Fion WK Cheung MS, Abstract Co-Author: Nothing to Disclose

Maria Yuen-Yee Law PhD, Presenter: Nothing to Disclose

Douglas K.S. Ng, Abstract Co-Author: Nothing to Disclose

To develop and evaluate a mobile cloud computer-aided evaluation (mcCAE) system for automatic evaluation of intensity modulated radiation therapy (IMRT) plans based on the Digital Imaging and Communications in Medicine (DICOM) standard.

The computational infrastructure was developed using the WampServer version 2.0, a package of Apache web server 2.2, PHP 5.2 and MySQL 5.1 with embedded mcCAE engine written in Objective C and JAVA. The mcCAE was a web-based system that complemented the current treatment planning system (TPS) in a radiotherapy department. Communication infrastructure for plan review and approval was built using mobile devices such as the iPad, iPhone or Android tablets. All modules were implemented on graphics processing unit (GPU)-based supercomputing hardware. Utilizing the MATLAB program language, a set of routines was written to parse key data from the DICOM for radiation therapy (RT) objects. Thirty IMRT plans were collected for evaluation of mcCAE system performance. Normalized root mean square deviation (NRMSD) was computed for comparison between manually extracted and mcCAE-extracted data. Mixed-design analysis of variance (ANOVA) was also performed to explore the impact of use of mcCAE system on plan evaluation time.

The mcCAE system for automatic evaluation of IMRT plans was successfully developed, allowing better appreciation of IMRT plans. Three major graphical user interfaces (GUIs) were created to intelligently lead the planners through the steps of plan evaluation process. On average, it took 6.5s to open an IMRT plan in the mobile device. The mcCAE-computed dose volume histogram (DVH) results were in good agreement with the manually extracted data with a NRMSD of less than 0.05%. The ANOVA results indicated that the evaluation time with the aid of mcCAE system was significantly shortened by 1.88-fold than that without using the mcCAE system, regardless of the level of experience.

The mcCAE system demonstrated good applicability of cloud computing into clinical practice and DICOM RT objects in data mining. The use of mcCAE system could eliminate human errors, provide plan quality control and enhance efficiency in evaluating IMRT plans.

The mcCAE system could represent a major breakthrough in the routine IMRT planning workflow by introducing remote plan evaluation and eliminating all tedious manual evaluation steps.

Cheung, F, Law, M, Ng, D, Development of a Mobile Cloud Computer-aided Evaluation System in Radiotherapy.  Radiological Society of North America 2012 Scientific Assembly and Annual Meeting, November 25 - November 30, 2012 ,Chicago IL. http://archive.rsna.org/2012/12032892.html