The lifestyle of modern society is a major contributing factor for the majority of patients suffering from more than one disease. To Screen and diagnose each of those diseases, there is a great need for portable, and economical diagnostic tools, which are highly stipulated to yield rapid and accurate results using a small volume of the samples such as blood, saliva, sweat, etc. Point-of-care Testing (POCT) is one of the approaches to harvest prompt diagnosis of numerous diseases. The Majority of Point-of-Care Devices (POCD) are developed to diagnose one disease within the specimen. On the other hand, multi-disease detection capabilities in the same point-of-care devices are considered to be an efficient candidate to execute the state-of-the-art platform for multi-disease detection. Most of the literature reviews in this field focus on Point-of-Care (POC) devices, their underlying principles of operation, and their potential applications. It is evident from a perusal of the scholarly works that no review articles have been written on multi-disease detection PoC devices. A review study analyzing the current level and functionality of multi-disease detection POC devices would be of great use to future researchers and device manufacturers. This review paper is addressing the above gap by focusing on various optical techniques like fluorescence, Absorbance, and Surface Plasmon Resonance (SPR) for multi-disease detection by harnessing the microfluidic-based POC device.
Each year, millions of people experience the terrible effects of malaria in different parts of the world. Humans fall sick by malaria through infected female Anopheles mosquitoes. Despite recent advancements in the field, microscopy remains the most common method for diagnosing malaria. Recent strides in the domains of signal processing, image processing, and sensing, through the application of artificial intelligence, especially machine learning and deep learning have yielded cost-effective solutions that improve diagnostic accuracy. In this work, we propose a tweaked version of the YOLOv5 framework, incorporating image signal processing techniques for screening malaria-infected cells and comparing it with established methods that highlight the pivotal role of sensing technologies. Our innovation revolves around two pivotal modifications. The conventional C3 module in YOLOv5 is replaced by the innovative C3TR structure, leveraging signal processing to facilitate the extraction of precise object properties while minimizing the interference of the image background. The PANet structure in the neck has been upgraded to the state-of-the-art BiFPN architecture harnessing image processing techniques to further extract the features of objects. The outcomes of our model are remarkable with an accuracy of 99.2%, a precision of 98.7%, and a recall of 98.5%. With these results, our model outperformed many of the existing methodologies which highlighted the crucial importance of image signal analysis and sensing technologies in transforming malaria detection and classification.
28 October 2024 in International Journal of Imaging Systems and Technology