Objective: Non-invasive fetal electrocardiography has the potential to provide vital information for evaluating the health status of the fetus. However, the low signal-to-noise ratio of the fetal electrocardiogram (EC...
详细信息
Objective: Non-invasive fetal electrocardiography has the potential to provide vital information for evaluating the health status of the fetus. However, the low signal-to-noise ratio of the fetal electrocardiogram (ECG) impedes the applicability of the method in clinical practice. Quality improvement of the fetal ECG is of great importance for providing accurate information to enable support in medical decision-making. In this paper we propose the use of artificial intelligence for the task of one-channel fetal ECG enhancement as a post-processing step after maternal ECG suppression. Approach: We propose a deep fully convolutional encoder-decoder framework, learning end-to-end mappings from noise-contaminated fetal ECGs to clean ones. Symmetric skip-layer connections are used between corresponding convolutional and transposed convolutional layers to help recover the signal details. Main results: Experiments on synthetic data show an average improvement of 7.5 dB in the signal-to-noise ratio (SNR) for input SNRs in the range of -15 to 15 dB. Application of the method with real signals and subsequent ECG interval analysis demonstrates a root mean square error of 9.9 and 14 ms for the PR and QT intervals, respectively, when compared with simultaneous scalp measurements. The proposed network can achieve substantial noise removal on both synthetic and real data. In cases of highly noise-contaminated signals some morphological features might be unreliably reconstructed. Significance: The presented method has the advantage of preserving individual variations in pulse shape and beat-to-beat intervals. Moreover, no prior knowledge on the power spectra of the noise or the pulse locations is required.
In the field of building detection research, an accurate, state-of-the-art semantic segmentation model must be constructed to classify each pixel of the image, which has an important reference value for the statistica...
详细信息
In the field of building detection research, an accurate, state-of-the-art semantic segmentation model must be constructed to classify each pixel of the image, which has an important reference value for the statistical work of a building area. Recent research efforts have been devoted to semantic segmentation using deep learning approaches, which can be further divided into two aspects. In this paper, we propose a single-side dual-branch network (SSDBN) based on an encoder-decoder structure, where an improved Res2Net model is used at the encoder stage to extract the basic feature information of prepared images while a dual-branch module is deployed at the decoder stage. An intermediate framework was designed using a new feature information fusion methods to capture more semantic information in a small area. The dual-branch decoding module contains a deconvolution branch and a feature enhancement branch, which are responsible for capturing multi-scale information and enhancing high-level semantic details, respectively. All experiments were conducted using the Massachusetts Buildings Dataset and WHU Satellite Dataset I (global cities). The proposed model showed better performance than other recent approaches, achieving an F1-score of 87.69% and an IoU of 75.83% with a low network size volume (5.11 M), internal parameters (19.8 MB), and GFLOPs (22.54), on the Massachusetts Buildings Dataset.
Despite significant advances in 3D human pose estimation from a single-view video, existing methods often struggle to produce reasonable human poses when the human is heavily occluded or blurred. To address this issue...
详细信息
Denoising of CT scans has attracted the attention of many researchers in the medical image analysis domain. encoder-decoder networks are deep learning neural networks that have become common for image denoising in rec...
详细信息
Denoising of CT scans has attracted the attention of many researchers in the medical image analysis domain. encoder-decoder networks are deep learning neural networks that have become common for image denoising in recent years. Shortcuts between the encoder and decoder layers are crucial for some image-to-image translation tasks. However, are all shortcuts necessary for CT denoising? To answer this question, we set up two encoder-decoder networks representing two popular architectures and then progressively removed shortcuts from the networks from shallow to deep (forward removal) and from deep to shallow (backward removal). We used two unrelated datasets with different noise levels to test the denoising performance of these networks using two metrics, namely root mean square error and content loss. The results show that while more than half of the shortcuts are still indispensable for CT scan denoising, removing certain shortcuts leads to performance improvement for denoising. Both shallow and deep shortcuts might be removed, thus retaining sparse connections, especially when the noise level is high. Backward removal seems to have a better performance than forward removal, which means deep shortcuts have priority to be removed. Finally, we propose a hypothesis to explain this phenomenon and validate it in the experiments.
