Medical imagereconstruction is often an ill-posed inverse problem. In order to address such ill-posed inverse problems, prior knowledge of the sought after object property is usually incorporated by means of regulari...
详细信息
ISBN:
(纸本)9781510633926
Medical imagereconstruction is often an ill-posed inverse problem. In order to address such ill-posed inverse problems, prior knowledge of the sought after object property is usually incorporated by means of regularization. For example, sparsity-promoting regularization in a suitable transform domain is widely used to reconstruct images with diagnostic quality from noisy and/or incomplete medical data. However, sparsity-promoting regularization may not be able to comprehensively describe the actual prior information of the objects being imaged. Deep generative models, such as generative adversarial networks (GANs) have shown great promise in learning the underlying distribution of images. Prior distributions for images estimated using GANs have been employed as a means of regularization with impressive results in several linear inverse problems in computer vision that are also relevant to medical imaging. However, in practice, it can be difficult for a GAN to comprehensively describe prior distributions, which can potentially lead to a lack of fidelity between the reconstructed image and the observed data. Recently, an image-adaptive GAN-based reconstruction method (IAGAN) was proposed to guarantee stronger data consistency by adapting the trained generative model parameters to the observed measurements. In this work, for the first time, we apply the IAGAN method to reconstruct images from undersampled magnetic resonance imaging (MRI) measurements. A state-of-the-art GAN model called Progressive Growing of GANs (ProGAN) was trained on a large number of ground truth images from the NYU fastMRI dataset, and the learned generator was subsequently employed in the IAGAN framework to reconstruct high fidelity images from retrospectively undersampled experimental k-space data in the validation dataset. It is demonstrated that by use of the GAN-based reconstruction method with noisy and/or incomplete measurements, we can potentially recover fine structures in the object th
Background Fingerprint biometrics play an essential role in authentication. It remains a challenge to match fingerprints with the minutiae or ridges missing. Many fingerprints failed to match their targets due to the ...
详细信息
Background Fingerprint biometrics play an essential role in authentication. It remains a challenge to match fingerprints with the minutiae or ridges missing. Many fingerprints failed to match their targets due to the incompleteness. Result In this work, we modeled the fingerprints with Bezier curves and proposed a novel algorithm to detect and restore fragmented ridges in incomplete fingerprints. In the proposed model, the Bezier curves' control points represent the fingerprint fragments, reducing the data size by 89% compared to image representations. The representation is lossless as the restoration from the control points fully recovering the image. Our algorithm can effectively restore incomplete fingerprints. In the SFinGe synthetic dataset, the fingerprint image matching score increased by an average of 39.54%, the ERR (equal error rate) is 4.59%, and the FMR1000 (false match rate) is 2.83%, these are lower than 6.56% (ERR) and 5.93% (FMR1000) before restoration. In FVC2004 DB1 real fingerprint dataset, the average matching score increased by 13.22%. The ERR reduced from 8.46% before restoration to 7.23%, and the FMR1000 reduced from 20.58 to 18.01%. Moreover, We assessed the proposed algorithm against FDP-M-net and U-finger in SFinGe synthetic dataset, where FDP-M-net and U-finger are both convolutional neural network models. The results show that the average match score improvement ratio of FDP-M-net is 1.39%, U-finger is 14.62%, both of which are lower than 39.54%, yielded by our algorithm. Conclusions Experimental results show that the proposed algorithm can successfully repair and reconstruct ridges in single or multiple damaged regions of incomplete fingerprint images, and hence improve the accuracy of fingerprint matching.
The approach to solving inverse problems of source identification in acoustics is proposed based on fuzzy relational calculus. The compositional rule of inference connects the real and observed fuzzy acoustic image us...
详细信息
ISBN:
(纸本)9783030542153;9783030542146
The approach to solving inverse problems of source identification in acoustics is proposed based on fuzzy relational calculus. The compositional rule of inference connects the real and observed fuzzy acoustic image using the relationship matrix, which reflects the degree of completeness of the microphone array measurement data. The fuzzy model of the acoustic field is based on 3D membership functions, for which the degree of membership decreases in proportion to the square of the distance to the source. The problem of reconstructing the acoustic field is formulated as the problem of inverse logical inference. The method for reconstructing the acoustic field fromincompletedata is proposed based on solving fuzzy relational equations. The problem consists in finding such a number of sound sources, their locations and powers, which minimize the difference between the model and observed fuzzy acoustic image. The solutions of the equation system represent the variants of the acoustic field reconstruction in the form of the main acoustic surface and a set of secondary acoustic surfaces. The main acoustic surface is generated by the least number of sources. The set of secondary acoustic surfaces represents the variants of the sound field reconstruction generated by the upper solutions for the number of sources. Since the sources distribution is completely determined by the properties of the solution set, the proposed approach allows avoiding the generation and selection of candidate sources, that provides simplification of the reconstruction process and reduction of time costs. The genetic and neural algorithm provides accurate and fast reconstruction of the acoustic field for an unknown number of sources and their configuration.
Dynamic imaging (such as computed tomography (CT) perfusion, dynamic CT angiography, dynamic positron emission tomography, four-dimensional CT, etc.) is widely used in the clinic. The multiple-scan mechanism of dynami...
