arXiv subjects

Shanshan Wang

Publications and source records attributed to Shanshan Wang.

At least 145 records · Page 8Linked to original sources

arXiv2022

Semi-Supervised and Self-Supervised Collaborative Learning for Prostate 3D MR Image Segmentation

Volumetric magnetic resonance (MR) image segmentation plays an important role in many clinical applications. Deep learning (DL) has recently achieved state-of-the-art or even human-level performance on various image segmentation tasks. Nevertheless, manually annotating volumetric MR images for DL model training is labor-exhaustive and time-consuming. In this work, we aim to train a semi-supervised and self-supervised collaborative learning framework for prostate 3D MR image segmentation while using extremely sparse annotations, for which the ground truth annotations are provided for just the central slice of each volumetric MR image. Specifically, semi-supervised learning and self-supervised learning methods are used to generate two independent sets of pseudo labels. These pseudo labels are then fused by Boolean operation to extract a more confident pseudo label set. The images with either manual or network self-generated labels are then employed to train a segmentation model for target volume extraction. Experimental results on a publicly available prostate MR image dataset demonstrate that, while requiring significantly less annotation effort, our framework generates very encouraging segmentation results. The proposed framework is very useful in clinical applications when training data with dense annotations are difficult to obtain.

cs.CV↗

arXiv2022

Adaptive PromptNet For Auxiliary Glioma Diagnosis without Contrast-Enhanced MRI

Multi-contrast magnetic resonance imaging (MRI)-based automatic auxiliary glioma diagnosis plays an important role in the clinic. Contrast-enhanced MRI sequences (e.g., contrast-enhanced T1-weighted imaging) were utilized in most of the existing relevant studies, in which remarkable diagnosis results have been reported. Nevertheless, acquiring contrast-enhanced MRI data is sometimes not feasible due to the patients physiological limitations. Furthermore, it is more time-consuming and costly to collect contrast-enhanced MRI data in the clinic. In this paper, we propose an adaptive PromptNet to address these issues. Specifically, a PromptNet for glioma grading utilizing only non-enhanced MRI data has been constructed. PromptNet receives constraints from features of contrast-enhanced MR data during training through a designed prompt loss. To further boost the performance, an adaptive strategy is designed to dynamically weight the prompt loss in a sample-based manner. As a result, PromptNet is capable of dealing with more difficult samples. The effectiveness of our method is evaluated on a widely-used BraTS2020 dataset, and competitive glioma grading performance on NE-MRI data is achieved.

eess.IV↗

arXiv2022

DIGEST: Deeply supervIsed knowledGE tranSfer neTwork learning for brain tumor segmentation with incomplete multi-modal MRI scans

Brain tumor segmentation based on multi-modal magnetic resonance imaging (MRI) plays a pivotal role in assisting brain cancer diagnosis, treatment, and postoperative evaluations. Despite the achieved inspiring performance by existing automatic segmentation methods, multi-modal MRI data are still unavailable in real-world clinical applications due to quite a few uncontrollable factors (e.g. different imaging protocols, data corruption, and patient condition limitations), which lead to a large performance drop during practical applications. In this work, we propose a Deeply supervIsed knowledGE tranSfer neTwork (DIGEST), which achieves accurate brain tumor segmentation under different modality-missing scenarios. Specifically, a knowledge transfer learning frame is constructed, enabling a student model to learn modality-shared semantic information from a teacher model pretrained with the complete multi-modal MRI data. To simulate all the possible modality-missing conditions under the given multi-modal data, we generate incomplete multi-modal MRI samples based on Bernoulli sampling. Finally, a deeply supervised knowledge transfer loss is designed to ensure the consistency of the teacher-student structure at different decoding stages, which helps the extraction of inherent and effective modality representations. Experiments on the BraTS 2020 dataset demonstrate that our method achieves promising results for the incomplete multi-modal MR image segmentation task.

