Denoising of Dynamic Sinogram by Image Guided Filtering for Positron Emission Tomography

Hashimoto, Fumio; Ohba, Hideki; Ote, Kibo; Tsukada, Hideo

doi:10.1109/trpms.2018.2869936

Cited by 24 publications

(21 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the computer simulation, the DIP method provided a higher PSNR than the other algorithms [17], [29], regardless of the time frame. The SSIM can evaluate the structural similarity, which cannot be evaluated by the PSNR [44].…”

Section: Discussionmentioning

confidence: 91%

“…We compared the DIP method with 3D GF, NLM, and the image-based dynamic IGF [17]. For GF, the full width at half maximum was set to 1.0 voxel.…”

Section: A Computer Simulationmentioning

confidence: 99%

“…Furthermore, Dutta et al applied a non-local means (NLM) filter [14] to dynamic PET images [15]. In addition, some post-denoising methods, such as HYPR processing [16], image guided filtering (IGF) [17], and wavelet denoising [18] have been developed. All exhibit a higher level of performance than the GF.…”

Section: Introductionmentioning

confidence: 99%

“…Our proposed method is regarded as being a type of ''unsupervised'' learning because it does not require an ideal label. Compared with the 3D NLM filter [29], [30] and IGF [17], our proposed method exhibited superior performance visually and quantitatively when applied to both a computer simulation and a real data obtained from a living monkey brain using 18 F-fluoro-2-deoxy-D-glucose ( 18 F-FDG).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Dynamic PET Image Denoising Using Deep Convolutional Neural Networks Without Prior Training Datasets

et al. 2019

Self Cite

View full text Add to dashboard Cite

Deep learning has attracted growing interest for application to medical imaging, such as positron emission tomography (PET), due to its excellent performance. Convolutional neural networks (CNNs), a facet of deep learning requires large training-image datasets. This presents a challenge in a clinical setting because it is difficult to prepare large, high-quality patient-related datasets. Recently, the deep image prior (DIP) approach has been devised, based on the fact that CNN structures have the intrinsic ability to solve inverse problems such as denoising without pre-training and do not require the preparation of training datasets. Herein, we proposed the dynamic PET image denoising using a DIP approach, with the PET data itself being used to reduce the statistical image noise. Static PET data were acquired for input to the network, with the dynamic PET images being handled as training labels, while the denoised dynamic PET images were represented by the network output. We applied the proposed DIP method to computer simulations and also to real data acquired from a living monkey brain with 18 F-fluoro-2-deoxy-D-glucose ( 18 F-FDG). As a simulation result, our DIP method produced less noisy and more accurate dynamic images than the other algorithms. Moreover, using real data, the DIP method was found to perform better than other types of post-denoising method in terms of contrast-to-noise ratio, and also maintain the contrast-to-noise ratio when resampling the list data to 1/5 and 1/10 of the original size, demonstrating that the DIP method could be applied to low-dose PET imaging. These results indicated that the proposed DIP method provides a promising means of post-denoising for dynamic PET images.INDEX TERMS Convolutional neural networks, deep image prior, deep learning, denoising, dynamic positron emission tomography.

show abstract

Section: Discussionmentioning

confidence: 91%

“…We compared the DIP method with 3D GF, NLM, and the image-based dynamic IGF [17]. For GF, the full width at half maximum was set to 1.0 voxel.…”

Section: A Computer Simulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic PET Image Denoising Using Deep Convolutional Neural Networks Without Prior Training Datasets

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…And Adam iteratively updates the neural network weights by calculating the first-order moment estimation and the second-order moment estimation of the gradient. The adaptive learning rate is calculated for each parameter to solve the problem of high-intensity noise or sparse gradient [ 34 ]. The basic steps of the Adam optimization algorithm are as follows:…”

Section: Network Parameter Settingmentioning

confidence: 99%

A Multifeature Extraction Method Using Deep Residual Network for MR Image Denoising

Yao

2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

In order to improve the resolution of magnetic resonance (MR) image and reduce the interference of noise, a multifeature extraction denoising algorithm based on a deep residual network is proposed. First, the feature extraction layer is constructed by combining three different sizes of convolution kernels, which are used to obtain multiple shallow features for fusion and increase the network’s multiscale perception ability. Then, it combines batch normalization and residual learning technology to accelerate and optimize the deep network, while solving the problem of internal covariate transfer in deep learning. Finally, the joint loss function is defined by combining the perceptual loss and the traditional mean square error loss. When the network is trained, it can not only be compared at the pixel level but also be learned at a higher level of semantic features to generate a clearer target image. Based on the MATLAB simulation platform, the TCGA-GBM and CH-GBM datasets are used to experimentally demonstrate the proposed algorithm. The results show that when the image size is set to 190 × 215 and the optimization algorithm is Adam, the performance of the proposed algorithm is the best, and its denoising effect is significantly better than other comparison algorithms. Especially under high-intensity noise levels, the denoising advantage is more prominent.

show abstract

Intelligent Enhancement for Low-Light Earth Remote Sensing Based on Physical Process Modeling

Jiuzhe,

Zhi,

Yun

et al. 2024

Springer Proceedings in Physics

View full text Add to dashboard Cite

Denoising of Dynamic Sinogram by Image Guided Filtering for Positron Emission Tomography

Cited by 24 publications

References 33 publications

Dynamic PET Image Denoising Using Deep Convolutional Neural Networks Without Prior Training Datasets

Dynamic PET Image Denoising Using Deep Convolutional Neural Networks Without Prior Training Datasets

A Multifeature Extraction Method Using Deep Residual Network for MR Image Denoising

Intelligent Enhancement for Low-Light Earth Remote Sensing Based on Physical Process Modeling

Contact Info

Product

Resources

About