JBFnet - Low Dose CT Denoising by Trainable Joint Bilateral Filtering

Published on Oct 4, 2020
· DOI :10.1007/978-3-030-59713-9_49
Mayank Patwari2
Estimated H-index: 2
(Siemens),
Ralf Gutjahr7
Estimated H-index: 7
(Siemens),
Rainer Raupach31
Estimated H-index: 31
(Siemens)
Sources
Abstract
Deep neural networks have shown great success in low dose CT denoising. However, most of these deep neural networks have several hundred thousand trainable parameters. This, combined with the inherent non-linearity of the neural network, makes the deep neural network diffcult to understand with low accountability. In this study we introduce JBFnet, a neural network for low dose CT denoising. The architecture of JBFnet implements iterative bilateral filtering. The filter functions of the Joint Bilateral Filter (JBF) are learned via shallow convolutional networks. The guidance image is estimated by a deep neural network. JBFnet is split into four filtering blocks, each of which performs Joint Bilateral Filtering. Each JBF block consists of 112 trainable parameters, making the noise removal process comprehendable. The Noise Map (NM) is added after filtering to preserve high level features. We train JBFnet with the data from the body scans of 10 patients, and test it on the AAPM low dose CT Grand Challenge dataset. We compare JBFnet with state-of-the-art deep learning networks. JBFnet outperforms CPCE3D, GAN and deep GFnet on the test dataset in terms of noise removal while preserving structures. We conduct several ablation studies to test the performance of our network architecture and training method. Our current setup achieves the best performance, while still maintaining behavioural accountability.
References25
Newest
Inspired by complexity and diversity of biological neurons, our group proposed quadratic neurons by replacing the inner product in current artificial neurons with a quadratic operation on input data, thereby enhancing the capability of an individual neuron. Along this direction, we are motivated to evaluate the power of quadratic neurons in popular network architectures, simulating human-like learning in the form of “quadratic-neuron-based deep learning”. Our prior theoretical studies have shown...
Source
#1Meng Li (PKU: Peking University)H-Index: 3
#2William Hsu (UCLA: University of California, Los Angeles)H-Index: 14
Last. Wen Gao (PKU: Peking University)H-Index: 3
view all 5 authors...
Computed tomography (CT) is a widely used screening and diagnostic tool that allows clinicians to obtain a high-resolution, volumetric image of internal structures in a non-invasive manner. Increasingly, efforts have been made to improve the image quality of low-dose CT (LDCT) to reduce the cumulative radiation exposure of patients undergoing routine screening exams. The resurgence of deep learning has yielded a new approach for noise reduction by training a deep multi-layer convolutional neural...
Source
#1Andreas Maier (FAU: University of Erlangen-Nuremberg)H-Index: 39
#2Christopher Syben (FAU: University of Erlangen-Nuremberg)H-Index: 10
Last. Silke Christiansen (Helmholtz-Zentrum Berlin)H-Index: 60
view all 10 authors...
We describe an approach for incorporating prior knowledge into machine learning algorithms. We aim at applications in physics and signal processing in which we know that certain operations must be embedded into the algorithm. Any operation that allows computation of a gradient or sub-gradient towards its inputs is suited for our framework. We derive a maximal error bound for deep nets that demonstrates that inclusion of prior knowledge results in its reduction. Furthermore, we also show experime...
Source
#1Hongming Shan (RPI: Rensselaer Polytechnic Institute)H-Index: 16
#2Atul Padole (Harvard University)H-Index: 17
Last. Ge Wang (RPI: Rensselaer Polytechnic Institute)H-Index: 81
view all 8 authors...
Commercial iterative reconstruction techniques help to reduce CT radiation dose but altered image appearance and artifacts limit their adoptability and potential use. Deep learning has been investigated for low-dose CT (LDCT). Here we design a modularized neural network for LDCT and compared it with commercial iterative reconstruction methods from three leading CT vendors. While popular networks are trained for an end-to-end mapping, our network performs an end-to-process mapping so that interme...
