Breast Cancer Classification from Digital Pathology Images via Connectivity-aware Graph Transformer.

Automated classification of breast cancer subtypes from digital pathology images has been an extremely challenging task due to the complicated spatial patterns of cells in the tissue micro-environment. While newly proposed graph transformers are able to capture more long-range dependencies to enhance accuracy, they largely ignore the topological connectivity between graph nodes, which is nevertheless critical to extract more representative features to address this difficult task. In this paper, we propose a novel connectivity-aware graph transformer (CGT) for phenotyping the topology connectivity of the tissue graph constructed from digital pathology images for breast cancer classification. Our CGT seamlessly integrates connectivity embedding to node feature at every graph transformer layer by using local connectivity aggregation, in order to yield more comprehensive graph representations to distinguish different breast cancer subtypes. In light of the realistic intercellular communication mode, we then encode the spatial distance between two arbitrary nodes as connectivity bias in self-attention calculation, thereby allowing the CGT to distinctively harness the connectivity embedding based on the distance of two nodes. We extensively evaluate the proposed CGT on a large cohort of breast carcinoma digital pathology images stained by Haematoxylin & Eosin. Experimental results demonstrate the effectiveness of our CGT, which outperforms state-of-the-art methods by a large margin. Codes are released on https://github.com/wang-kang-6/CGT.

Robust Corrupted Data Recovery and Clustering via Generalized Transformed Tensor Low-Rank Representation.

Tensor analysis has received widespread attention in high-dimensional data learning. Unfortunately, the tensor data are often accompanied by arbitrary signal corruptions, including missing entries and sparse noise. How to recover the characteristics of the corrupted tensor data and make it compatible with the downstream clustering task remains a challenging problem. In this article, we study a generalized transformed tensor low-rank representation (TTLRR) model for simultaneously recovering and clustering the corrupted tensor data. The core idea is to find the latent low-rank tensor structure from the corrupted measurements using the transformed tensor singular value decomposition (SVD). Theoretically, we prove that TTLRR can recover the clean tensor data with a high probability guarantee under mild conditions. Furthermore, by using the transform adaptively learning from the data itself, the proposed TTLRR model can approximately represent and exploit the intrinsic subspace and seek out the cluster structure of the tensor data precisely. An effective algorithm is designed to solve the proposed model under the alternating direction method of multipliers (ADMMs) algorithm framework. The effectiveness and superiority of the proposed method against the compared methods are showcased over different tasks, including video/face data recovery and face/object/scene data clustering.

Progressive Feature Fusion Attention Dense Network for Speckle Noise Removal in OCT Images.

Although deep learning for Big Data analytics has achieved promising results in the field of optical coherence tomography (OCT) image denoising, the low recognition rate caused by complex noise distribution and a large number of redundant features is still a challenge faced by deep learning-based denoising methods. Moreover, the network with large depth will bring high computational complexity. To this end, we propose a progressive feature fusion attention dense network (PFFADN) for speckle noise removal in OCT images. We arrange densely connected dense blocks in the deep convolution network, and sequentially connect the shallow convolution feature map with the deep one extracted from each dense block to form a residual block. We add attention mechanism to the network to extract the key features and suppress the irrelevant ones. We fuse the output feature maps from all dense blocks and input them to the reconstruction output layer. We compare PFFADN with the state-of-the-art denoising algorithms on retinal OCT images. Experiments show that our method has better improvement in denoising performance.

Is blockchain for Internet of Medical Things a panacea for COVID-19 pandemic?

The outbreak of the COVID-19 pandemic has deeply influenced the lifestyle of the general public and the healthcare system of the society. As a promising approach to address the emerging challenges caused by the epidemic of infectious diseases like COVID-19, Internet of Medical Things (IoMT) deployed in hospitals, clinics, and healthcare centers can save the diagnosis time and improve the efficiency of medical resources though privacy and security concerns of IoMT stall the wide adoption. In order to tackle the privacy, security, and interoperability issues of IoMT, we propose a framework of blockchain-enabled IoMT by introducing blockchain to incumbent IoMT systems. In this paper, we review the benefits of this architecture and illustrate the opportunities brought by blockchain-enabled IoMT. We also provide use cases of blockchain-enabled IoMT on fighting against the COVID-19 pandemic, including the prevention of infectious diseases, location sharing and contact tracing, and the supply chain of injectable medicines. We also outline future work in this area.

Securing Internet of Medical Things with Friendly-jamming schemes.

