Super-resolution reconstruction of single anisotropic 3D MR images using residual convolutional neural network

Du, Jinglong; He, Zhongshi; Wang, Lulu; Gholipour, Ali; Zhou, Zexun; Chen, Dingding; Jia, Yuanyuan

doi:10.1016/j.neucom.2018.10.102

Cited by 78 publications

(72 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Table 3, it can be observed that our proposed method achieves state-of-the-art performance. Specifically, in clinical data, our model outperform state-of-the-art RLSR[11] by 0.20dB (PSNR) and 0.0021 (SSIM). For the simulation dataset, our model is 0.06dB higher than RLSR in the PSNR value and the same as RLSR in the SSIM metric.…”

mentioning

confidence: 88%

“…The residual connection is proved to have a positive effect on feature flow [11]. We explore the effect of the residual mechanism in our model, including local residuals and global residuals.…”

Section: Effect Of Residual Connectionmentioning

confidence: 99%

“…Considering this problem, Pham et al [10] subsequently proposed a deep 3D residual network for brain MR image SR which achieved better performance than their previous method [9]. Du et al [11] further optimized the deep network structure by adopting both long and short skip connections, which alleviated the vanishing gradient problem of deep networks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Gating Feature Dense Network for Single Anisotropic Mr Image Super-Resolution

Wang

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

High resolution (HR) magnetic resonance (MR) images are crucial for medical diagnosis. However, in practice, low resolution MR images are often acquired due to hardware limitation. In this work, we propose a gating feature dense network to reconstruct HR MR images from low resolution acquisitions, where we use local residual dense block (LRDB) as the backbone. We propose gating mechanism, which includes absorption gate and release gate, to adaptively introduce the informative features of previous LRDBs to current LRDB to solve the problem of insufficient features sharing. The absorption gate can fuse the output feature of LRDBs with adaptive weights, which allows the model to adaptively learn the effects of different LRDBs for MR image superresolution (SR). Experimental results show that our proposed method achieves a new state-of-the-art quantitative and visual performance in anisotropic MR image SR.

show abstract

mentioning

confidence: 88%

Section: Effect Of Residual Connectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Gating Feature Dense Network for Single Anisotropic Mr Image Super-Resolution

Wang

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some works [1], [3], [5], [6], [9]- [11], [14]- [16], [18] focused on 2D upsampling, i.e. on increasing the width and height of CT/MRI slices, while other works [2], [4], [8], [12] focused on 3D upsampling, i.e.…”

Section: Related Workmentioning

confidence: 99%

Convolutional Neural Networks With Intermediate Loss for 3D Super-Resolution of CT and MRI Scans

Ionescu

Verga

2020

IEEE Access

View full text Add to dashboard Cite

Computed Tomography (CT) scanners that are commonly-used in hospitals and medical centers nowadays produce low-resolution images, e.g. one voxel in the image corresponds to at most onecubic millimeter of tissue. In order to accurately segment tumors and make treatment plans, radiologists and oncologists need CT scans of higher resolution. The same problem appears in Magnetic Resonance Imaging (MRI). In this paper, we propose an approach for the single-image super-resolution of 3D CT or MRI scans. Our method is based on deep convolutional neural networks (CNNs) composed of 10 convolutional layers and an intermediate upscaling layer that is placed after the first 6 convolutional layers. Our first CNN, which increases the resolution on two axes (width and height), is followed by a second CNN, which increases the resolution on the third axis (depth). Different from other methods, we compute the loss with respect to the ground-truth high-resolution image right after the upscaling layer, in addition to computing the loss after the last convolutional layer. The intermediate loss forces our network to produce a better output, closer to the ground-truth. A widely-used approach to obtain sharp results is to add Gaussian blur using a fixed standard deviation. In order to avoid overfitting to a fixed standard deviation, we apply Gaussian smoothing with various standard deviations, unlike other approaches. We evaluate the proposed method in the context of 2D and 3D super-resolution of CT and MRI scans from two databases, comparing it to related works from the literature and baselines based on various interpolation schemes, using 2× and 4× scaling factors. The empirical study shows that our approach attains superior results to all other methods. Moreover, our subjective image quality assessment by human observers reveals that both doctors and regular annotators chose our method in favor of Lanczos interpolation in 97.55% cases for an upscaling factor of 2× and in 96.69% cases for an upscaling factor of 4×. In order to allow others to reproduce our state-of-the-art results, we provide our code as open source at https://github.com/lilygeorgescu/3d-super-res-cnn. INDEX TERMSConvolutional neural networks, single-image super-resolution, CT images, MRI images, medical image super-resolution.

show abstract

“…Another image enhancement technique is super-resolution. Most approaches rely on pairs of high-and low-resolution images of a single modality to learn the low-to high-resolution mapping [59][60][61][62][63][64]. Others do not use external training data.…”

Section: Signal Enhancementmentioning

confidence: 99%

Deep learning for brain disorders: from data processing to disease treatment

Burgos

Bottani

Faouzi

et al. 2020

Briefings in Bioinformatics

View full text Add to dashboard Cite

In order to reach precision medicine and improve patients’ quality of life, machine learning is increasingly used in medicine. Brain disorders are often complex and heterogeneous, and several modalities such as demographic, clinical, imaging, genetics and environmental data have been studied to improve their understanding. Deep learning, a subpart of machine learning, provides complex algorithms that can learn from such various data. It has become state of the art in numerous fields, including computer vision and natural language processing, and is also growingly applied in medicine. In this article, we review the use of deep learning for brain disorders. More specifically, we identify the main applications, the concerned disorders and the types of architectures and data used. Finally, we provide guidelines to bridge the gap between research studies and clinical routine.

show abstract

Super-resolution reconstruction of single anisotropic 3D MR images using residual convolutional neural network

Cited by 78 publications

References 12 publications

Gating Feature Dense Network for Single Anisotropic Mr Image Super-Resolution

Gating Feature Dense Network for Single Anisotropic Mr Image Super-Resolution

Convolutional Neural Networks With Intermediate Loss for 3D Super-Resolution of CT and MRI Scans

Deep learning for brain disorders: from data processing to disease treatment

Contact Info

Product

Resources

About