Residual Feature Attentional Fusion Network for Lightweight Chest CT Image Super-Resolution

The diagnosis of COVID-19 requires chest computed tomography (CT). High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease, so it is of clinical importance to study super-resolution (SR) algorithms applied to CT images to improve the reso-lution of CT images. However, most of the existing SR algorithms are studied based on natural images, which are not suitable for medical images;and most of these algorithms improve the reconstruction quality by increasing the network depth, which is not suitable for machines with limited resources. To alleviate these issues, we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution (RFAFN). Specifically, we design a contextual feature extraction block (CFEB) that can extract CT image features more efficiently and accurately than ordinary residual blocks. In addition, we propose a feature-weighted cascading strategy (FWCS) based on attentional feature fusion blocks (AFFB) to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information. Finally, we suggest a global hierarchical feature fusion strategy (GHFFS), which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels. Numerous experiments show that our method performs better than most of the state-of-the-art (SOTA) methods on the COVID-19 chest CT dataset. In detail, the peak signal-to-noise ratio (PSNR) is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at x3 SR compared to the suboptimal method, but the number of parameters and multi-adds are reduced by 22K and 0.43G, respectively. Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.

Privacy-Preserving Fast Three-Factor Authentication and Key Agreement for IoT-Based E-Health Systems

Electronic healthcare (e-health) systems have received renewed interest, particularly in the current COVID-19 pandemic (e.g., lockdowns and changes in hospital policies due to the pandemic). However, ensuring security of both data-at-rest and data-in-transit remains challenging to achieve, particularly since data is collected and sent from less insecure devices (e.g., patients' wearable or home devices). While there have been a number of authentication schemes, such as those based on three-factor authentication, to provide authentication and privacy protection, a number of limitations associated with these schemes remain (e.g., (in)security or computationally expensive). In this study, we present a privacy-preserving three-factor authenticated key agreement scheme that is sufficiently lightweight for resource-constrained e-health systems. The proposed scheme enables both mutual authentication and session key negotiation in addition to privacy protection, with minimal computational cost. The security of the proposed scheme is demonstrated in the Real-or-Random model. Experiments using Raspberry Pi show that the proposed scheme achieves reduced computational cost (of up to 89.9% in comparison to three other related schemes).

Towards Secure and Privacy-Preserving Data Sharing for COVID-19 Medical Records: A Blockchain-Empowered Approach

COVID-19 is currently a major global public health challenge. In the battle against the outbreak of COVID-19, how to manage and share the COVID-19 Electric Medical Records (CEMRs) safely and effectively in the world, prevent malicious users from tampering with CEMRs, and protect the privacy of patients are very worthy of attention. In particular, the semi-trusted medical cloud platform has become the primary means of hospital medical data management and information services. Security and privacy issues in the medical cloud platform are more prominent and should be addressed with priority. To address these issues, on the basis of ciphertext policy attribute-based encryption, we propose a blockchain-empowered security and privacy protection scheme with traceable and direct revocation for COVID-19 medical records. In this scheme, we perform the blockchain for uniform identity authentication and all public keys, revocation lists, etc are stored on a blockchain. The system manager server is responsible for generating the system parameters and publishes the private keys for the COVID-19 medical practitioners and users. The cloud service provider (CSP) stores the CEMRs and generates the intermediate decryption parameters using policy matching. The user can calculate the decryption key if the user has private keys and intermediate decrypt parameters. Only when attributes are satisfied access policy and the user's identity is out of the revocation list, the user can get the intermediate parameters by CSP. The malicious users may track according to the tracking list and can be directly revoked. The security analysis demonstrates that the proposed scheme is indicated to be safe under the Decision Bilinear Diffie-Hellman (DBDH) assumption and can resist many attacks. The simulation experiment demonstrates that the communication and storage overhead is less than other schemes in the public-private key generation, CEMRs encryption, and decryption stages. Besides, we also verify that the proposed scheme works well in the blockchain in terms of both throughput and delay.

