X-Ray computed tomography (CT) is one of the most popular imaging modality in the medical image analysis for clinical application. Meanwhile, the potential risk of X-Ray radiation dose to patients has attracted the public attention. Over the past decades, extensive efforts have been made for developing low-dose CT. However, X-Ray radiation dose reduction may result in increased noise and artifacts, which can significantly compromise the image quality and deteriorate the diagnostic performance. Hence, restoring CT image from low-dose CT and improving the diagnostic performance is a challenging for the vast researchers and developers. In this paper, a method based on deep learning techniques is proposed for low-dose CT noise reduction. Our method integrates convolutional neural network (CNN) blocks, residual learning, exponential linear units (ELUs) into a deep learning framework. Especially, loss of structural similarity index (SSIM) is combines to the final objective function to improve the image quality. Differs from general deep learning based denoising method, our deep CNN blocks architecture learning noise directly from original low-dose CT images, then restores denoised CT image by subtracting the obtained noise image from the original low-dose CT. After training patch by patch, the proposed method attains promising performance compared to state of the art traditional methods (non-local means and Block-matching 3D) and representative deep learning methods (primary three layers convolutional neural networks and residual encoder-decoder convolutional neural network) in visual effects and quantitative measurements. Extensive experiments was implemented for how choosing the coefficients of overall loss function and the number of CNN blocks. The experimental results demonstrate that our noise reduction method is effective for low-dose CT and potential clinic application.
Spectral computed tomography (CT) has the capability to resolve the energy levels of incident photons, which is able to distinguish different material compositions. Nowadays, deep learning has generated widespread attention in CT imaging applications. In this paper, a method of material decomposition for spectral CT based on improved Fully Convolutional DenseNets (FC-DenseNets) was proposed. Spectral data were acquired by a photon-counting detector and reconstructed spectral CT images were used to construct a training dataset. Experimental results showed that the proposed method could effectively identify bone and different tissues in high noise levels. This work could establish guidelines for multi-material decomposition approaches with spectral CT.
This paper proposes an image segmentation algorithm with fully convolutional networks (FCN) in binocular imaging system under various circumstance. Image segmentation is perfectly solved by semantic segmentation. FCN classifies the pixels, so as to achieve the level of image semantic segmentation. Different from the classical convolutional neural networks (CNN), FCN uses convolution layers instead of the fully connected layers. So it can accept image of arbitrary size. In this paper, we combine the convolutional neural network and scale invariant feature matching to solve the problem of visual positioning under different scenarios. All high-resolution images are captured with our calibrated binocular imaging system and several groups of test data are collected to verify this method. The experimental results show that the binocular images are effectively segmented without over-segmentation. With these segmented images, feature matching via SURF method is implemented to obtain regional information for further image processing. The final positioning procedure shows that the results are acceptable in the range of 1.4∼1.6 m, the distance error is less than 10mm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.