Computed tomography super-resolution using convolutional neural networks

Yu, Hwanjo; Liu, Ding; Shi, Honghui; Yu, Hanchao; Wang, Zhangyang; Wang, Xinchao; Cross, Brent; Bramler, Matthew; Huang, Thomas S.

doi:10.1109/icip.2017.8297022

Cited by 72 publications

(51 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our first ablation experiment, we have eliminated all the enhancements in order to show the performance level of a baseline CNN on the CH data set. Since there are several SISR works [3], [6], [16], [18] based on the standard ESPCN model [19], we have eliminated the second convolutional block in the second ablation experiment, transforming our architecture into a standard ESPCN architecture. The performance drops from 0.9270 to 0.9236 in terms of SSIM and from 36.22 to 35.94 in terms of PSNR.…”

Section: Ablation Study Resultsmentioning

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

Section: Ablation Study Resultsmentioning

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

show abstract

“…Therefore, the low and variant resolution on the z-axis is another difficulty in nodule detection, especially for the small nodules. Many studies [57][58][59][60] have adopted the deep-learning-based superresolution approaches to address the problem in CT and MRI images. It is interesting to incorporate the super-resolution into the proposed nodule detection and classification framework.…”

Section: Discussion and Future Workmentioning

confidence: 99%

A Joint Detection and Recognition Approach to Lung Cancer Diagnosis From CT Images With Label Uncertainty

Liu

Chan

2020

IEEE Access

View full text Add to dashboard Cite

Automatic lung cancer diagnosis from computer tomography (CT) images requires the detection of nodule location as well as nodule malignancy prediction. This paper proposes a joint lung nodule detection and classification network for simultaneous lung nodule detection, segmentation and classification subject to possible label uncertainty in the training set. It operates in an end-to-end manner and provides detection and classification of nodules simultaneously together with a segmentation of the detected nodules. Both the nodule detection and classification subnetworks of the proposed joint network adopt a 3-D encoderdecoder architecture for better exploration of the 3-D data. Moreover, the classification subnetwork utilizes the features extracted from the detection subnetwork and multiscale nodule-specific features for boosting the classification performance. The former serves as valuable prior information for optimizing the more complicated 3D classification network directly to better distinguish suspicious nodules from other tissues compared with direct backpropagation from the decoder. Experimental results show that this co-training yields better performance on both tasks. The framework is validated on the LUNA16 and LIDC-IDRI datasets and a pseudo-label approach is proposed for addressing the label uncertainty problem due to inconsistent annotations/labels. Experimental results show that the proposed nodule detector outperforms the state-of-the-art algorithms and yields comparable performance as state-of-the-art nodule classification algorithms when classification alone is considered. Since our joint detection/recognition approach can directly detect nodules and classify its malignancy instead of performing the tasks separately, our approach is more practical for automatic cancer and nodules detection.

show abstract

“…Instead of constructing a high-quality image by the network itself, we incorporate residual learning strategy to capture high-frequency features that can help improve the quality of low-dose CT images. 12 The covariance of pixel level features will significantly influence the denoising performance. 11 Indeed, in our experiments the pure CNN-based model tends to produce blurry features.…”

Section: Methodsmentioning

confidence: 99%

Low-dose CT via deep CNN with skip connection and network-in-network

You

Yang

Zhang

et al. 2019

Developments in X-Ray Tomography XII

View full text Add to dashboard Cite

A major challenge in computed tomography (CT) is how to minimize patient radiation exposure without compromising image quality and diagnostic performance. The use of deep convolutional (Conv) neural networks for noise reduction in Low-Dose CT (LDCT) images has recently shown a great potential in this important application. In this paper, we present a highly efficient and effective neural network model for LDCT image noise reduction. Specifically, to capture local anatomical features we integrate Deep Convolutional Neural Networks (CNNs) and Skip connection layers for feature extraction. Also, we introduce parallelized 1 × 1 CNN, called Network in Network, to lower the dimensionality of the output from the previous layer, achieving faster computational speed at less feature loss. To optimize the performance of the network, we adopt a Wasserstein generative adversarial network (WGAN) framework. Quantitative and qualitative comparisons demonstrate that our proposed network model can produce images with lower noise and more structural details than state-of-the-art noise-reduction methods.The PSNRs, SSIMs, and RMSEs are listed in Table 1. For noise reduction, the performance metrics were significantly improved by our proposed method (DCSCN). This demonstrates that using residual learning steak artifacts and image noise can be largely removed, enhancing the image quality. In this pilot study, DCSCN achieved the best performance in terms of PSNR and SSIM, and preserved anatomical features the most faithfully. However, there still exits blurry effects as shown in Figs. 3 and 5. DCSWGAN obtained the second best results in term of SSIM. It is noted that our method DCSWGAN produced visually pleasant results with sharp edges. CONCLUSIONIn this work, we have proposed a CNN-based network with skip-connection and network in network to capture structural information and suppress image noise. First, both local and global features are cascaded through skip connections before passing to the reconstruction network. Then, multi-channels are introduced for the reconstruction network with different local receptive fields to optimize the reconstruction performance. Also, the network in network technique is applied to lower the computational complexity. Our results have suggested that the proposed method could be generalized to various medical image denoising problems but further efforts are needed for training, validation, testing, and optimization.

show abstract

Computed tomography super-resolution using convolutional neural networks

Cited by 72 publications

References 21 publications

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

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

A Joint Detection and Recognition Approach to Lung Cancer Diagnosis From CT Images With Label Uncertainty

Low-dose CT via deep CNN with skip connection and network-in-network

Contact Info

Product

Resources

About