DuaNet: A Novel Lightweight CNN Model for Classifying Five-class Lung Diseases

Lung diseases rank among the world's top killers and disablers. Therefore, early identification is crucial for improving long-term survival rates and boosting the chances of recovery. Unlike the traditional method, machine learning (ML) showed great success in the medical field, mainly detecting and diagnosing different diseases. Most recently, the deep learning approach enhanced classification accuracy and eliminated the difficulty of manual feature extraction. As a literature conclusion, the model performance accuracy is inversely proportional to the number of lung diseases under consideration. In addition, no more than four classes (including normal) were considered previously. This work developed a lightweight CNN model, identified as DuaNet, with higher accuracy than the up-to-the-date models. The dataset has 930 X-ray images, categorized into five-class lung diseases: normal, tuberculosis, pneumonia COVID-19, pneumonia viral, and pneumonia bacterial. DuaNet comprises fifteen layers involving input, seven convolutional blocks, three max-pooling, three fully connected, and one output (Softmax) layer. Each convolutional block consists of a convolutional layer, Batch normalization, and ReLU activation function. The final model (DuaNet) obtained a performance accuracy of 99.87%, with 100% for other metrics. © 2022 IEEE.

Research and Optimization of a Lightweight Refined Mask-Wearing Detection Algorithm Based on an Attention Mechanism

To address the current problems of the incomplete classification of mask-wearing detection data, small-target miss detection, and the insufficient feature extraction capabilities of lightweight networks dealing with complex faces, a lightweight method with an attention mechanism for detecting mask wearing is presented in this paper. This study incorporated an "incorrect_mask” category into the dataset to address incomplete classification. Additionally, the YOLOv4-tiny model was enhanced with a prediction feature layer and feature fusion execution, expanding the detection scale range and improving the performance on small targets. A CBAM attention module was then introduced into the feature enhancement network, which re-screened the feature information of the region of interest to retain important feature information and improve the feature extraction capabilities. Finally, a focal loss function and an improved mosaic data enhancement strategy were used to enhance the target classification performance. The experimental results of classifying three objects demonstrate that the lightweight model's detection speed was not compromised while achieving a 2.08% increase in the average classification precision, which was only 0.69% lower than that of the YOLOv4 network. Therefore, this approach effectively improves the detection effect of the lightweight network for mask-wearing.

Detail-oriented capsule network for classification of CT scan images performing the detection of COVID-19.

COVID-19 is one of the biggest pandemics that the world is facing today, and every day, we are coming up with new challenges in this area. Still, much research is already going on to overcome this pandemic, and we also get succeeded to some extent. Diverse sources such as MRI, CT scanning, blood samples, X-ray image, and many more are available to detect COVID-19. Thus, it can be easily said that through image processing, the classification of COVID-19 can be done. In this study, the COVID-19 detection is done by classifying with the use of a type of convolutional neural network termed a detail-oriented capsule network. Chest CT scan imaging for the prediction of COVID-19 and non-COVID-19 are classified in the present paper using a Detailed Oriented capsule network (DOCN). Accuracy, specificity, and sensitivity are parameters used for model evaluation. The proposed model has achieved 98% accuracy, 81% sensitivity, and 98.4% specificity.

A Lightweight CNN Architecture for Chest X-ray Images Analysis to Facilitate Early Stage Detection of Lung Diseases

Lung-related diseases are one of the significant causes of death among infants and children. However, the mortality rate can be reduced by the detection of lung abnormality at an early stage. Traditionally, radiologists identify irregularities by interpreting chest x-ray images which is time-consuming. Therefore, researchers have proposed many automated systems for diagnosing pneumonia and other lung-related diseases. Due to the remarkable performance of Convolutional Neural Networks(CNN) in image classification, it has gained immense popularity in chest x-ray image analysis. Most of the research has utilized famous pre-trained Imagenet models for more accurate analysis of Chest X-ray images. However, the problem with these architectures is that they have many parameters that increase the training time, which makes the detection process lengthy. This paper introduces a lightweight, compact, and well-tuned CNN architecture with far fewer parameters than the pre-trained model to analyze two of the most common lung diseases, pneumonia and Covid-19. We have evaluated our model on two benchmark datasets. Experimental results show that our lightweight CNN model has far fewer hyperparameters than other state-of-the-art models but achieves similar results. We have achieved an accuracy of 90.38% on the kermany dataset and 96.90% on the Covid-19 Radiography dataset. © 2022 IEEE.

