Deep auto-context convolutional neural networks for standard-dose PET image estimation from low-dose PET/MRI

Xiang, Lei; Qiao, Yu; Nie, Dong; An, Le; Lin, Weili; Wang, Qian; Shen, Dinggang

doi:10.1016/j.neucom.2017.06.048

Cited by 248 publications

(152 citation statements)

References 40 publications

Supporting

Mentioning

149

Contrasting

Unclassified

Order By: Relevance

“…There have been recent publications on the use of machine learning algorithms for classification and segmentation purposes (6)(7)(8)(9)(10). CNNs have been used to obtain standard-dose CT and PET images from low-dose data (11,12) and to enhance images by determining scatter correction parameters (13) and CNN-augmented emission-based attenuation correction (14) in PET. Recently, Gong et al used computersimulated PET images to pretrain a denoising CNN and then fine-tuned the CNN with patient data (15).…”

mentioning

confidence: 99%

Denoising of Scintillation Camera Images Using a Deep Convolutional Neural Network: A Monte Carlo Simulation Approach

2019

View full text Add to dashboard Cite

Scintillation camera images contain a large amount of Poisson noise. We have investigated whether noise can be removed in whole-body bone scans using convolutional neural networks (CNNs) trained with sets of noisy and noiseless images obtained by Monte Carlo simulation. Methods: Three CNNs were generated using 3 different sets of training images: simulated bone scan images, images of a cylindric phantom with hot and cold spots, and a mix of the first two. Each training set consisted of 40,000 noiseless and noisy image pairs. The CNNs were evaluated with simulated images of a cylindric phantom and simulated bone scan images. The mean squared error between filtered and true images was used as difference metric, and the coefficient of variation was used to estimate noise reduction. The CNNs were compared with gaussian and median filters. A clinical evaluation was performed in which the ability to detect metastases for CNNand gaussian-filtered bone scans with half the number of counts was compared with standard bone scans. Results: The best CNN reduced the coefficient of variation by, on average, 92%, and the best standard filter reduced the coefficient of variation by 88%. The best CNN gave a mean squared error that was on average 68% and 20% better than the best standard filters, for the cylindric and bone scan images, respectively. The best CNNs for the cylindric phantom and bone scans were the dedicated CNNs. No significant differences in the ability to detect metastases were found between standard, CNN-, and gaussian-filtered bone scans. Conclusion: Noise can be removed efficiently regardless of noise level with little or no resolution loss. The CNN filter enables reducing the scanning time by half and still obtaining good accuracy for bone metastasis assessment.

show abstract

mentioning

confidence: 99%

Denoising of Scintillation Camera Images Using a Deep Convolutional Neural Network: A Monte Carlo Simulation Approach

2019

View full text Add to dashboard Cite

show abstract

“…We compare our method with the following state-of-the-art multi-modality based PET estimation methods: (1) mapping based sparse representation method (m-SR) [2], (2) tripled dictionary learning method (t-DL) [4], (3) multi-level CCA method (m-CCA) [5], and (4) auto-context CNN method [3]. The averaged PSNR are given in Fig.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…By combining functional and morphologic information, PET/MRI system could increase diagnostic accuracy for various malignancies. Previous research also indicates the benefit brought by multi-modality data to PET image quality enhancement [1–3]. …”

Section: Introductionmentioning

confidence: 99%

Locality Adaptive Multi-modality GANs for High-Quality PET Image Synthesis

Wang

Zhou

Wang

et al. 2018

Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

Self Cite

View full text Add to dashboard Cite

Positron emission topography (PET) has been substantially used in recent years. To minimize the potential health risks caused by the tracer radiation inherent to PET scans, it is of great interest to synthesize the high-quality full-dose PET image from the low-dose one to reduce the radiation exposure while maintaining the image quality. In this paper, we propose a locality adaptive multi-modality generative adversarial networks model (LA-GANs) to synthesize the full-dose PET image from both the low-dose one and the accompanying T1-weighted MRI to incorporate anatomical information for better PET image synthesis. This paper has the following contributions. First, we propose a new mechanism to fuse multi-modality information in deep neural networks. Different from the traditional methods that treat each image modality as an input channel and apply the same kernel to convolute the whole image, we argue that the contributions of different modalities could vary at different image locations, and therefore a unified kernel for a whole image is not appropriate. To address this issue, we propose a method that is locality adaptive for multimodality fusion. Second, to learn this locality adaptive fusion, we utilize 1 × 1 × 1 kernel so that the number of additional parameters incurred by our method is kept minimum. This also naturally produces a fused image which acts as a pseudo input for the subsequent learning stages. Third, the proposed locality adaptive fusion mechanism is learned jointly with the PET image synthesis in an end-to-end trained 3D conditional GANs model developed by us. Our 3D GANs model generates high quality PET images by employing large-sized image patches and hierarchical features. Experimental results show that our method outperforms the traditional multi-modality fusion methods used in deep networks, as well as the state-of-the-art PET estimation approaches.

show abstract

“…handwriting, face, behavior...), recommender systems or image classification. Hundreds of papers have been published in the last years providing different types of deep neural networks in some selected areas [13], [14], particularly in medical image analysis [15], [16], where CNNs have become increasingly popular and widely applied.…”

Section: Introductionmentioning

confidence: 99%

Super-resolution of 3D Magnetic Resonance Images by Random Shifting and Convolutional Neural Networks

Thurnhofer‐Hemsi

López‐Rubio

Roé-Vellvé

et al. 2018

2018 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Enhancing resolution is a permanent goal in magnetic resonance (MR) imaging, in order to keep improving diagnostic capability and registration methods. Super-resolution (SR) techniques are applied at the postprocessing stage, and their use and development have progressively increased during the last years. In particular, example-based methods have been mostly proposed in recent state-of-the-art works. In this paper, a combination of a deep-learning SR system and a random shifting technique to improve the quality of MR images is proposed, implemented and tested. The model was compared to four competitors: cubic spline interpolation, non-local means upsampling, low-rank total variation and a three-dimensional convolutional neural network trained with patches of HR brain images (SRCNN3D). The newly proposed method showed better results in Peak Signal-to-Noise Ratio, Structural Similarity index, and Bhattacharrya coefficient. Computation times were at the same level as those of these up-to-date methods. When applied to downsampled MR structural T1 images, the new method also yielded better qualitative results, both in the restored images and in the images of residuals.

show abstract

Deep auto-context convolutional neural networks for standard-dose PET image estimation from low-dose PET/MRI

Cited by 248 publications

References 40 publications

Denoising of Scintillation Camera Images Using a Deep Convolutional Neural Network: A Monte Carlo Simulation Approach

Denoising of Scintillation Camera Images Using a Deep Convolutional Neural Network: A Monte Carlo Simulation Approach

Locality Adaptive Multi-modality GANs for High-Quality PET Image Synthesis

Super-resolution of 3D Magnetic Resonance Images by Random Shifting and Convolutional Neural Networks

Contact Info

Product

Resources

About