Machine Learning Approach for Detecting Liver Tumours in CT images using the Gray Level Co-Occurrence Metrix

Over 2.4 % of deaths in India each year are caused by liver diseases. Due to its mild early signs, liver disease is also challenging to diagnose. Frequently, the signs only become obvious when it is too late. Even more challenging than segmenting the liver is segmenting the tumour from the liver. Imaging procedures like computed tomography, magnetic resonance imaging, and ultrasound are utilised to separate the liver and liver tumour once a sample of liver tissue has been removed. This research suggests a machine learning method from CT images-based automatic assistance system for stage categorization. Then, the features are extracted from the CT images using the Gray-Level Co-Occurrence Matrix (GLCM) method. Finally, it is suggested that the computed tomography (CT) pictures of livers containing tumours be categorised using a Random Forest technique. Using the described method, liver tumour images are classified as benign or malignant. The real value accuracy for liver segmentation was found to be approximately 99.55%, 97.85%, and 98.16% based on the experimental investigation. Using the described method, liver tumour images are classified as benign or malignant. These modifications improve the system’s ability to recognise the tumour from the CT pictures.