A Lightweight Segmentation Network Based on Weak Supervision for COVID-19 Detection

The Coronavirus Disease 2019 (COVID-19) outbreak in late 2019 threatens global health security. Computed tomography (CT) can provide richer information for the diagnosis and treatment of COVID-19. Unfortunately, labeling of COVID-19 lesion chest CT images is an expensive affair. We solved the challenge of chest CT labeling by simply marking point annotations to the lesion areas, i.e., by marking individual pixels for each lesion area in the chest CT scan. It takes only a few seconds to complete the labeling using this labeling strategy. We also designed a lightweight segmentation model with approximately 10% of the number of model parameters of the conventional model. So, the proposed model segmented the lesions of a single image in only 0.05 s. In order to obtain the shape and size of lesions from point labels, the convex-hull based segmentation (CHS) loss function is proposed in this paper, which enables the model to obtain an approximate fully supervised performance on point labels. The experiments were compared with the current state-of-the-art (SOTA) point label segmentation methods on the COVID-19-CT-Seg dataset, and our model showed a large improvement: IoU improved by 28.85%, DSC improved by 28.91%, Sens improved by 13.75%, Spes improved by 1.18%, and MAE decreased by 1.10%. Experiments on the dataset show that the proposed model combines the advantages of lightweight and weak supervision, resulting in more accurate COVID-19 lesion segmentation results while having only a 10% performance difference with the fully supervised approach. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Improving Radiology Report Generation via Object Dropout Strategy and MLP-based Captioner

Recently, automatically generating radiology reports has been addressed since it can not only relieve the pressure on doctors but also avoid misdiagnosis. Radiology report generation is a fundamental and critical step of auxiliary diagnosis. Due to the COVID-19 pandemic, a more accurate and robust structure for radiology report generation is urgently needed. Although radiology report generation is achieving remarkable progress, existing methods still face two main shortcomings. On the one hand, the strong noise in medical images usually interferes with the diagnosis process. On the other hand, these methods usually require complex structure while ignoring that efficiency is also an important metric for this task. To solve the two aforementioned problems, we introduce a novel method for medical report generation, the termed attention-guided object dropout MLP(ODM) model. In brief, ODM first incorporates a tailored pre-trained model to pre-align medical regions and corresponding language reports to capture text-related image features. Then, a fine-grained dropout strategy based on the attention matrix is proposed to relieve training pressure by dropping content-irrelevant information. Finally, inspired by the lightweight structure of Multilayer Perceptron(MLP), ODM adopts an MLP-based structure as an encoder to simplify the entire framework. Extensive experiments demonstrate the effectiveness of our ODM. More remarkably, ODM achieves state-of-the-art performance on IU X-Ray, MIMIC-CXR, and ROCO datasets, with the CIDEr-D score being increased from 26.8% to 41.4%, 21.1% to 30.2%, and 9.1% to 19.3%, respectively. © 2022 IEEE.

Exploring the Capabilities of a Lightweight CNN Model in Accurately Identifying Renal Abnormalities: Cysts, Stones, and Tumors, Using LIME and SHAP

Kidney abnormality is one of the major concerns in modern society, and it affects millions of people around the world. To diagnose different abnormalities in human kidneys, a narrow-beam x-ray imaging procedure, computed tomography, is used, which creates cross-sectional slices of the kidneys. Several deep-learning models have been successfully applied to computer tomography images for classification and segmentation purposes. However, it has been difficult for clinicians to interpret the model's specific decisions and, thus, creating a "black box” system. Additionally, it has been difficult to integrate complex deep-learning models for internet-of-medical-things devices due to demanding training parameters and memory-resource cost. To overcome these issues, this study proposed (1) a lightweight customized convolutional neural network to detect kidney cysts, stones, and tumors and (2) understandable AI Shapely values based on the Shapley additive explanation and predictive results based on the local interpretable model-agnostic explanations to illustrate the deep-learning model. The proposed CNN model performed better than other state-of-the-art methods and obtained an accuracy of 99.52 ± 0.84% for K = 10-fold of stratified sampling. With improved results and better interpretive power, the proposed work provides clinicians with conclusive and understandable results.

