Search

Radiation therapy is the standard treatment for early stage Nasopharyngeal cancer (NPC). Thus, accurate delineation of target volumes at risk in NPC is important. While manual delineation is time‐consuming and labour‐intensive process and also leads to significant inter‐ and intra‐practitioner variability. Thus, computer‐aided segmentation algorithm is required. However, segmentation task is not trivial due to large variations (e.g., shape and size) of nasopharynx structure across subjects. Moreover, extreme foreground and background class imbalance in NPC segmentation remains challenge. In this paper, we propose a threedimensional densely connected convolutional neural network with multi‐scale feature pyramids for NPC segmentation. We adapt the densely connected convolutional block into a new structure via adding feature pyramids. The concatenated pyramid feature carries multi‐scale and hierarchical semantic information which is effective for segmenting different size of tumors and perceiving hierarchical context information. To address the foreground and background imbalance problem, we propose an enhanced version of focal loss. It prevents the large number of negative voxels far from boundaries from overwhelming the segmentation algorithm. We validated the proposed method on 120 clinical subjects. Experimental results demonstrate that our approach out‐performed state‐of‐the‐art methods and human experts.

Intelligent network is crucial in the building of telecom networks because it utilizes artificial intelligent technologies to improve the performance. Salient object detection has increasingly attracted interest from intelligent network research since estimating human attention to objects is a crucial step in various surveillance applications. However, the computational-consuming and memory-consuming detection model is still less effective when it is deployed only either on the cloud or on the edge. In this article, we propose a specially-designed cloud-edge distributed framework for salient object detection based on the intelligent network. This framework can overcome the difficulty to transmit massive data in the cloud-only deployment scheme, as well as the difficulty to analyze massive data in the edge-only deployment scheme. However, the traditional cloud-edge distributed schemes are unsuitable to salient object detection task because of two challenges: 1) balance between the within-semantic knowledge and cross-semantic knowledge for the model training in different servers; 2) contradiction between extracting the semantic knowledge with global contextual information and local detailed information. To tackle the first challenge, our framework enables a hierarchical information allocation strategy in the cloud. It can prompt the salient object detection model in the edge to learn more from the similar scenes or semantics with where the edge server is located, while preserving the generalization ability of the model in the different scenes. To address the second challenge, our framework proposes a novel pyramidal deep learning model. It can effectively capture the global contextual features of the salient object, while preserving its local detailed features. The extensive experiments performed on six commonly- used public datasets can demonstrate the effectiveness of our framework and its superiority to 11 state-of-the-art approaches.

Fast and accurate MRI image reconstruction from undersampled data is crucial in clinical practice. Deep learning based reconstruction methods have shown promising advances in recent years. However, recovering fine details from undersampled data is still challenging. In this paper, we introduce a novel deep learning based method, Pyramid Convolutional RNN (PC-RNN), to reconstruct images from multiple scales. Based on the formulation of MRI reconstruction as an inverse problem, we design the PC-RNN model with three convolutional RNN (ConvRNN) modules to iteratively learn the features in multiple scales. Each ConvRNN module reconstructs images at different scales and the reconstructed images are combined by a final CNN module in a pyramid fashion. The multi-scale ConvRNN modules learn a coarse-to-fine image reconstruction. Unlike other common reconstruction methods for parallel imaging, PC-RNN does not employ coil sensitive maps for multi-coil data and directly model the multiple coils as multi-channel inputs. The coil compression technique is applied to standardize data with various coil numbers, leading to more efficient training. We evaluate our model on the fastMRI knee and brain datasets and the results show that the proposed model outperforms other methods and can recover more details. The proposed method is one of the winner solutions in the 2019 fastMRI competition., Comment: Copyright\copyright 2022 IEEE. Personal use of this material is permitted. However, permission to use this material for any other purposes must be obtained from the IEEE by sending a request to pubs-permissions@ieee.org

By taking the 16 cities in Anhui Province for evaluation, the main influencing factors and indicator system for integrated urban-rural development in the new era were explored, to build the BCC model, cross-efficiency model, and game cross-efficiency model of DEA. The above models were applied for empirical analysis and comparative study on the rural revitalization and urban-rural integration efficiency in Anhui Province, to summarize the conclusions efficiency and give suggestions based on the above calculations.