eess.IV↗

arXiv2022

Response functions as a new concept to study local dynamics in traffic networks

Vehicle velocities in neighbouring road sections are correlated with memory effects. We explore the response of the velocities in the sequence of sections to a congestion in a given section and its dynamic characteristics. To this end, we transfer the concept of response functions from previous applications in finance to traffic systems. The dynamical characteristics are of particular interest. We identify two phases, a phase of transient response and a phase of long-term response. The transient response is pronounced when considering the backward propagation of heavy congestions but almost vanishes for forward propagation. For each response phase, we find a linear relation between the velocity response and the congestion correlator, implying that the correlation of congestion is most likely the cause for the velocity response. We also construct a susceptible-decelerated-withdrawing model mathematically inspired by the susceptible-infectious-recovered (SIR) model in epidemiology to describe the transient response. We find that the heavy congestion on a section propagates forward and backward at a similar rate, but the forward sections are more likely to recover from the effect of heavy congestion than the backward sections.

physics.soc-ph↗

arXiv2022

PARCEL: Physics-based Unsupervised Contrastive Representation Learning for Multi-coil MR Imaging

With the successful application of deep learning to magnetic resonance (MR) imaging, parallel imaging techniques based on neural networks have attracted wide attention. However, in the absence of high-quality, fully sampled datasets for training, the performance of these methods is limited. And the interpretability of models is not strong enough. To tackle this issue, this paper proposes a Physics-bAsed unsupeRvised Contrastive rEpresentation Learning (PARCEL) method to speed up parallel MR imaging. Specifically, PARCEL has a parallel framework to contrastively learn two branches of model-based unrolling networks from augmented undersampled multi-coil k-space data. A sophisticated co-training loss with three essential components has been designed to guide the two networks in capturing the inherent features and representations for MR images. And the final MR image is reconstructed with the trained contrastive networks. PARCEL was evaluated on two vivo datasets and compared to five state-of-the-art methods. The results show that PARCEL is able to learn essential representations for accurate MR reconstruction without relying on fully sampled datasets.

eess.IV↗

arXiv2022

Self-supervised Graph Learning for Long-tailed Cognitive Diagnosis

Cognitive diagnosis is a fundamental yet critical research task in the field of intelligent education, which aims to discover the proficiency level of different students on specific knowledge concepts. Despite the effectiveness of existing efforts, previous methods always considered the mastery level on the whole students, so they still suffer from the Long Tail Effect. A large number of students who have sparse data are performed poorly in the model. To relieve the situation, we proposed a Self-supervised Cognitive Diagnosis (SCD) framework which leverages the self-supervised manner to assist the graph-based cognitive diagnosis, then the performance on those students with sparse data can be improved. Specifically, we came up with a graph confusion method that drops edges under some special rules to generate different sparse views of the graph. By maximizing the consistency of the representation on the same node under different views, the model could be more focused on long-tailed students. Additionally, we proposed an importance-based view generation rule to improve the influence of long-tailed students. Extensive experiments on real-world datasets show the effectiveness of our approach, especially on the students with sparse data.

cs.CY↗

arXiv2022

Specificity-Preserving Federated Learning for MR Image Reconstruction

Federated learning (FL) can be used to improve data privacy and efficiency in magnetic resonance (MR) image reconstruction by enabling multiple institutions to collaborate without needing to aggregate local data. However, the domain shift caused by different MR imaging protocols can substantially degrade the performance of FL models. Recent FL techniques tend to solve this by enhancing the generalization of the global model, but they ignore the domain-specific features, which may contain important information about the device properties and be useful for local reconstruction. In this paper, we propose a specificity-preserving FL algorithm for MR image reconstruction (FedMRI). The core idea is to divide the MR reconstruction model into two parts: a globally shared encoder to obtain a generalized representation at the global level, and a client-specific decoder to preserve the domain-specific properties of each client, which is important for collaborative reconstruction when the clients have unique distribution. Such scheme is then executed in the frequency space and the image space respectively, allowing exploration of generalized representation and client-specific properties simultaneously in different spaces. Moreover, to further boost the convergence of the globally shared encoder when a domain shift is present, a weighted contrastive regularization is introduced to directly correct any deviation between the client and server during optimization. Extensive experiments demonstrate that our FedMRI's reconstructed results are the closest to the ground-truth for multi-institutional data, and that it outperforms state-of-the-art FL methods.