An Efficient Medicine Identification and Delivery System Based on Mobile Manipulation Robot

In recent years, with the emergence of COVID-19, the shortage of medical resources has become increasingly obvious. However, current environments such as hospital wards still require a large number of medical staff to deliver medicines. In this paper, we propose a mobile robot that can complete medicine grabbing and delivery in a hospital ward scenario. First, a lightweight neural network is built to improve the detection efficiency of Faster R-CNN algorithm for boxed medicine. Then, the pose of the robotic arm grasping the pill box is determined by point cloud matching to control the mechanical grasping of the pill box. Finally, a discomfort function representing the collision risk between the robot and the pedestrian is incorporated into the Risk-RRT algorithm to improve the navigation performance of the algorithm. By building a real experimental platform, the experiments verify the performance of our proposed medicine delivery robot system. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

An evaluation of lightweight deep learning techniques in medical imaging for high precision COVID-19 diagnostics

Timely and rapid diagnoses are core to informing on optimum interventions that curb the spread of COVID-19. The use of medical images such as chest X-rays and CTs has been advocated to supplement the Reverse-Transcription Polymerase Chain Reaction (RT-PCR) test, which in turn has stimulated the application of deep learning techniques in the development of automated systems for the detection of infections. Decision support systems relax the challenges inherent to the physical examination of images, which is both time consuming and requires interpretation by highly trained clinicians. A review of relevant reported studies to date shows that most deep learning algorithms utilised approaches are not amenable to implementation on resource-constrained devices. Given the rate of infections is increasing, rapid, trusted diagnoses are a central tool in the management of the spread, mandating a need for a low-cost and mobile point-of-care detection systems, especially for middle- and low-income nations. The paper presents the development and evaluation of the performance of lightweight deep learning technique for the detection of COVID-19 using the MobileNetV2 model. Results demonstrate that the performance of the lightweight deep learning model is competitive with respect to heavyweight models but delivers a significant increase in the efficiency of deployment, notably in the lowering of the cost and memory requirements of computing resources. © 2022 The Author(s)

LiMS-Net: A Lightweight Multi-Scale CNN for COVID-19 Detection from Chest CT Scans

Recent years have witnessed a rise in employing deep learning methods, especially convolutional neural networks (CNNs) for detection of COVID-19 cases using chest CT scans. Most of the state-of-the-art models demand a huge amount of parameters which often suffer from overfitting in the presence of limited training samples such as chest CT data and thereby, reducing the detection performance. To handle these issues, in this paper, a lightweight multi-scale CNN called LiMS-Net is proposed. The LiMS-Net contains two feature learning blocks where, in each block, filters of different sizes are applied in parallel to derive multi-scale features from the suspicious regions and an additional filter is subsequently employed to capture discriminant features. The model has only 2.53M parameters and therefore, requires low computational cost and memory space when compared to pretrained CNN architectures. Comprehensive experiments are carried out using a publicly available COVID-19 CT dataset and the results demonstrate that the proposed model achieves higher performance than many pretrained CNN models and state-of-the-art methods even in the presence of limited CT data. Our model achieves an accuracy of 92.11% and an F1-score of 92.59% for detection of COVID-19 from CT scans. Further, the results on a relatively larger CT dataset indicate the effectiveness of the proposed model. © 2023 Association for Computing Machinery.

SuperMini-seg: An ultra lightweight network for COVID-19 lung infection segmentation from CT images.

The automatic segmentation of lung lesions from COVID-19 computed tomography (CT) images is helpful in establishing a quantitative model to diagnose and treat COVID-19. To this end, this study proposes a lightweight segmentation network called the SuperMini-Seg. We propose a new module called the transformer parallel convolution module (TPCB), which introduces both transformer and convolution operations in one module. SuperMini-seg adopts the structure of a double-branch parallel to downsample the image and designs a gated attention mechanism in the middle of the two parallel branches. At the same time, the attentive hierarchical spatial pyramid (AHSP) module and criss-cross attention module are adopted, and more than 100K parameters are present in the model. At the same time, the model is scalable, and the parameter quantity of SuperMini-seg-V2 reaches more than 70K. Compared with other advanced methods, the segmentation accuracy was almost reached the state-of-art method. The calculation efficiency was high, which is convenient for practical deployment.