Purpose Nonlinear multimodal image registration, for example, the fusion of computed tomography (CT) and magnetic resonance imaging (MRI), fundamentally depends on a definition of image similarity. Previous methods th...
详细信息
Purpose Nonlinear multimodal image registration, for example, the fusion of computed tomography (CT) and magnetic resonance imaging (MRI), fundamentally depends on a definition of image similarity. Previous methods that derived modality-invariant representations focused on either global statistical grayscale relations or local structural similarity, both of which are prone to local optima. In contrast to most learning-based methods that rely on strong supervision of aligned multimodal image pairs, we aim to overcome this limitation for further practical use cases. Methods We propose a new concept that exploits anatomical shape information and requires only segmentation labels for both modalities individually. First, a shape-constrained encoder-decoder segmentation network without skip connections is jointly trained on labeled CT and MRI inputs. Second, an iterative energy-based minimization scheme is introduced that relies on the capability of the network to generate intermediate nonlinear shape representations. This further eases the multimodal alignment in the case of large deformations. Results Our novel approach robustly and accurately aligns 3D scans from the multimodal whole-heart segmentation dataset, outperforming classical unsupervised frameworks. Since both parts of our method rely on (stochastic) gradient optimization, it can be easily integrated in deep learning frameworks and executed on GPUs. Conclusions We present an integrated approach for weakly supervised multimodal image registration. Achieving promising results due to the exploration of intermediate shape features as registration guidance encourages further research in this direction.
Due to the complexity of object information and optical conditions of high-resolution aerial imagery, it is difficult to obtain fine semantic segmentation performance. Although various deep neural network structures h...
详细信息
Due to the complexity of object information and optical conditions of high-resolution aerial imagery, it is difficult to obtain fine semantic segmentation performance. Although various deep neural network structures have been proposed to improve segmentation accuracy, there is still room for improving accuracy by making full use of multiscale features and integrating these single weak classifiers into a strong classifier. In this paper, we use a reduced SegNet network to realize the end-to-end classification of high-resolution aerial images. In addition, to use multiscale information, we present the R-SegUnet which combines the feature information of each convolution block in the reduced SegNet encoding network with the feature information of the corresponding convolution block in the decoding network. Furthermore, considering that the surface features in high-resolution aerial images are very complex, we investigate a 6to2_Net that converts the six-classification model into six binary-classification models for the recognition effect on small objects. Finally, we ensemble the above three different models to get the segmentation results. Experiment results on ISPRS Potsdam benchmark dataset show that our algorithm is state-of-the-art method. We also analyze the inference performance of our models on a variety of parallel computing devices.
Accurate quantification of cerebral blood flow (CBF) is essential for the diagnosis and assessment of a wide range of neurological diseases. Positron emission tomography (PET) with radiolabeled water (O-15-water) is t...
详细信息
Accurate quantification of cerebral blood flow (CBF) is essential for the diagnosis and assessment of a wide range of neurological diseases. Positron emission tomography (PET) with radiolabeled water (O-15-water) is the gold-standard for the measurement of CBF in humans, however, it is not widely available due to its prohibitive costs and the use of short-lived radiopharmaceutical tracers that require onsite cyclotron production. Magnetic resonance imaging (MRI), in contrast, is more accessible and does not involve ionizing radiation. This study presents a convolutional encoder-decoder network with attention mechanisms to predict the gold-standard O-15-water PET CBF from multi-contrast MRI scans, thus eliminating the need for radioactive tracers. The model was trained and validated using 5-fold cross-validation in a group of 126 subjects consisting of healthy controls and cerebrovascular disease patients, all of whom underwent simultaneous O-15-water PET/MRI. The results demonstrate that the model can successfully synthesize high-quality PET CBF measurements (with an average SSIM of 0.924 and PSNR of 38.8 dB) and is more accurate compared to concurrent and previous PET synthesis methods. We also demonstrate the clinical significance of the proposed algorithm by evaluating the agreement for identifying the vascular territories with impaired CBF. Such methods may enable more widespread and accurate CBF evaluation in larger cohorts who cannot undergo PET imaging due to radiation concerns, lack of access, or logistic challenges.
