Philips Research North America

2 ARTICLES PUBLISHED IN JoVE

Medicine

Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization

Vania Tacher¹, MingDe Lin², Nikhil Bhagat¹, Nadine Abi Jaoudeh³, Alessandro Radaelli⁴, Niels Noordhoek⁴, Bart Carelsen⁴, Bradford J. Wood³, Jean-François Geschwind¹

¹Russell H. Morgan Department of Radiology and Radiological Science, Division of Vascular and Interventional Radiology, The Johns Hopkins Hospital, ²Clinical Informatics, Interventional, and Translational Solutions (CIITS), Philips Research North America, ³Center for Interventional Oncology, Interventional Radiology Section, National Institutes of Health, ⁴Interventional X-ray, Philips Healthcare

Dual-phase cone-beam computed tomography (DP-CBCT) is a useful intraprocedural imaging technique for transarterial chemo-embolization treatment with drug-eluting beads of hepatocellular carcinoma. DP-CBCT has been used to perform three major steps in oncologic interventional radiology: tumor localization (see), navigation and intraprocedural catheter guidance (reach), and intraprocedural evaluation of treatment success (treat).

Medicine

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Aaron Abajian¹, Nikitha Murali¹, Lynn Jeanette Savic^1,2, Fabian Max Laage-Gaupp¹, Nariman Nezami¹, James S. Duncan³, Todd Schlachter¹, MingDe Lin⁴, Jean-François Geschwind⁵, Julius Chapiro¹

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.