,Mannudeep K. Kalra,Ge Wang +7 more
TL;DR: This paper introduces a new CT image denoising method based on the generative adversarial network (GAN) with Wasserstein distance and perceptual similarity that is capable of not only reducing the image noise level but also trying to keep the critical information at the same time.
Journal ArticleDOI
On the determination of functions from their integral values along certain manifolds
TL;DR: The problem which is solved is the inversion of this linear functional transformation, that is the following questions are answered: can every line function satisfying suitable regularity conditions be regarded as constructed in this way?
Journal ArticleDOI
The ASTRA Toolbox: A platform for advanced algorithm development in electron tomography.
Wim van Aarle,Willem Jan Palenstijn,Willem Jan Palenstijn,Jan De Beenhouwer,Thomas Altantzis,Sara Bals,K. Joost Batenburg,K. Joost Batenburg,K. Joost Batenburg,Jan Sijbers +9 more
TL;DR: The ASTRA Toolbox provides an extensive set of fast and flexible building blocks that can be used to develop advanced reconstruction algorithms, effectively removing limitations in the geometrical parameters of the acquisition model and the algorithms used for reconstruction.
Journal ArticleDOI
CT artifacts: Causes and reduction techniques
TL;DR: Methods for reducing noise and out-of-field artifacts may enable ultra-high resolution limited field of view imaging of tumors and other structures and result in a more accurate diagnosis.
Journal ArticleDOI
Low-dose CT via convolutional neural network
TL;DR: A deep convolutional neural network is here used to map low-dose CT images towards its corresponding normal-dose counterparts in a patch-by-patch fashion, demonstrating a great potential of the proposed method on artifact reduction and structure preservation.