LightR-YOLOv5: A compact rotating detector for SARS-CoV-2 antigen-detection rapid diagnostic test results.

Nucleic acid testing is currently the golden reference for coronaviruses (SARS-CoV-2) detection, while the SARS-CoV-2 antigen-detection rapid diagnostic tests (RDT) is an important adjunct. RDT can be widely used in the community or regional screening management as self-test tools and may need to be verified by healthcare authorities. However, manual verification of RDT results is a time-consuming task, and existing object detection algorithms usually suffer from high model complexity and computational effort, making them difficult to deploy. We propose LightR-YOLOv5, a compact rotating SARS-CoV-2 antigen-detection RDT results detector. Firstly, we employ an extremely light-weight L-ShuffleNetV2 network as a feature extraction network with a slight reduction in recognition accuracy. Secondly, we combine semantic and texture features in different layers by judiciously combining and employing GSConv, depth-wise convolution, and other modules, and further employ the NAM attention to locate the RDT result detection region. Furthermore, we propose a new data augmentation approach, Single-Copy-Paste, for increasing data samples for the specific task of RDT result detection while achieving a small improvement in model accuracy. Compared with some mainstream rotating object detection networks, the model size of our LightR-YOLOv5 is only 2.03MB, and it is 12.6%, 6.4%, and 7.3% higher in mAP@.5:.95 metrics compared to RetianNet, FCOS, and R3Det, respectively.

Lightweight deep CNN-based models for early detection of COVID-19 patients from chest X-ray images.

Hundreds of millions of people worldwide have recently been infected by the novel Coronavirus disease (COVID-19), causing significant damage to the health, economy, and welfare of the world's population. Moreover, the unprecedented number of patients with COVID-19 has placed a massive burden on healthcare centers, making timely and rapid diagnosis challenging. A crucial step in minimizing the impact of such problems is to automatically detect infected patients and place them under special care as quickly as possible. Deep learning algorithms, such as Convolutional Neural Networks (CNN), can be used to meet this need. Despite the desired results, most of the existing deep learning-based models were built on millions of parameters (weights), which are not applicable to devices with limited resources. Inspired by such fact, in this research, we developed two new lightweight CNN-based diagnostic models for the automatic and early detection of COVID-19 subjects from chest X-ray images. The first model was built for binary classification (COVID-19 and Normal), whereas the second one was built for multiclass classification (COVID-19, viral pneumonia, or normal). The proposed models were tested on a relatively large dataset of chest X-ray images, and the results showed that the accuracy rates of the 2- and 3-class-based classification models are 98.55% and 96.83%, respectively. The results also revealed that our models achieved competitive performance compared with the existing heavyweight models while significantly reducing cost and memory requirements for computing resources. With these findings, we can indicate that our models are helpful to clinicians in making insightful diagnoses of COVID-19 and are potentially easily deployable on devices with limited computational power and resources.

An efficient lightweight encryption model with re-encryption scheme to create robust blockchain architecture for COVID-19 data

Handling electronic health records from the Internet of Medical Things is one of the most challenging research areas as it consists of sensitive information, which targets attackers. Also, dealing with modern healthcare systems is highly complex and expensive, requiring much secured storage space. However, blockchain technology can mitigate these problems through improved health record management. The proposed work develops a scalable, lightweight framework based on blockchain technology to improve COVID-19 data security, scalability and patient privacy. Initially, the COVID-19 related data records are hashed using the enhanced Merkle tree data structure. The hashed values are encrypted by lattice based cryptography with a Homomorphic proxy re-encryption scheme in which the input data are secured. After completing the encryption process, the blockchain uses inter planetary file system to store secured information. Finally, the Proof of Work concept is utilized to validate the security of the input COVID based data records. The proposed work's experimental setup is performed using the Python tool. The performance metrics like encryption time, re-encryption time, decryption time, overall processing time, and latency prove the efficacy of the proposed schemes. © 2022 John Wiley & Sons Ltd.

