Segmentation and Detection of Liver Tumors from CT Scans using TransUNet Architecture in Deep Learning

Globally, liver tumors and the third major cancer killer and sixth common disease. They occur mostly in people who take tobacco or alcohol very often. These factors are responsible for around 75–85 percent of cases of primary liver cancer. Nonetheless, manual diagnosis of liver tumors is known to be a challenging task due to tumor heterogeneity, diverse shapes and sizes as well as many types of imaging artifacts that can occur with relatively limited annotated data. Diagnosis and treatment planning of liver tumors are highly affected by the critical task of segmenting tumor in medical images. Further, for identifying stages, precision and make a doctor treatment-level understanding of learning characteristics tumor Since the knowledge that has been many feature extraction techniques formulated some frameworks onset detection tumors begun its course which could be fully transformed into applications targeted response type against size as well volume based However, this is an error-prone and time-consuming process. Thus, a solution to overcome these challenges is introduced by using Deep Learning (DL) with the TransUNet model which belongs to Convolutional Network architecture for instant image processing. Doctors use this system to conveniently detect and segment tumors from images, it is a way of approximating tumor size and stage so that more accurate treatment can be given. To sum up, liver tumors as a worldwide health problem are largely related to alcohol and tobacco consumption. Manual diagnosis is tough however with the help of advanced deep learning methods such as TransUNet we can detect tumors at an early stage and accurately providing better treatment to patients by doctors.