Dual-Level Security based Cyclic18 Steganographic Method and its Application for Secure Transmission of Keyframes during Wireless Capsule Endoscopy

Image Data Security Mechanism Based on the Internet of Things Cardiac Catheterization Laboratory Information Management System Research and Design

With the development of science and technology, more and more operations are performed in the cardiac catheterization laboratory. During such operations, a lot of relevant imaging data need to be retained. These imaging data can be used for clinical and scientific research and teaching applications, but imaging data security has also become an increasingly important issue. This article is based on the Internet of Things cardiac catheterization laboratory information management system image data security mechanism system research. First of all, this article adopts the literature method to study the application research of the Internet of Things technology in the medical field, as well as the relevant medical imaging data security technology methods. Then, the medical image data security mechanism was designed, and the image data security model of the cardiac catheterization laboratory information management system based on the Internet of Things was established. Finally, the application of decentralized management of the Internet of Things RFID technology on medical equipment and the security of the application of this technology on medical imaging data are analyzed, and finally a conclusion is drawn. The image data security mechanism established in this article is based on the Internet of Things technology. The security rate of image information data reaches more than 95%, the information data security level reaches level 1, and the average data missing rate is only 4.7%. It is a brand-new breakthrough, hoping to further improve the efficiency of hospital information management and protect the safety of medical information.

Deep Learning for Multigrade Brain Tumor Classification in Smart Healthcare Systems: A Prospective Survey

Brain tumor is one of the most dangerous cancers in people of all ages, and its grade recognition is a challenging problem for radiologists in health monitoring and automated diagnosis. Recently, numerous methods based on deep learning have been presented in the literature for brain tumor classification (BTC) in order to assist radiologists for a better diagnostic analysis. In this overview, we present an in-depth review of the surveys published so far and recent deep learning-based methods for BTC. Our survey covers the main steps of deep learning-based BTC methods, including preprocessing, features extraction, and classification, along with their achievements and limitations. We also investigate the state-of-the-art convolutional neural network models for BTC by performing extensive experiments using transfer learning with and without data augmentation. Furthermore, this overview describes available benchmark data sets used for the evaluation of BTC. Finally, this survey does not only look into the past literature on the topic but also steps on it to delve into the future of this area and enumerates some research directions that should be followed in the future, especially for personalized and smart healthcare.

Secure Framework for Internet of Things Based e-Health System

Internet of Things (IoT) is the emerging technology finding applications in a wide range of fields that include smart homes, intelligent transportation, e-health, supply chain management. Among IoT applications, e-health is one of the most promising application in which smart devices capable of monitoring physiological parameters of patients are implanted in or around their bodies which automatically sense and transmit collected data to medical consultants. However, security issues for electronic patient records (EPR) in-transit hinder the usage of IoT in e-health systems. Among these issues, EPR confidentiality and entity authentication are major concerns. In this article, confidentiality of EPR and its secure transmission over network is focused mainly. A security framework is proposed where-in smart devices encrypt sensed physiological data with Light-Weight Encryption Algorithm and Advanced Encryption Standard cryptographic algorithms. The security framework and the designed protocol provides better security and are energy efficient as presented in the evaluation section.

Biometrics-Based RSA Cryptosystem for Securing Real-Time Communication

Real-time online communication technology has become increasingly important in modern business applications. It allows people to easily connect with business partners over the Internet through the camera lens on digital devices. However, despite the fact that users can identify and confirm the identity of the person in front of the camera, they cannot verify the authenticity of messages between communication partners. It is because the tunnel for the video is not the same as the tunnel that delivers the messages. To protect confidential messages, it is essential to establish a secure communication channel between users. This paper proposes a biometrics-based RSA cryptosystem to secure real-time communication in business. The idea put forward is to generate a cryptographic public key based on a user’s biometric information without using Public Key Infrastructure (PKI) and establish a secured channel in a public network. In such a way, the key must be verified with the user’s biometrics online. Since the key is derived from the user’s biometrics, it is strongly user-dependent and works well to convince others of the authenticity of the owner. Additionally, the derived biometric key is self-certified with the user’s biometrics, which means the cost of certificate storage, delivery and revocation can be significantly reduced.

Visual saliency models for summarization of diagnostic hysteroscopy videos in healthcare systems

In clinical practice, diagnostic hysteroscopy (DH) videos are recorded in full which are stored in long-term video libraries for later inspection of previous diagnosis, research and training, and as an evidence for patients' complaints. However, a limited number of frames are required for actual diagnosis, which can be extracted using video summarization (VS). Unfortunately, the general-purpose VS methods are not much effective for DH videos due to their significant level of similarity in terms of color and texture, unedited contents, and lack of shot boundaries. Therefore, in this paper, we investigate visual saliency models for effective abstraction of DH videos by extracting the diagnostically important frames. The objective of this study is to analyze the performance of various visual saliency models with consideration of domain knowledge and nominate the best saliency model for DH video summarization in healthcare systems. Our experimental results indicate that a hybrid saliency model, comprising of motion, contrast, texture, and curvature saliency, is the more suitable saliency model for summarization of DH videos in terms of extracted keyframes and accuracy.