Multi-modal medical image registration takes an essential role in image-based clinical diagnosis and surgical planning. It is not trivial due to appearance variations across different modalities. Rigidly aligning two images is used to register rigid body structure, and it is also usually the first step for deformable registration with a large discrepancy. In the field of computer vision, one well-established method for image alignment is to find corresponding points from two images, and image alignment is based on identified corresponding points. Our method lies in this category. Feature representation is crucial in finding corresponding points. However, conventional feature representation like SIFT does not take multi-modal information into account, and thus, it fails. In this paper, we propose a Convolution Neural Network Feature-based Registration (CNNFR) method for aligning the multi-modal medical image. The important component in this method is learning keypoint descriptors using contrastive metric learning, which minimizes the difference between two feature representations from two corresponding points and maximizes difference of two feature representation from two distant points. Also, a transfer learning-based CNNRF (TrCNNRF) is proposed to improve the generalization learning performance when the training data are insufficient. Experimental results demonstrate that the proposed methods can achieve superior performance regarding both accuracy and robustness, which can be used to rigidly register multi-modal images and provide an initial estimation for non-rigid registration in clinical practices.

Accurate estimation of shape thickness from medical images is crucial in clinical applications. For example, the thickness of myocardium is one of the key to cardiac disease diagnosis. While mathematical models are available to obtain accurate dense thickness estimation, they suffer from heavy computational overhead due to iterative solvers. To this end, we propose novel methods for dense thickness estimation, including a fast solver that estimates thickness from binary annular shapes and an end-to-end network that estimates thickness directly from raw cardiac images. We test the proposed models on three cardiac datasets and one synthetic dataset, achieving impressive results and generalizability on all. Thickness estimation is performed without iterative solvers or manual correction, which is \(100\times \) faster than the mathematical model. We also analyze thickness patterns on different cardiac pathologies with a standard clinical model and the results demonstrate the potential clinical value of our method for thickness based cardiac disease diagnosis.

Image registration plays an important role in medical image analysis. Conventional optimization based methods provide an accurate estimation due to the iterative process at the cost of expensive computation. Deep learning methods such as learn-to-map are much faster but either iterative or coarse-to-fine approach is required to improve accuracy for handling large motions. In this work, we proposed to learn a registration optimizer via a multi-scale neural ODE model. The inference consists of iterative gradient updates similar to a conventional gradient descent optimizer but in a much faster way, because the neural ODE learns from the training data to adapt the gradient efficiently at each iteration. Furthermore, we proposed to learn a modal-independent similarity metric to address image appearance variations across different image contrasts. We performed evaluations through extensive experiments in the context of multi-contrast 3D MR images from both public and private data sources and demonstrate the superior performance of our proposed methods.

In this paper, influential parameters on the hydraulic fracturing processes in porous media were investigated. Besides, the simultaneous stimulation of solids, fluids and fractures geomechanical equations were numerically analyzed as a developed 3D model. To do this, the Abacus software was used as a multi-objective program to solve the physical-mechanical symmetry law governing equations, according to the finite element method. Two different layers, A (3104&ndash, 2984 m) and B (4216&ndash, 4326 m), are considered in the model. According to the result of this study, the maximum fracture opening length in the connection of the wall surface is 10 and 9 mm for layer B and layer A, respectively. Moreover, the internal fracture fluid pressure for layer B and layer A is 65 and 53 Mpa. It is indicated that fracture fluid pressure reduced with the increase in fracture propagation length. Consequently, the results of this study would be of benefit for petroleum industries to consider several crucial geomechanical characteristics in hydraulic fractures simultaneously as a developed numerical model for different formation layers to compare a comprehensive analysis between each layer.

Motion estimation of cardiac MRI videos is crucial for the evaluation of human heart anatomy and function. Recent researches show promising results with deep learning-based methods. In clinical deployment, however, they suffer dramatic performance drops due to mismatched distributions between training and testing datasets, commonly encountered in the clinical environment. On the other hand, it is arguably impossible to collect all representative datasets and to train a universal tracker before deployment. In this context, we proposed a novel fast online adaptive learning (FOAL) framework: an online gradient descent based optimizer that is optimized by a meta-learner. The meta-learner enables the online optimizer to perform a fast and robust adaptation. We evaluated our method through extensive experiments on two public clinical datasets. The results showed the superior performance of FOAL in accuracy compared to the offline-trained tracking method. On average, the FOAL took only $0.4$ second per video for online optimization., Comment: Accepted by CVPR 2020

Magnetic resonance (MR) imaging is widely used in clinical scenarios, while the long acquisition time is still one of its major limitations. An efficient way to accelerate the imaging process is to subsample the k-space, where MR signal is physically acquired, and then estimate the fully-sampled MR image from subsampled signal with a learned reconstruction model. In this work, we are inspired from the idea of neural network pruning and propose a novel strategy to learn the k-space subsampling pattern and the reconstruction model alternately in a data-driven fashion. More specifically, in each iteration of learning, we first greedily eliminate a few phases that are considered less important in the k-space according to their assigned weights, and then fine-tune the reconstruction model. In our pilot study, experiments demonstrated the robustness and superiority of our proposed method in both single- and multi-modal MRI settings.

