An Involuntary Liver Cancer Recognition in Abdominal Liver Imageries with Soft Optimization Methods in Biomedical Application

• Published in: 2023 IEEE International Conference on Integrated Circuits and Communication Systems (ICICACS) pp. 1 - 6
• Main Authors: Kumar, M. Vinodh, Kumar Patra, Raj, K, Veena, Siva Kumar Reddy, A, Sunil Kumar, V
• Format: Conference Proceeding
• Language: English
• Published: IEEE 24.02.2023
• Subjects: accuracy; ann; Biomedical monitoring; Computed tomography; ct scan; Image segmentation; Liver; Liver cancer; Software; Software algorithms
• DOI: 10.1109/ICICACS57338.2023.10099601

A medical image recovery system can be used for a variety of useful purposes, one of which is the classification of medical images. When numerous different types of medical imaging evidence are accessible, it is essential to have accurate categorization models. Because of the CT paradigm in clinical diagnosis, radiologists are able to properly detect and monitor changes in the body's physiological state. The ability to differentiate between different types of tissues in a CT image based on the various grey rates along each line contributes significantly to the accuracy of a medical diagnosis. The standard practice for diagnosing cancer relies on scientific and histological data, both of which have the potential to lead to incorrect or erroneous findings. The liver, which may be found in the upper abdominal region of the external human form, is responsible for filtering the blood and getting rid of any toxins it discovers in the process. The distinction between the two types of cancer is taught through an artificial neural network in this method. A number of different parameters, including accuracy, area, correlation, entropy, homogeneity, contrast, and the similarity index, are employed to conduct an analysis of the impact. After that, researchers tried to enhance the early identification and treatment of liver cancer by segmenting and classifying liver tumors from CT images. This was done in order to gain a better understanding of the disease. The accuracy of the identification was raised to 99.63 percent thanks to the classifier and optimizer that was proposed.