Martina Descovich, PhD

Professor

Dr. Descovich specializes in the physics of stereotactic radiosurgery (SRS) and stereotactic body radiation therapy (SBRT). SRS and SBRT are advanced modalities of radiation therapy, enabling high targeting accuracy. The CyberKnife system is a medical device entirely dedicated to SRS and SBRT treatments. It combines a sophisticated tracking system with a robotically mounted linear accelerator capable of delivering radiation from hundreds of different directions while synchronizing with respiratory induced target motion. Radiosurgery treatments are complex and require a team of specialized experts. Dr. Descovich has been the lead physicist responsible for the CyberKnife program since the installation of the CyberKnife VSI at Helen Diller Family Comprehensive Cancer Center in 2010.

Publications

Deep match: A zero-shot framework for improved fiducial-free respiratory motion tracking.

A digital male pelvis phantom series showing anatomical variations over the course of fractionated radiotherapy treatment.

End-to-end validation of fiducial tracking accuracy in robotic radiosurgery using MRI-only simulation imaging.

Predicting successful clinical candidates for fiducial-free lung tumor tracking with a deep learning binary classification model.

Improved accuracy of relative electron density and proton stopping power ratio through CycleGAN machine learning.

Irradiation of Nf1 mutant mouse models of spinal plexiform neurofibromas drives pathologic progression and decreases survival.

Stereotactic Body Radiation Therapy and High-Dose-Rate Brachytherapy Boost in Combination With Intensity Modulated Radiation Therapy for Localized Prostate Cancer: A Single-Institution Propensity Score Matched Analysis.

Improved contrast and noise of megavoltage computed tomography (MVCT) through cycle-consistent generative machine learning.

Technical Note: Performance of CyberKnife® tracking using low-dose CT and kV imaging.

DoseGAN: a generative adversarial network for synthetic dose prediction using attention-gated discrimination and generation.

DoseNet: a volumetric dose prediction algorithm using 3D fully-convolutional neural networks.

A continuous arc delivery optimization algorithm for CyberKnife m6.