Machine Learning Methods Using Texture Feature Selection in Diagnosis of Liver Cancer

The liver is essential to a wide variety of physiological and metabolic activities that take place in our bodies. A lack of liver function or liver dysfunction can lead to various health issues, the most serious of which is the illness. Early identification of liver illness can help shorten the treatment duration and minimize liver damage by decreasing the usage of drugs that are not essential. The application of machine learning techniques in medicine has shown promising results in illness diagnosis due to advances in technology. This research aimed to discover the essential characteristics of the data set, using textural feature selection methods so that they could be applied in the early diagnosis of liver disorders. This was done in order to diagnose liver failure disease. The model in machine learning methods has been improved, which has led to an improvement in the success rate of illness detection. The results obtained were compared with the findings of other research published in the literature that used the same data set. The diagnostic success rate for liver failure illness, as determined by applying machine learning algorithms known as Decision Trees (DT), was 94.67%. It is hoped that the developed models may assist medical professionals in the early detection of liver illness.