Human Body-Related Disease Diagnosis Systems Using CMOS Image Sensors: A Systematic Review

Abstract

According to the Center for Disease Control and Prevention (CDC), the average human life expectancy is 78.8 years. Specifically, 3.2 million deaths are reported yearly due to heart disease, cancer, Alzheimer’s disease, diabetes, and COVID-19. Diagnosing the disease is mandatory in the current way of living to avoid unfortunate deaths and maintain average life expectancy. CMOS image sensor (CIS) became a prominent technology in assisting the monitoring and clinical diagnosis devices to treat diseases in the medical domain. To address the significance of CMOS image ‘sensors’ usage in disease diagnosis systems, this paper focuses on the CIS incorporated disease diagnosis systems related to vital organs of the human body like the heart, lungs, brain, eyes, intestines, bones, skin, blood, and bacteria cells causing diseases. This literature survey’s main objective is to evaluate the ‘systems’ capabilities and highlight the most potent ones with advantages, disadvantages, and accuracy, that are used in disease diagnosis. This systematic review used PRISMA workflow for study selection methodology, and the parameter-based evaluation is performed on disease diagnosis systems related to the human body’s organs. The corresponding CIS models used in systems are mapped organ-wise, and the data collected over the last decade are tabulated.

A Hybrid Model for Driver Emotion Detection Using Feature Fusion Approach

“…The second direction utilizes the information from physiological signals such as electrocardiogram (E.C.G) [ 10 ], electroencephalogram (E.E.G) [ 11 ], photo plethysmography (P.P.G) [ 12 ], electrical dermal activity (E.D.A) [ 13 ] by connecting physical sensors to the human body [ 14 ] that is difficult to focus on driving due to these body-worn sensors. To overcome this problem, the third direction is evolved by analyzing the image captured by the camera sensor inside the vehicle to track the driver’s emotions without any physical contact.…”

Deep Neural Network Approach for Pose, Illumination, and Occlusion Invariant Driver Emotion Detection

“…Ooi et al [ 11 ] in 2016 proposed a driver emotion recognition framework based on electrodermal activity (E.D.A.) measurements with medical diagnosable physical sensors [ 38 ] using SVMs to predict the driver’s emotions. In 2010, Nasoz et al [ 39 ] introduced a driver emotion system using K.N.N.…”

“…Among all these works, some results [ 15 , 25 , 26 , 28 , 31 , 33 ] have proposed systems running in a non-car environment, whereas works [ 20 , 29 , 37 , 40 , 41 , 42 ] have been conducted in a real-time environment. Some results [ 14 , 16 , 17 , 18 , 24 , 30 , 38 , 39 ] have used a simulator environment.…”

Modified Self-Adaptive Bayesian Algorithm for Smart Heart Disease Prediction in IoT System

“…Figure 1 depicts the causes of heart disease: cardiovascular arrests, coronary artery disease (CAD), vascular disease, circulatory diseases, etc. To prevent tragic deaths and preserve the average lifespan, a condition must be diagnosed [6]. The Internet of Things (IoT), computer networking, and 5G are examples of automated networks that are used in healthcare.…”