Deep nets vs expert designed features in medical physics: An IMRT QA case study
Medical Physics2018Vol. 45(6), pp. 2672–2680
Citations Over TimeTop 1% of 2018 papers
Yannet Interian, V.C. Rideout, Vasant Kearney, Efstathios D. Gennatas, Olivier Morin, J Cheung, Timothy D. Solberg, Gilmer Valdés
Abstract
Convolutional neural networks (CNNs) with transfer learning can predict IMRT QA passing rates by automatically designing features from the fluence maps without human expert supervision. Predictions from CNNs are comparable to a system carefully designed by physicist experts.
Related Papers
- → A geometrical model for the Monte Carlo simulation of the TrueBeam linac(2015)40 cited
- → WE‐C‐108‐04: A Monte Carlo Investigation of Low‐Z Targets in a TrueBeam Linear Accelerator Using Varian Virtualinac(2013)4 cited
- → Evaluation of the Varian TrueBeam™ 6 MV phase-space files for the Monte Carlo simulation in small field dosimetry(2022)2 cited
- → SU‐E‐T‐33: A Comparative Study of Commissioning Data of Two TrueBeam LINACs with TrueBeam Representative Beam Data(2013)1 cited
- → SU‐E‐T‐624: Portal Dosimetry Commissioning of Multiple (6) Varian TrueBeam Linacs Equipped with PortalVision DMI MV Imager(2015)