Magnetic Resonance Imaging (MRI) is one of the most commonly used modalities in medical imaging, and one of the main limitations is its slow scanning and reconstruction speed. Recently, deep learning used for compressed sensing (CS) methods have been proposed to accelerate the acquisition by undersampling in the K-space and reconstruct images with neural networks. However, there are still some challenges remained: First, directly training networks based on L1/L2 distance to the target fully sampled images may lead to fuzzy reconstruction images because L1/L2 loss only enforces the overall image or patch similarity, but does not consider the local details such as anatomical sharpness. Second, Generative Adversarial Networks (GAN) can partially solve this problem. The undersampling image gets the latent space through the encoder, and the image is reconstructed by the decoder based on GAN loss, but it may generate unrealistic details by lacking of constraints in K-space domain. Third, most of the networks after training are fixed and have limited adaptation capability in the inference time, and the patient-specific information cannot be effectively used. To resolve these challenges, we proposed a new compressed sensing GAN reconstruction method, and there are two main contributions: (1) We proposed a encoder-decoder structure, which guided GAN optimization strategy data-consistency in latent space to improve the reconstruction quality such as preserving more local details and improving the anatomical sharpness while constraining GAN to follow the data distribution in the K-space to prevent the unrealistic details. (2) An online update strategy is used to find the best representation in the latent space for the underlying patient, and the reconstruct result can be further improved by incorporating the patient-specific information. Extensive experimental results show the effectiveness of our method.

Cardiac motion estimation is critical to the assessment of cardiac function. Myocardium feature tracking (FT) can directly estimate cardiac motion from cine MRI, which requires no special scanning procedure. However, current deep learning-based FT methods may result in unrealistic myocardium shapes since the learning is solely guided by image intensities without considering anatomy. On the other hand, motion estimation through learning is challenging because ground-truth motion fields are almost impossible to obtain. In this study, we propose a novel Anatomy-Aware Tracker (AATracker) for cardiac motion estimation that preserves anatomy by weak supervision. A convolutional variational autoencoder (VAE) is trained to encapsulate realistic myocardium shapes. A baseline dense motion tracker is trained to approximate the motion fields and then refined to estimate anatomy-aware motion fields under the weak supervision from the VAE. We evaluate the proposed method on long-axis cardiac cine MRI, which has more complex myocardium appearances and motions than short-axis. Compared with other methods, AATracker significantly improves the tracking performance and provides visually more realistic tracking results, demonstrating the effectiveness of the proposed weakly-supervision scheme in cardiac motion estimation.

We propose to formulate MRI image reconstruction as an optimization problem and model the optimization trajectory as a dynamic process using ordinary differential equations (ODEs). We model the dynamics in ODE with a neural network and solve the desired ODE with the off-the-shelf (fixed) solver to obtain reconstructed images. We extend this model and incorporate the knowledge of off-the-shelf ODE solvers into the network design (learned solvers). We investigate several models based on three ODE solvers and compare models with fixed solvers and learned solvers. Our models achieve better reconstruction results and are more parameter efficient than other popular methods such as UNet and cascaded CNN. We introduce a new way of tackling the MRI reconstruction problem by modeling the continuous optimization dynamics using neural ODEs.

The research on land circulation problems are put forward and a whole set of survey methods for land transfer is designed in this paper. By studying the main factors that influence the willingness of land transfer, combining with the investigation of land transfer intention, logistic regression analysis theory is used to analyze the land transfer intention and relevant influencing factors. The research shows that the satisfaction degree of land income, land circulation patterns are clear or not and the intention of land transfer are the intrinsic factors to promote the land transfer intention. The purchase of houses in the city, the demand for medical services in the city and the willingness of the land transfer are the external factors that promote the land circulation. Finally, several main conclusions and suggestions on land circulation are given.

Multimodal image registration is a vital initial step in several medical image applications for providing complementary information from different data modalities. Since images with different modalities do not exhibit the same characteristics, finding their accurate correspondences remains a challenge. For convolutional multimodal registration methods, two components are quite significant: descriptive image feature as well as the suited similarity metric. However, these two components are often custom-designed and are infeasible to the high diversity of tissue appearance across modalities. In this paper, we translate image registration into a decision-making problem, where registration is achieved via an artificial agent trained by asynchronous reinforcement learning. More specifically, convolutional long-short-term-memory is incorporated after stacked convolutional layers in this method to extract spatial-temporal image features and learn the similarity metric implicitly. A customized reward function driven by landmark error is advocated to guide the agent to the correct registration direction. A Monte Carlo rollout strategy is also leveraged to perform as a look-ahead inference in the testing stage, to increase registration accuracy further. Experiments on paired CT and MR images of patients diagnosed as nasopharyngeal carcinoma demonstrate that our method achieves state-of-the-art performance in medical image registration.