详细信息
ISBN:
(纸本)9781510633926
Dynamic imaging (such as computed tomography (CT) perfusion, dynamic CT angiography, dynamic positron emission tomography, four-dimensional CT, etc.) is widely used in the clinic. The multiple-scan mechanism of dynamic imaging results in greatly increased radiation dose and prolonged acquisition time. To deal with these problems, low-mAs or sparse-view protocols are usually adopted, which lead to noisy or incompletedata for each frame. To obtain high-quality images from the corrupted data, a popular strategy is to incorporate the composite image that reconstructed using the full dataset into the iterative reconstruction procedure. Previous studies have tried to enforce each frame to approach the composite image in each iteration, which, however, introduces mixed temporal information into each frame. In this paper, we propose an average consistency (AC) model for dynamic CT imagereconstruction. The core idea of AC is to enforce the average of all frames to approach the composite image in each iteration, which preserves image edges and noise characteristics while avoids the invasion of mixed temporal information. Experiment on a dynamic phantom and a patient for CT perfusion imaging shows that the proposed method obtains the best qualitative and quantitative results. We conclude that the AC model is a general framework and a superior way of using the composite image for dynamic CT reconstruction.
Dual-panel PET scanners have many advantages in dedicated breast imaging and on-board imaging applications since the compact scanners can be combined with other imaging and treatment modalities. The major challenges o...
详细信息
3D object instance reconstructionfrom a cluttered 2D scene image is an ill-posed problem. The main challenge is posed by the lack of geometric information in color images and heavy occlusions that lead to incomplete ...
详细信息
ISBN:
(纸本)9781728193601
3D object instance reconstructionfrom a cluttered 2D scene image is an ill-posed problem. The main challenge is posed by the lack of geometric information in color images and heavy occlusions that lead to incomplete shape details. To deal with this problem, existing works on 3D instance reconstruction directly learn the mapping between the intensity image and the corresponding 3D volume model. Different from these works, we propose to explicitly incorporate 2.5D geometric cues, such as the surface normal, relative depth, and height, while generating full 3D shapes from 2D images. With an intermediate step focused on estimating these 2.5D geometric features, we propose a novel convolutional neural network design that progressively moves from 2D to full 3D estimation. Our model automatically generates instance-specific surface normal maps, relative depth, and height that are compactly encoded within our network design and consequently used to improve the 3D instance reconstruction. Our experimental results on the large-scale synthetic SUNCG dataset and the real-world NYU depth v2 dataset demonstrate the effectiveness of the proposed approach where it beats the state-of-the-art Factored3D network [15].
The principles outlined by compressed sensing can permit a sensor to collect reduced amount of data and still reconstruct an exact outcome. This can for example be used to generate super-resolution sparse range-Dopple...
详细信息
ISBN:
(数字)9781728168135
ISBN:
(纸本)9781728168135
The principles outlined by compressed sensing can permit a sensor to collect reduced amount of data and still reconstruct an exact outcome. This can for example be used to generate super-resolution sparse range-Doppler radar images while emitting a reduced number of pulses within a coherent processing interval. In this paper, we investigate the use of neural networks as a mean to solve the sparse reconstruction problem with specific emphasis towards range-Doppler images. The neural networks are trained to generate a sparse Doppler profile fromincomplete time domain data in line with traditional sparse L-1-norm minimization. We show that this approach is viable through fully connected feed forwarding networks and the results closely mimic sparse recovered range-Doppler maps.
We investigate the problem of training neural networks fromincompleteimages without replacing missing values. For this purpose, we first represent an image as a graph, in which missing pixels are entirely ignored. T...
详细信息
ISBN:
(纸本)9783030638320;9783030638337
We investigate the problem of training neural networks fromincompleteimages without replacing missing values. For this purpose, we first represent an image as a graph, in which missing pixels are entirely ignored. The graph image representation is processed using a spatial graph convolutional network (SGCN) - a type of graph convolutional networks, which is a proper generalization of classical CNNs operating on images. On one hand, our approach avoids the problem of missing data imputation while, on the other hand, there is a natural correspondence between CNNs and SGCN. Experiments confirm that our approach performs better than analogical CNNs with the imputation of missing values on typical classification and reconstruction tasks.
Rapid advancement and active research in computer vision applications and 3D imaging have made a high demand for efficient depth image estimation techniques. The depth image acquisition, however, is typically challeng...
详细信息
CT imagereconstructionfromincompletedata, such as sparse views and limited angle reconstruction, is an important and challenging problem in medical imaging. This work proposes a new deep convolutional neural netwo...
详细信息
ISBN:
(纸本)9781479981311
CT imagereconstructionfromincompletedata, such as sparse views and limited angle reconstruction, is an important and challenging problem in medical imaging. This work proposes a new deep convolutional neural network (CNN), called JSR-Net, that jointly reconstructs CT images and their associated Radon domain projections. JSR-Net combines the traditional model based approach with deep architecture design of deep learning. A hybrid loss function is adopted to improve the performance of the JSR-Net making it more effective in protecting important image structures. Numerical experiments demonstrate that JSR-Net outperforms some latest model based reconstruction methods, as well as a recently proposed deep model.
暂无评论