Source
Aug 1, 2018 in ICPR (International Conference on Pattern Recognition)
#1Andreas MaierH-Index: 39
#2Frank SchebeschH-Index: 5
Last. Rebecca Fahrig (FAU: University of Erlangen-Nuremberg)H-Index: 3
view all 7 authors...
In this paper, we consider the use of prior knowledge within neural networks. In particular, we investigate the effect of a known transform within the mapping from input data space to the output domain. We demonstrate that use of known transforms is able to change maximal error bounds and that these are additive for the entire sequence of transforms. In order to explore the effect further, we consider the problem of X-ray material decomposition as an example to incorporate additional prior knowl...
Source
#1Hongming Shan (RPI: Rensselaer Polytechnic Institute)H-Index: 16
#2Atul Padole (Harvard University)H-Index: 17
Last. Ge Wang (RPI: Rensselaer Polytechnic Institute)H-Index: 81
view all 8 authors...
Commercial iterative reconstruction techniques help to reduce the radiation dose of computed tomography (CT), but altered image appearance and artefacts can limit their adoptability and potential use. Deep learning has been investigated for low-dose CT (LDCT). Here, we design a modularized neural network for LDCT and compare it with commercial iterative reconstruction methods from three leading CT vendors. Although popular networks are trained for an end-to-end mapping, our network performs an e...
Source
#1Wei XuH-Index: 13
#2Ziyi ZhengH-Index: 9
Last. Klaus MuellerH-Index: 52
view all 5 authors...
Source
Jun 18, 2018 in CVPR (Computer Vision and Pattern Recognition)
#1Huikai WuH-Index: 8
#2Shuai Zheng (eBay)H-Index: 19
Last. Kaiqi Huang (Center for Excellence in Education)H-Index: 54
view all 4 authors...
Image processing and pixel-wise dense prediction have been advanced by harnessing the capabilities of deep learning. One central issue of deep learning is the limited capacity to handle joint upsampling. We present a deep learning building block for joint upsampling, namely guided filtering layer. This layer aims at efficiently generating the high-resolution output given the corresponding low-resolution one and a high-resolution guidance map. The proposed layer is composed of a guided filter, wh...
Source
Low-dose computed tomography (LDCT) has attracted major attention in the medical imaging field, since CT-associated X-ray radiation carries health risks for patients. The reduction of the CT radiation dose, however, compromises the signal-to-noise ratio, which affects image quality and diagnostic performance. Recently, deep-learning-based algorithms have achieved promising results in LDCT denoising, especially convolutional neural network (CNN) and generative adversarial network (GAN) architectu...
Source
The continuous development and extensive use of computed tomography (CT) in medical practice has raised a public concern over the associated radiation dose to the patient. Reducing the radiation dose may lead to increased noise and artifacts, which can adversely affect the radiologists’ judgment and confidence. Hence, advanced image reconstruction from low-dose CT data is needed to improve the diagnostic performance, which is a challenging problem due to its ill-posed nature. Over the past years...
Source
Cited By2
Newest
#1Mamta Juneja (University Institute of Engineering and Technology, Panjab University)H-Index: 13
#2Saasha Joshi (University Institute of Engineering and Technology, Panjab University)
Last. Prashant Jindal (University Institute of Engineering and Technology, Panjab University)H-Index: 11
view all 7 authors...
Source
Cone Beam Computed Tomography(CBCT) is a now known method to conduct CT imaging. Especially, The Low Dose CT imaging is one of possible options to protect organs of patients when conducting CT imaging. Therefore Low Dose CT imaging can be an alternative instead of Standard dose CT imaging. However Low Dose CT imaging has a fundamental issue with noises within results compared to Standard Dose CT imaging. Currently, there are lots of attempts to erase the noises. Most of methods with artificial i...
#1Mayank PatwariH-Index: 2
#2Ralf GutjahrH-Index: 7
Last. Andreas MaierH-Index: 39
view all 4 authors...
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.