eess.IV↗

arXiv2022

K-space and Image Domain Collaborative Energy based Model for Parallel MRI Reconstruction

Decreasing magnetic resonance (MR) image acquisition times can potentially make MR examinations more accessible. Prior arts including the deep learning models have been devoted to solving the problem of long MRI imaging time. Recently, deep generative models have exhibited great potentials in algorithm robustness and usage flexibility. Nevertheless, none of existing schemes can be learned or employed to the k-space measurement directly. Furthermore, how do the deep generative models work well in hybrid domain is also worth being investigated. In this work, by taking advantage of the deep energy-based models, we propose a k-space and image domain collaborative generative model to comprehensively estimate the MR data from under-sampled measurement. Experimental comparisons with the state-of-the-arts demonstrated that the proposed hybrid method has less error in reconstruction accuracy and is more stable under different acceleration factors

eess.IV↗

arXiv2022

SelfCoLearn: Self-supervised collaborative learning for accelerating dynamic MR imaging

Lately, deep learning has been extensively investigated for accelerating dynamic magnetic resonance (MR) imaging, with encouraging progresses achieved. However, without fully sampled reference data for training, current approaches may have limited abilities in recovering fine details or structures. To address this challenge, this paper proposes a self-supervised collaborative learning framework (SelfCoLearn) for accurate dynamic MR image reconstruction from undersampled k-space data. The proposed framework is equipped with three important components, namely, dual-network collaborative learning, reunderampling data augmentation and a specially designed co-training loss. The framework is flexible to be integrated with both data-driven networks and model-based iterative un-rolled networks. Our method has been evaluated on in-vivo dataset and compared it to four state-of-the-art methods. Results show that our method possesses strong capabilities in capturing essential and inherent representations for direct reconstructions from the undersampled k-space data and thus enables high-quality and fast dynamic MR imaging.

eess.IV↗

arXiv2022

Self-supervised Learning of Audio Representations from Audio-Visual Data using Spatial Alignment

Learning from audio-visual data offers many possibilities to express correspondence between the audio and visual content, similar to the human perception that relates aural and visual information. In this work, we present a method for self-supervised representation learning based on audio-visual spatial alignment (AVSA), a more sophisticated alignment task than the audio-visual correspondence (AVC). In addition to the correspondence, AVSA also learns from the spatial location of acoustic and visual content. Based on 360$^\text{o}$ video and Ambisonics audio, we propose selection of visual objects using object detection, and beamforming of the audio signal towards the detected objects, attempting to learn the spatial alignment between objects and the sound they produce. We investigate the use of spatial audio features to represent the audio input, and different audio formats: Ambisonics, mono, and stereo. Experimental results show a 10 $\%$ improvement on AVSA for the first order ambisonics intensity vector (FOA-IV) in comparison with log-mel spectrogram features; the addition of object-oriented crops also brings significant performance increases for the human action recognition downstream task. A number of audio-only downstream tasks are devised for testing the effectiveness of the learnt audio feature representation, obtaining performance comparable to state-of-the-art methods on acoustic scene classification from ambisonic and binaural audio.

eess.AS↗

arXiv2022

Mining Function Homology of Bot Loaders from Honeypot Logs

Self-contained loaders are widely adopted in botnets for injecting loading commands and spawning new bots. While researchers can dissect bot clients to get various information of botnets, the cloud-based and self-contained design of loaders effectively hinders researchers from understanding the loaders' evolution and variation using classic methods. The decoupled nature of bot loaders also dramatically reduces the feasibility of investigating relationships among clients and infrastructures. In this paper, we propose a text-based method to investigate and analyze details of bot loaders using honeypots. We leverage high interaction honeypots to collect request logs and define eight families of bot loaders based on the result of agglomerative clustering. At the function level, we push our study further to explore their homological relationship based on similarity analysis of request logs using sequence aligning techniques. This further exploration discloses that the released code of Mirai keeps spawning new generations of botnets both on the client and the server side. This paper uncovers the homology of active botnet infrastructures, providing a new prospect on finding covert relationships among cybercrimes. Bot loaders are precisely investigated at the function level to yield a new insight for researchers to identify the botnet's infrastructures and track their evolution over time.

