Overview and Context
Liver cancer is the sixth most common cancer diagnosis and the fourth most frequent cause of cancer-related death globally. In the United States in 2020, an estimated 42,810 new cases of liver cancer will be diagnosed with a mortality estimate of 30,160 people. Globally and within the United States, liver cancer is one of only two cancers to have an increasing mortality rate year- over-year over the past 20 years. The DataLab will work with Dr. Goldman to test the ability of machine learning models to help identify signs of liver cancer from medical images.
Automatic identification of anomalies in medical imaging will improve the treatment localization and specificity while reducing the risk of negative outcomes during treatment. We expect that machine learning algorithms applied to medical imaging can classify the location and optimal treatment paths for liver cancer.
Significant investigation has demonstrated the feasibility and efficacy of machine learning algorithms for multiple types of medical imaging. In the field of angiography (studies of the inside of blood vessels), machine learning has had great success in detecting abnormalities using imaging data. This project will develop similar machine learning models to discover and classify abnormalities in medical images of the liver.
The goals of this project seek to fundamentally alter norms for liver cancer treatment. This innovation will also act as a stepping stone for further development of this technology at the UC Davis Medical Center, paving the way for more computer assisted diagnosis techniques.