SELDNet: Sequenced encoder and lightweight decoder network for COVID-19 infection region segmentation.

Segmenting regions of lung infection from computed tomography (CT) images shows excellent potential for rapid and accurate quantifying of Coronavirus disease 2019 (COVID-19) infection and determining disease development and treatment approaches. However, a number of challenges remain, including the complexity of imaging features and their variability with disease progression, as well as the high similarity to other lung diseases, which makes feature extraction difficult. To answer the above challenges, we propose a new sequence encoder and lightweight decoder network for medical image segmentation model (SELDNet). (i) Construct sequence encoders and lightweight decoders based on Transformer and deep separable convolution, respectively, to achieve different fine-grained feature extraction. (ii) Design a semantic association module based on cross-attention mechanism between encoder and decoder to enhance the fusion of different levels of semantics. The experimental results showed that the network can effectively achieve segmentation of COVID-19 infected regions. The dice of the segmentation result was 79.1%, the sensitivity was 76.3%, and the specificity was 96.7%. Compared with several state-of-the-art image segmentation models, our proposed SELDNet model achieves better results in the segmentation task of COVID-19 infected regions.

Past, present and future prospective of global carbon fibre composite developments and applications

Carbon fibre and carbon fibre reinforced polymer matrix composites (CFRPs) are important lightweight materials for aerospace, automotive, rail transport, infrastructure, and renewable energy applications. This paper provides a comprehensive review on the history of carbon fibres and carbon fibre composites, the current global CFRPs consumption, and trends for future developments in the aerospace, wind turbine, automotive, pressure vessels, sports and leisure, and construction sectors. The history of carbon fibres and CFRPs is discussed over four representative periods including their early development (1950–60's), growth of carbon fibre composites industry (1970–80's), major adoption of carbon fibre composites (the first wave, 1990–2000's), and expanded use of carbon fibre composites (the second wave, 2010's and beyond). Despite a 37% decline of carbon fibre consumption in the aerospace industry in 2021 caused by COVID-19, the global CFRP demand was around 181 kt which more than doubled its value in 2014. There is tangible projected increase over the next five years and the demand for CFRPs is expected to reach 285 kt in 2025, mainly attributed from the fast expansion of non-aerospace industries such as the wind energy sector. Lower cost carbon fibres (e.g., large tow) and associated manufacturing technologies are continually evolving. Finally, the implications of emerging materials and manufacturing methods in conjunction with recycling and reuse for carbon fibre composites are discussed. [ FROM AUTHOR]

MMViT-Seg: A lightweight transformer and CNN fusion network for COVID-19 segmentation.

BACKGROUND AND OBJECTIVE: COVID-19 is a serious threat to human health. Traditional convolutional neural networks (CNNs) can realize medical image segmentation, whilst transformers can be used to perform machine vision tasks, because they have a better ability to capture long-range relationships than CNNs. The combination of CNN and transformers to complete the task of semantic segmentation has attracted intense research. Currently, it is challenging to segment medical images on limited data sets like that on COVID-19. METHODS: This study proposes a lightweight transformer+CNN model, in which the encoder sub-network is a two-path design that enables both the global dependence of image features and the low layer spatial details to be effectively captured. Using CNN and MobileViT to jointly extract image features reduces the amount of computation and complexity of the model as well as improves the segmentation performance. So this model is titled Mini-MobileViT-Seg (MMViT-Seg). In addition, a multi query attention (MQA) module is proposed to fuse the multi-scale features from different levels of decoder sub-network, further improving the performance of the model. MQA can simultaneously fuse multi-input, multi-scale low-level feature maps and high-level feature maps as well as conduct end-to-end supervised learning guided by ground truth. RESULTS: The two-class infection labeling experiments were conducted based on three datasets. The final results show that the proposed model has the best performance and the minimum number of parameters among five popular semantic segmentation algorithms. In multi-class infection labeling results, the proposed model also achieved competitive performance. CONCLUSIONS: The proposed MMViT-Seg is tested on three COVID-19 segmentation datasets, with results showing that this model has better performance than other models. In addition, the proposed MQA module, which can effectively fuse multi-scale features of different levels further improves the segmentation accuracy.