Working with DICOM at scale?
DICOMAnon helps imaging teams anonymize, batch process, and automate DICOM workflows without writing custom scripts.
Author profile
University of California, Los Angeles
DICOMAnon helps imaging teams anonymize, batch process, and automate DICOM workflows without writing custom scripts.
To achieve more favorable clinical VMAT/IMRT outcomes, preclinical studies that mimic clinical practices and provide highly statistically significant small animal (SA) studies are essential. However, such high-throughput studies are currently impractical beca...
Conventional iterative closest point (ICP) algorithms capable of 3D surface registration perform best with non-deformable surfaces. Such methods are not efficient in head and neck (HN) RT, where one part of the surface is rigid (head) while another part is de...
When positioning patients for head and neck radiation therapy procedures, it can be difficult to position the patient without knowledge of the limits of motion due to physiological constraints caused by the neck vertebrae. This work seeks to develop a dynamic...
Manual segmentation of immunohistochemical (IHC) stained images is a time-consuming task that typically takes 1-2 workdays to segment all images needed for analysis. Deep learning-based methods were employed to create an AI model to automatically segment IHC...
Routine and pre-treatment clinical irradiator quality assurance (QA) is vital for ensuring safe, accurate, and reproducible patient care. A primary factor limiting statistical significance in preclinical research is the lack of reproducibility, mainly due to...
While phantom studies demonstrate high spatial accuracy for Surface-Guided Radiation Therapy (SGRT) systems, validation with live human subjects is critical. Non-rigid facial motion and the lack of a concurrent motion reference standard present unique challen...