Smart IoMT-based segmentation of coronavirus infections using lung CT scans

Karar, Mohamed Esmail; Khan, Faizal Z; Alshahrani, Hussain; Reyad, Omar

doi:10.1016/j.aej.2023.02.020

Cited by 7 publications

(4 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2023, Mohamed et al [ 21 ] proposed integrating SENets within the IoMT framework to automate the Segmentation of COVID-19 infections in lung CT images. This integration incorporated SE blocks directly into DRN to create Seresnets based on LinkNet and U-Net models.…”

Section: Literature Reviewmentioning

confidence: 99%

“…However, the adopted framework must simultaneously address segmentation and disease classification tasks. The SENets were developed in [ 21 ] that offer a structure similarity index, higher Dice score, enhanced alignment measure, and low mean absolute error; nevertheless, the chosen approach necessitated the inclusion of additional datasets from various medical imaging modalities. The improved firefly algorithm was employed in [ 22 ], which offers less running time, good accuracy, and sensitivity; however, further investigation is required to explore variations in segmentation accuracy across different CT images.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Segmenting and classifying lung diseases with M-Segnet and Hybrid Squeezenet-CNN architecture on CT images

Shafi,

Chinnappan

2024

PLoS ONE

View full text Add to dashboard Cite

Diagnosing lung diseases accurately and promptly is essential for effectively managing this significant public health challenge on a global scale. This paper introduces a new framework called Modified Segnet-based Lung Disease Segmentation and Severity Classification (MSLDSSC). The MSLDSSC model comprises four phases: "preprocessing, segmentation, feature extraction, and classification." Initially, the input image undergoes preprocessing using an improved Wiener filter technique. This technique estimates the power spectral density of the noisy and original images and computes the SNR assisted by PSNR to evaluate image quality. Next, the preprocessed image undergoes Segmentation to identify and separate the RoI from the background objects in the lung image. We employ a Modified Segnet mechanism that utilizes a proposed hard tanh-Softplus activation function for effective Segmentation. Following Segmentation, features such as MLDN, entropy with MRELBP, shape features, and deep features are extracted. Following the feature extraction phase, the retrieved feature set is input into a hybrid severity classification model. This hybrid model comprises two classifiers: SDPA-Squeezenet and DCNN. These classifiers train on the retrieved feature set and effectively classify the severity level of lung diseases.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Segmenting and classifying lung diseases with M-Segnet and Hybrid Squeezenet-CNN architecture on CT images

Shafi,

Chinnappan

2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…This implies that the end-user is unable to take preventative steps to stop such changeable data attacks. As a result, several researchers have concentrated on designing methods for imaging security in medical applications [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Medical Image Privacy Enhancement Using Key Extension of Advanced Encryption Standard

Reyad,

Mansour,

Zanaty

et al. 2024

Sohag Journal of Sciences

View full text Add to dashboard Cite

In recent years, conventional encryption techniques cannot be used directly in the transmission of electronic health data. The main reason is the restrictions on data quantity, data multitude, and storage assimilation, particularly in the case that patient private data is sent through unsecured paths. Because image structure differs from textual information considering two unique elements which are damage to data and violation of confidentiality, some patients may miss out the privacy and in bad cases the integrity of owned data contents. So, an encryption scheme is required so that medical data and information can be privately shared over the Internet with other data centers without being concerned significantly about privacy breaches. This study aims at enhancing the privacy of medical images and offers protection from intrusion assaults. The proposed method makes encryption and decryption more secure and robust by using a key extension in the key schedule of the advanced encryption standard (AES) algorithm. Various safety evaluation metrics are used such as histogram, entropy, number of pixels change rate (NPCR), and correlation coefficient. The test of unified average changing intensity (UACI) is also computed. Finally, the test scores obtained show high values of the suggested medical image ciphering model is effective and convenient for health data transmission.

show abstract

“…In the case of the IoMT, two main factors raise the temperature of the system. Radiation through the antenna is the first cause, while the consumption of power is the other major cause [50].…”

mentioning

confidence: 99%

Towards a Secure and Sustainable Internet of Medical Things (IoMT): Requirements, Design Challenges, Security Techniques, and Future Trends

et al. 2023

View full text Add to dashboard Cite

Recent advances in machine-to-machine (M2M) communications, mini-hardware manufacturing, and micro computing have led to the development of the Internet of Things (IoT). The IoT is integrated with medical devices in order to enable better treatment, cost-effective medical solutions, improved patient monitoring, and enhanced personalized healthcare. This has led to the development of more complex and heterogeneous Internet of Medical Things (IoMT) systems that have their own operating systems and protocols. Even though such pervasive and low-cost sensing devices can bring about enormous changes in the healthcare sector, these are prone to numerous security and privacy issues. Security is thus a major challenge in these critical systems, one that inhibits their widespread adoption. However, significant inroads have been made by the on-going research, which powers the IoMT applications by incorporating prevalent security measures. In this regard, this paper highlights the significance of implementing key security measures, and essential aspects of the IoMT that make it useful for interconnecting various internal and external working domains of healthcare. This paper presents state-of-the-art techniques for securing IoMT systems, in terms of data transmission, collection, and storage. Furthermore, the paper also explores various security requirements, inherent design challenges, and various security techniques that could make the IoMT more secure and sustainable. Finally, the paper gives a panoramic view of the current status of research in the field and outlines some future research directions in this area.

show abstract

Smart IoMT-based segmentation of coronavirus infections using lung CT scans

Cited by 7 publications

References 54 publications

Segmenting and classifying lung diseases with M-Segnet and Hybrid Squeezenet-CNN architecture on CT images

Segmenting and classifying lung diseases with M-Segnet and Hybrid Squeezenet-CNN architecture on CT images

Medical Image Privacy Enhancement Using Key Extension of Advanced Encryption Standard

Towards a Secure and Sustainable Internet of Medical Things (IoMT): Requirements, Design Challenges, Security Techniques, and Future Trends

Contact Info

Product

Resources

About