cs.CR↗

arXiv2022

Artificial Intelligence Enabled Spectral Reconfigurable Fiber Laser

The combinations of artificial intelligence and lasers provide powerful ways to form smart light sources with ground-breaking functions. Here, a Raman fiber laser (RFL) with reconfigurable and programmable spectra in an ultra-wide bandwidth is developed based on spectral-spatial manipulation of light in multimode fiber (MMF). The proposed fiber laser uses nonlinear gain from cascaded stimulated Raman scattering, random distributed feedback from Rayleigh scattering, and point feedback from an MMF-based smart spectral filter. Through wavefront shaping controlled by a genetic algorithm, light of selective wavelength(s) can be focused in the MMF, forming the filter that, together with the active part of the laser, actively shape the output spectrum with a high degree of freedom. We achieved arbitrary spectral shaping of the cascaded RFL (e.g., continuously tunable single-wavelength and multi-wavelength laser with customizable linewidth, mode separation, and power distribution) from the 1st- to the 3rd-order Stokes emission by adjusting the pump power and auto-optimization of the smart filter. Our research uses artificial-intelligence controlled light manipulation in a fiber platform with multi-eigenmodes and nonlinear gain, mapping the spatial control into the spectral domain as well as extending the linear control of light in MMF to active light emission, which is of great significance for applications in optical communication, sensing, and spectroscopy.

physics.optics↗

arXiv2022

Paying More Attention to Self-attention: Improving Pre-trained Language Models via Attention Guiding

Pre-trained language models (PLM) have demonstrated their effectiveness for a broad range of information retrieval and natural language processing tasks. As the core part of PLM, multi-head self-attention is appealing for its ability to jointly attend to information from different positions. However, researchers have found that PLM always exhibits fixed attention patterns regardless of the input (e.g., excessively paying attention to [CLS] or [SEP]), which we argue might neglect important information in the other positions. In this work, we propose a simple yet effective attention guiding mechanism to improve the performance of PLM by encouraging attention towards the established goals. Specifically, we propose two kinds of attention guiding methods, i.e., map discrimination guiding (MDG) and attention pattern decorrelation guiding (PDG). The former definitely encourages the diversity among multiple self-attention heads to jointly attend to information from different representation subspaces, while the latter encourages self-attention to attend to as many different positions of the input as possible. We conduct experiments with multiple general pre-trained models (i.e., BERT, ALBERT, and Roberta) and domain-specific pre-trained models (i.e., BioBERT, ClinicalBERT, BlueBert, and SciBERT) on three benchmark datasets (i.e., MultiNLI, MedNLI, and Cross-genre-IR). Extensive experimental results demonstrate that our proposed MDG and PDG bring stable performance improvements on all datasets with high efficiency and low cost.

cs.CL↗

arXiv2022

Multi-Weight Respecification of Scan-specific Learning for Parallel Imaging

Parallel imaging is widely used in magnetic resonance imaging as an acceleration technology. Traditional linear reconstruction methods in parallel imaging often suffer from noise amplification. Recently, a non-linear robust artificial-neural-network for k-space interpolation (RAKI) exhibits superior noise resilience over other linear methods. However, RAKI performs poorly at high acceleration rates, and needs a large amount of autocalibration signals as the training samples. In order to tackle these issues, we propose a multi-weight method that implements multiple weighting matrices on the undersampled data, named as MW-RAKI. Enforcing multiple weighted matrices on the measurements can effectively reduce the influence of noise and increase the data constraints. Furthermore, we incorporate the strategy of multiple weighting matrixes into a residual version of RAKI, and form MW-rRAKI.Experimental compari-sons with the alternative methods demonstrated noticeably better reconstruction performances, particularly at high acceleration rates.

