Unhealthy Liver Detection using CNN with IoT

• Published in: 2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS) pp. 1079 - 1083
• Main Authors: Pushpa, S. Ewins Pon, Jayasree, T., John, Vineeth Ajith, Subramanian, Abhishek, Chandrashekhar, Varun, Sankareswaran, Sivakumar
• Format: Conference Proceeding
• Language: English
• Published: IEEE 14.06.2023
• Subjects: Computed Tomography; Convolutional Neural Networks; Mobile Communications Module; Unhealthy liver
• DOI: 10.1109/ICSCSS57650.2023.10169799

Liver diseases are very common and challenging task for indentification, in today's world. Be it because of the excessive use of alcohol or any other underlying conditions, it affects a lot of the general public. The methodology proposed in this work, uses the fundamental principles of Image Processing and Convolutional Neural Networks (CNN) to detect a healthy or an unhealthy liver. A deep learning approach, more specifically Convolutional Neural Networks is used to extract information from the Computed Tomography (CT) images of the liver which is then analyzed to distinguish between healthy and unhealthy liver. The proposed methodology includes, a successful extraction of the features of the image using principles of image processing, followed by further extraction of critical information at the different layers of the CNN algorithm. The Internet of Things system is equipped with Wi-Fi module as well as a Global System for Mobile Communications module. The Wi-Fi module continually updates, the status of a patient liver to a server. The Global System for Mobile Communications (GSM) module automatically, sends out an alert message to the patient's emergency contact, when an unhealthy liver has been detected.