The Internet of Medical Things (IoMT)-enabled e-healthcare can complement traditional medical treatments in a flexible and convenient manner. However, security and privacy become the main concerns of IoMT due to the limited computational capability, memory space and energy constraint of medical sensors, leading to the in-feasibility for conventional cryptographic approaches, which are often computationally-complicated. In contrast to cryptographic approaches, friendly jamming (Fri-jam) schemes will not cause extra computing cost to medical sensors, thereby becoming potential countermeasures to ensure security of IoMT. In this paper, we present a study on using Fri-jam schemes in IoMT. We first analyze the data security in IoMT and discuss the challenges. We then propose using Fri-jam schemes to protect the confidential medical data of patients collected by medical sensors from being eavesdropped. We also discuss the integration of Fri-jam schemes with various communication technologies, including beamforming, Simultaneous Wireless Information and Power Transfer (SWIPT) and full duplexity. Moreover, we present two case studies of Fri-jam schemes in IoMT. The results of these two case studies indicate that the Fri-jam method will significantly decrease the eavesdropping risk while leading to no significant influence on legitimate transmission.

A Novel Friendly Jamming Scheme in Industrial Crowdsensing Networks against Eavesdropping Attack.

Eavesdropping attack is one of the most serious threats in industrial crowdsensing networks. In this paper, we propose a novel anti-eavesdropping scheme by introducing friendly jammers to an industrial crowdsensing network. In particular, we establish a theoretical framework considering both the probability of eavesdropping attacks and the probability of successful transmission to evaluate the effectiveness of our scheme. Our framework takes into account various channel conditions such as path loss, Rayleigh fading, and the antenna type of friendly jammers. Our results show that using jammers in industrial crowdsensing networks can effectively reduce the eavesdropping risk while having no significant influence on legitimate communications.

Link Connectivity and Coverage of Underwater Cognitive Acoustic Networks under Spectrum Constraint.

Extensive attention has been given to the use of cognitive radio technology in underwater acoustic networks since the acoustic spectrum became scarce due to the proliferation of human aquatic activities. Most of the recent studies on underwater cognitive acoustic networks (UCANs) mainly focus on spectrum management or protocol design. Few efforts have addressed the quality-of-service (QoS) of UCANs. In UCANs, secondary users (SUs) have lower priority to use acoustic spectrum than primary users (PUs) with higher priority to access spectrum. As a result, the QoS of SUs is difficult to ensure in UCANs. This paper proposes an analytical model to investigate the link connectivity and the probability of coverage of SUs in UCANs. In particular, this model takes both topological connectivity and spectrum availability into account, though spectrum availability has been ignored in most recent studies. We conduct extensive simulations to evaluate the effectiveness and the accuracy of our proposed model. Simulation results show that our proposed model is quite accurate. Besides, our results also imply that the link connectivity and the probability of coverage of SUs heavily depend on both the underwater acoustic channel conditions and the activities of PUs.

On Connectivity of Wireless Sensor Networks with Directional Antennas.

In this paper, we investigate the network connectivity of wireless sensor networks with directional antennas. In particular, we establish a general framework to analyze the network connectivity while considering various antenna models and the channel randomness. Since existing directional antenna models have their pros and cons in the accuracy of reflecting realistic antennas and the computational complexity, we propose a new analytical directional antenna model called the iris model to balance the accuracy against the complexity. We conduct extensive simulations to evaluate the analytical framework. Our results show that our proposed analytical model on the network connectivity is accurate, and our iris antenna model can provide a better approximation to realistic directional antennas than other existing antenna models.

On Performance Analysis of Protective Jamming Schemes in Wireless Sensor Networks.

Wireless sensor networks (WSNs) play an important role in Cyber Physical Social Sensing (CPSS) systems. An eavesdropping attack is one of the most serious threats to WSNs since it is a prerequisite for other malicious attacks. In this paper, we propose a novel anti-eavesdropping mechanism by introducing friendly jammers to wireless sensor networks (WSNs). In particular, we establish a theoretical framework to evaluate the eavesdropping risk of WSNs with friendly jammers and that of WSNs without jammers. Our theoretical model takes into account various channel conditions such as the path loss and Rayleigh fading, the placement schemes of jammers and the power controlling schemes of jammers. Extensive results show that using jammers in WSNs can effectively reduce the eavesdropping risk. Besides, our results also show that the appropriate placement of jammers and the proper assignment of emitting power of jammers can not only mitigate the eavesdropping risk but also may have no significant impairment to the legitimate communications.

On Modeling Eavesdropping Attacks in Underwater Acoustic Sensor Networks.

The security and privacy of underwater acoustic sensor networks has received extensive attention recently due to the proliferation of underwater activities. This paper proposes an analytical model to investigate the eavesdropping attacks in underwater acoustic sensor networks. Our analytical framework considers the impacts of various underwater acoustic channel conditions (such as the acoustic signal frequency, spreading factor and wind speed) and different hydrophones (isotropic hydrophones and array hydrophones) in terms of network nodes and eavesdroppers. We also conduct extensive simulations to evaluate the effectiveness and the accuracy of our proposed model. Empirical results show that our proposed model is quite accurate. In addition, our results also imply that the eavesdropping probability heavily depends on both the underwater acoustic channel conditions and the features of hydrophones.