eess.IV↗

arXiv2022

Identifying subdominant collective effects in a large motorway network

In a motorway network, correlations between parts or, more precisely, between the sections of (different) motorways, are of considerable interest. Knowledge of flows and velocities on individual motorways is not sufficient, rather, their correlations determine or reflect, respectively, the functionality of and the dynamics on the network. These correlations are time-dependent as the dynamics on the network is highly non-stationary. Apart from the conceptual importance, correlations are also indispensable to detect risks of failure in a traffic network. Here, we proceed with revealing a certain hierarchy of correlations in traffic networks that is due to the presence and to the extent of collectivity. In a previous study, we focused on the collectivity motion present in the entire traffic network, i.e. the collectivity of the system as a whole. Here, we manage to subtract this dominant effect from the data and identify the subdominant collectivities which affect different, large parts of the traffic network. To this end, we employ a spectral analysis of the correlation matrix for the whole system. We thereby extract information from the virtual network induced by the correlations and map it on the true topology, i.e. on the real motorway network. The uncovered subdominant collectivities provide a new characterization of the traffic network. We carry out our study for the large motorway network of North Rhine-Westphalia (NRW), Germany.

physics.soc-ph↗

arXiv2022

Variable Augmented Network for Invertible MR Coil Compression

A large number of coils are able to provide enhanced signal-to-noise ratio and improve imaging performance in parallel imaging. Nevertheless, the increasing growth of coil number simultaneously aggravates the drawbacks of data storage and reconstruction speed, especially in some iterative reconstructions. Coil compression addresses these issues by generating fewer virtual coils. In this work, a novel variable augmentation network for invertible coil compression termed VAN-ICC is presented. It utilizes inherent reversibility of normalizing flow-based models for high-precision compression and invertible recovery. By employing the variable augmentation technology to image/k-space variables from multi-coils, VAN-ICC trains invertible networks by finding an invertible and bijective function, which can map the original data to the compressed counterpart and vice versa. Experiments conducted on both fully-sampled and under-sampled data verified the effectiveness and flexibility of VAN-ICC. Quantitative and qualitative comparisons with traditional non-deep learning-based approaches demonstrated that VAN-ICC can carry much higher compression effects. Additionally, its performance is not susceptible to different number of virtual coils.

cs.CV↗

arXiv2022

Rethinking the optimization process for self-supervised model-driven MRI reconstruction

Recovering high-quality images from undersampled measurements is critical for accelerated MRI reconstruction. Recently, various supervised deep learning-based MRI reconstruction methods have been developed. Despite the achieved promising performances, these methods require fully sampled reference data, the acquisition of which is resource-intensive and time-consuming. Self-supervised learning has emerged as a promising solution to alleviate the reliance on fully sampled datasets. However, existing self-supervised methods suffer from reconstruction errors due to the insufficient constraint enforced on the non-sampled data points and the error accumulation happened alongside the iterative image reconstruction process for model-driven deep learning reconstrutions. To address these challenges, we propose K2Calibrate, a K-space adaptation strategy for self-supervised model-driven MR reconstruction optimization. By iteratively calibrating the learned measurements, K2Calibrate can reduce the network's reconstruction deterioration caused by statistically dependent noise. Extensive experiments have been conducted on the open-source dataset FastMRI, and K2Calibrate achieves better results than five state-of-the-art methods. The proposed K2Calibrate is plug-and-play and can be easily integrated with different model-driven deep learning reconstruction methods.

eess.IV↗

arXiv2022

Spatial Correlation Analysis of Traffic Flow on Parallel Motorways in Germany

With the widely used method of correlation matrix analysis, this study reveals the change of traffic states on parallel motorways in North Rhine-Westphalia, Germany. In terms of the time series of traffic flow and velocity, we carry out a quantitative analysis in correlations and reveal a high level of strongly positive traffic flow correlation and rich structural features in the corresponding correlation matrices. The strong correlation is mainly ascribed to the daily time evolution of traffic flow during the periods of rush hours and non-rush hours. In terms of free flow and congestion, the structural features are able to capture the average traffic situation we derive from our data. Furthermore, the structural features in correlation matrices for individual time periods corroborate our results from the correlation matrices regarding a whole day. The average correlations in traffic flows and velocities over all pairwise sections disclose the traffic behavior during each individual time period. Our contribution uncovers the potential application of correlation analysis on the study of traffic networks as a complex system.

physics.soc-ph↗