We propose a dictionary-matching-free pipeline for multi-parametric quantitative MRI image computing. Our approach has two stages based on compressed sensing reconstruction and deep learned quantitative inference. The...
详细信息
We propose a dictionary-matching-free pipeline for multi-parametric quantitative MRI image computing. Our approach has two stages based on compressed sensing reconstruction and deep learned quantitative inference. The reconstruction phase is convex and incorporates efficient spatiotemporal regularisations within an accelerated iterative shrinkage algorithm. This minimises the under-sampling (aliasing) artefacts from aggressively short scan times. The learned quantitative inference phase is purely trained on physical simulations (Bloch equations) that are flexible for producing rich training samples. We propose a deep and compact encoder-decoder network with residual blocks in order to embed Bloch manifold projections through multi-scale piecewise affine approximations, and to replace the non-scalable dictionary matching baseline. Tested on a number of datasets we demonstrate effectiveness of the proposed scheme for recovering accurate and consistent quantitative information from novel and aggressively subsampled 2D/3D quantitative MRI acquisition protocols. (c) 2020 Elsevier B.V. All rights reserved.
Predicting RNA binding protein(RBP) binding sites on circular RNAs(circ RNAs) is a fundamental step to understand their interaction mechanism. Numerous computational methods are developed to solve this problem, but th...
详细信息
Predicting RNA binding protein(RBP) binding sites on circular RNAs(circ RNAs) is a fundamental step to understand their interaction mechanism. Numerous computational methods are developed to solve this problem, but they cannot fully learn the features. Therefore, we propose circ-CNNED, a convolutional neural network(CNN)-based encoding and decoding framework. We first adopt two encoding methods to obtain two original matrices. We preprocess them using CNN before fusion. To capture the feature dependencies, we utilize temporal convolutional network(TCN) and CNN to construct encoding and decoding blocks, respectively. Then we introduce global expectation pooling to learn latent information and enhance the robustness of circ-CNNED. We perform circ-CNNED across 37 datasets to evaluate its effect. The comparison and ablation experiments demonstrate that our method is superior. In addition, motif enrichment analysis on four datasets helps us to explore the reason for performance improvement of circ-CNNED.
Global river monitoring is an important mission within the remote sensing society. One of the main challenges faced by this mission is generating an accurate water mask from remote sensing images (RSI) of rivers (RSIR...
详细信息
Global river monitoring is an important mission within the remote sensing society. One of the main challenges faced by this mission is generating an accurate water mask from remote sensing images (RSI) of rivers (RSIR), especially on a global scale with various river features. Aiming at better water area classification using semantic information, this paper presents a segmentation method for global river monitoring based on semantic clustering and semantic fusion. Firstly, an encoder-decoder network (AEN)-based architecture is proposed to obtain the semantic features from RSIR. Secondly, a clustering-based semantic fusion method is proposed to divide semantic features of RSIR into groups and train convolutional neural networks (CNN) models corresponding to each group using data augmentation and semi-supervised learning. Thirdly, a semantic distance-based segmentation fusion method is proposed for fusing the CNN models result into final segmentation mask. We built a global river dataset that contains multiple river segments from each continent of the world based on Sentinel-2 satellite imagery. The result shows that the F1-score of the proposed segmentation method is 93.32%, which outperforms several state-of-the-art algorithms, and demonstrates that grouping semantic information helps better segment the RSIR in global scale.
暂无评论