Article Preview
Top1. Introduction
In the current era, the rapid growth in science and technology helped the human community by providing a number of facilities to lead a pleasant and modern life. The technological advancement, such as the high speed internet facilities further reduced the communication barrier among humans and supports a fast data transmission between two users (nodes) with a considerable security with end to end encryption. The recent developments in internet associated applications, such as Internet of Things (IoT), Industrial Internet of Things (IIoT) and Internet of Medical Things (IoMT) also expanded the application of the internet in variety of domains (Jaleel et al., 2020; Manogaran et al., 2018; Taniar, Leung, Rahayu et al, 2008; Taniar, Rahayu, Lee et al, 2008).
The main advantage of this facility includes; (i) Efficient data collection and transmission, (ii) Interoperability, (iii) Remote monitoring, storage and retrieval, and (iv) Centralized and distributed control with better end to end encryption. The invention of the IoMT concept modernized the medical domain and it facilitates in the field-level as well as the remote monitoring of the patient with improved accuracy. The IoMT includes a sufficient sensor array, a field/remote monitoring device and a communication network. The performance of the IoMT can be enhanced by improving the associated hardware, software and the communication network (Balas et al., 2020). Recently, a number of procedures are discussed to detect the disease using the preserved and benchmark medical dataset (Daly & Taniar, 2004; Gkoulalas-Divanis et al., 2014; Kwok et al., 2002; Shen et al., 2019).
The proposed research work aims to discuss the need for the preservation of the earlier patients Disease-Evidence-Information (DEvI) to support the efficient identification of similar disease in other patients. This work presents an IoMT supported framework to assist the remote/field level disease monitoring with the help of carefully preserved disease information. In this work, the diagnosis of Lung Nodule (LN) is considered as the case study and the need of DEVI for the diagnosis of lung abnormality is discussed using appropriate experimental results. The proposed experimental investigation is demonstrated using the common lung imaging modalities, such as the Computed-Tomography (CT) and chest X-ray.
Lungs are the vital internal organ in human physiology, which is responsible to supply the oxygen to body organs. The abnormality in lung will severely distress the normal functioning of human and hence, a recommended medical screening is essential to detect and cure the abnormality. Lung cancer is one of the common diseases in humans and the 2018 report of the World-Health-Organization (WHO) confirmed 1.76 million deaths are due to lung cancer (Shen et al., 2019). The Abnormal Cell Growth (ACG) in lung is normally seen as the LN and the ACG may be non-cancerous (benign) or cancerous (malignant). The detection and evaluation of the ACG dimension confirms its stage (benign/malignant). The discussion by Olson (n.d.) confirms that the benign LN dimension may vary from 5 to 30 millimeters and the LN whose dimension is > 30 may be malignant. The detection and confirmation of the malignant LN needs a continuous follow-up and accurate examination. During the continuous follow-up action, the doctor will suggest a continuous imaging test over a predefined time (around two-years) and during every test, the present image slide is compared with the previous one to check the vital parameters of the LN, such as appurtenance, dimension and shape. When this comparison presents a deviation, then the doctor may recommend a bronchoscopy or tissue biopsy test to confirm that the LN is cancerous (Girvin & Ko, 2008; Herth, 2011; Xu et al., 2013). This procedure confirms that the detection of the cancerous LN needs earlier information of the patient (around two year data) to be maintained in order to support the efficient diagnosis. The essential information can be maintained in the field (hospital) or in a remote location (medical databank) and this data is to be preserved till the patient continues the treatment. When the perfectly chosen data is preserved, then it can help the doctor to detect the similar case of disease when a new patient’s is diagnosed. Further, the preserved data can be used to standardize the computer based detection system existing in the hospital.
This research aims to suggest a framework to support the remote/field level diagnosis of the LN using preserved DEvI. This framework suggests the essential steps to be followed during the remote LN diagnosis using a secured communication network, which integrates the automated diagnostic system and the radiologist.