Minor and major errors may occur in both manual and automatic organ contouring process, such as mis-localization or severe under/over-segmentation. They can subsequently impact the accuracy of dose optimization and planning. This study aims to develop an auto...
Author profile
Quan Chen, PhD
Mayo Clinic Arizona
Automated Identification of AI Contouring Outliers Using Template Shape-Based Analysis and Centroid Mapping without Case-Specific Ground Truth
Poster Program · Therapy Physics
Beyond Global Metrics: Unmasking Clinically Meaningful Deviations Using a Novel Local Metric In Regression Testing of Deployed Auto-Segmentation Models
Deep-learning (DL) auto-segmentation is routinely used clinically, yet domain shift and vendor model upgrades can change behavior in non-intuitive ways. We present a regression-testing framework to commission upgraded commercial auto-contouring models and to...
Poster Program · Therapy Physics
Feasibility and Benefit of Reduced CTV-to-PTV Margins In Prostate VMAT Using Monte Carlo–Based Geometric Perturbation
The MIRAGE trial demonstrated reduced acute toxicity in intact prostate radiotherapy in MRI arm, partially attributed to the use of smaller PTV margins (2 mm versus 4 mm with CT guidance). Motivated by these findings, this study retrospectively evaluates whet...
Poster Program · Therapy Physics
Robustness Enhancement for VMAT-TBI Planning and Treatment Delivery for Patients Wider Than 48cm
To identify planning techniques that consistently result in robust VMAT-TBI plans for patients wider than 48cm that allow for patient setup uncertainty 5mm or more.
Poster Program · Therapy Physics