MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Update On DVH Analytics: An Open-Source DICOM-RT Database Application

D Cutright1*, M Gopalakrishnan2, A Roy3, (1) University of Chicago Medicine, Chicago, IL, (2) Northwestern Memorial Hospital, Chicago, IL, (3) The University of Texas at San Antonio, San Antonio, TX

Presentations

(Sunday, 7/12/2020)   [Eastern Time (GMT-4)]

Room: AAPM ePoster Library

Purpose:
DVH Analytics (DVHA) is an open-source software application used to collect DICOM-RT data and provide analytical tools. Since its publication in 2018, it has been completely rewritten as a native desktop application.

Methods:
DVHA is now based on the wxPython framework – turning DVHA into a desktop class application that runs on Microsoft Windows, macOS, and Linux. Furthermore, single-file executables are available (for Windows and Mac) so users do not need to install (or understand how to use) python. New features include machine learning modules, importing of non-DICOM data, control charts, and a more user-friendly SQL engine. Machine learning modules allow users to generate models with random forest, support vector machine, decision tree, and gradient boosting algorithms. Non-DICOM data can be imported using a simple copy and paste from external spreadsheet applications. DVHA also generates control charts; a risk-adjusted control chart will be generated with a paired multi-variable regression. Previously, DVHA required users to create and setup a PostgreSQL database, which is not trivial. DVHA now supports SQLite3, relieving users of any explicit SQL database setup or the need for admin privileges to their desktop.

Results:
Using a single physician’s practice, 80 prostate patients were imported to demonstrate the new features of DVHA. Gamma pass-rates for these 80 prostate patients were imported using the python library IMRT QA Data Miner (IQDM). Multi-variable linear and random forest models were generated for gamma pass-rate prediction. Additionally, a control chart for IMRT QA results was generated as recommended by TG-218.

Conclusion:
A free and open-source desktop application has been developed that can store, organize, parse, and analyze non-image based DICOM-RT data. This software provides means to query large patient datasets, view data over time, perform statistical tests, build predictive models, and generate control charts.

Keywords

DICOM-RT, Computer Software, Statistical Analysis

Taxonomy

IM/TH- Informatics: Informatics in Therapy (general)

Contact Email