Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular CarcinomaAaron Abajian 1, Nikitha Murali 1, Lynn Jeanette Savic 1,2, Fabian Max Laage-Gaupp 1, Nariman Nezami 1, James S. Duncan 3, Todd Schlachter 1, MingDe Lin 4, Jean-François Geschwind 5, Julius Chapiro 1
1Department of Radiology and Biomedical Imaging, Yale School of Medicine, 2Department of Diagnostic and Interventional Radiology, Universitätsmedizin Charité Berlin, 3Department of Biomedical Engineering, Yale School of Engineering and Applied Science, 4Philips Research North America, 5Prescience Labs
Intra-arterial therapies are the standard of care for patients with hepatocellular carcinoma who cannot undergo surgical resection. A method for predicting response to these therapies is proposed. The technique uses pre-procedural clinical, demographic, and imaging information to train machine learning models capable of predicting response prior to treatment.
