Automated Segmentation of Lung Parenchyma Using Colour Based Fuzzy C-Means Clustering

Khan, Z. Faizal

doi:10.1007/s42835-019-00224-8

Cited by 12 publications

(14 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These security threats are inherent to the system design. These threats can be classified into various categories such as data collection level [ 8 , 9 , 10 ], transmission level [ 11 , 12 , 13 , 14 ] and storage level [ 15 , 16 ], which are described more clearly in Section 3 . Due to these threats in security and privacy of the EHR data, some users are not ready to use these applications.…”

Section: Related Workmentioning

confidence: 99%

Quantum Diffie–Hellman Extended to Dynamic Quantum Group Key Agreement for e-Healthcare Multi-Agent Systems in Smart Cities

Naresh¹,

Nasralla

Reddi

et al. 2020

Sensors

View full text Add to dashboard Cite

Multi-Agent Systems can support e-Healthcare applications for improving quality of life of citizens. In this direction, we propose a healthcare system architecture named smart healthcare city. First, we divide a given city into various zones and then we propose a zonal level three-layered system architecture. Further, for effectiveness we introduce a Multi-Agent System (MAS) in this three-layered architecture. Protecting sensitive health information of citizens is a major security concern. Group key agreement (GKA) is the corner stone for securely sharing the healthcare data among the healthcare stakeholders of the city. For establishing GKA, many efficient cryptosystems are available in the classical field. However, they are yet dependent on the supposition that some computational problems are infeasible. In light of quantum mechanics, a new field emerges to share a secret key among two or more members. The unbreakable and highly secure features of key agreement based on fundamental laws of physics allow us to propose a Quantum GKA (QGKA) technique based on renowned Quantum Diffie–Hellman (QDH). In this, a node acts as a Group Controller (GC) and forms 2-party groups with remaining nodes, establishing a QDH-style shared key per each two-party. It then joins these keys into a single group key by means of a XOR-operation, acting as a usual group node. Furthermore, we extend the QGKA to Dynamic QGKA (DQGKA) by adding join and leave protocol. Our protocol performance was compared with existing QGKA protocols in terms of Qubit efficiency (QE), unitary operation (UO), unitary operation efficiency (UOE), key consistency check (KCC), security against participants attack (SAP) and satisfactory results were obtained. The security analysis of the proposed technique is based on unconditional security of QDH. Moreover, it is secured against internal and external attack. In this way, e-healthcare Multi-Agent System can be robust against future quantum-based attacks.

show abstract

Section: Related Workmentioning

confidence: 99%

Quantum Diffie–Hellman Extended to Dynamic Quantum Group Key Agreement for e-Healthcare Multi-Agent Systems in Smart Cities

Naresh¹,

Nasralla

Reddi

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…At last, the average accuracy of segmentation of CT images of the lungs reached 0.9946. Khan [14] proposed a novel approach for segmenting lung parenchyma using the combination of colour features and improved fuzzy-C means clustering in this paper. This method overcomes the disadvantages of existing CT lung parenchyma segmentation techniques since it combines the color features of different pixels present in the entire image.…”

Section: ) Lung Segmentation Algorithms Based On Pixels Of Lung Ct Imentioning

confidence: 99%

“…where A represents the area segmented by the algorithm, in addition B represents the area marked manually. When the result of neural network segmentation is better, the value of Furthermore, the accuracy of LDDNet is higher than the traditional methods [8], [14], [19]. From above, the conclusion can be drawn that LDDNet has better performance than most of the traditional methods.…”

Section: Metrics and Measurements For Experimentsmentioning

confidence: 99%

A Lung Dense Deep Convolution Neural Network for Robust Lung Parenchyma Segmentation

Chen

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Lung parenchyma segmentation is the prerequisite for an automatic diagnosis system to analyze lung CT (computed tomography) images. However, traditional lung segmentation algorithms have poor adaptability and are not effectively robust regarding lung databases with blood vessels and small voids which can interfere the segmentation. The main work of this paper is as follows: Firstly, a lung dense deep convolutional neural network (LDDNet) is proposed, which adopts some popular optimizer methods, such as dense block, batch normalization (BN) and dropout. The performance of LDDNet is tested on the public lung database LIDC-IDRI which contains many cases of interference for segmentation. Secondly, the labeled with blood vessels and small voids are not contained by the public ground-truth masks of the LIDC-IDRI database, therefore these regions are labeled by us with LabelMe software. Thirdly, for the aim of exploring the effect of image preprocessing on segmenting lung CT images with deep neural network, contrast enhancing, median filtering and Laplacian filtering are used to preprocess the image as comparative experiments. Finally, dataset is classified into four classes by the geometrical shapes to test the performance of LDDNet. The accuracy of the segmentation experiment reaches over 99% and the four classes can all reach over 95%. Additionally, blood vessels and small voids are segmented out from the lung parenchyma which is not achieved by other methods. Experimental results confirm that the proposed LDDNet can segment the lung parenchymal area more accurately and has better robustness in comparison with other neural networks and most of the traditional methods. INDEX TERMS Deep dense neural network, lung segmentation, robustness.

show abstract

“…This sort of unauthorised access affects the overall performance of healthcare systems [6]. Networks present in the hospitals [21,5] can be easily accessed by the hackers. Jamming based attack, collision based attack, de-synchronization based attacks, spoofing and selective forwarding based attacks are the common types of attacks that is done so far during the stage data collection.…”

Section: Related Studiesmentioning

confidence: 99%

“…In these EHRs, the authorised persons can be the patients or the doctors. The data present in the servers can be available in local or cloud based which stores, analyse the stored health data [5]. The components which are present in the networks can be the inter connector between the patients and the medical staff for enhancing the broadcasting and distribution of data [6].…”

Section: Introductionmentioning

confidence: 99%

Application of Intelligent Multi Agent Based Systems For E-Healthcare Security

2019

Inf. Sci. Lett.

View full text Add to dashboard Cite

In recent years, availability and usage of extensive systems for Electronic Healthcare Record (EHR) is increased. In medical centers such hospitals and other laboratories, more health data sets were formed during the treatment process. In order to enhance the standard of the services provided in healthcare, these records where shared and can be used by various users depends on their requirements. As a result, notable issues in the security and privacy where obtained which should be monitored and removed in order to make the use of EHR more effectively. Various researches have been done in the past literature for improving the standards of the security and privacy in E-health systems. In spite of this, it is not completely enhanced. In this paper, a comprehensive analysis is done by selecting the existing approaches and models which were proposed for the security and privacy of the E-healthcare systems. Also, a novel Intelligent-based Access Control Security Model (IBAC) based on multi agents is proposed to maintain and support the security and privacy of E-healthcare systems. This system uses agents in order to maintain security and privacy while accessing the E-health data between the users.

show abstract

Automated Segmentation of Lung Parenchyma Using Colour Based Fuzzy C-Means Clustering

Cited by 12 publications

References 24 publications

Quantum Diffie–Hellman Extended to Dynamic Quantum Group Key Agreement for e-Healthcare Multi-Agent Systems in Smart Cities

Quantum Diffie–Hellman Extended to Dynamic Quantum Group Key Agreement for e-Healthcare Multi-Agent Systems in Smart Cities

A Lung Dense Deep Convolution Neural Network for Robust Lung Parenchyma Segmentation

Application of Intelligent Multi Agent Based Systems For E-Healthcare Security

Contact Info

Product

Resources

About