Development of DICOM-Based Computer-Aided System and Conformity Index for Evaluation of Intensity Modulated Radiation Therapy Plans for Head-and-Neck Cancer

Introduction: The aim of this study was to develop a computer-aided evaluation (CAE) system which incorporated a conformity index with a dose-distance two-dimensional factor (CIDD) for automatic evaluation of intensity modulated radiation therapy (IMRT) plans for head-and-neck cancer.;Methodology: Utilizing the MATLAB program, a set of routines were written to parse key data from the Digital Imaging and Communications in Medicine for radiation therapy (DICOM RT) objects. Thirty IMRT plans for head-and-neck cancer were collected for CAE system evaluation. Normalized root mean square deviation (NRMSD) was computed for comparison between manually extracted and CAE-extracted data. To further assess the plan quality discerning power of CIDD, another three computed tomography data sets of head and neck cancer patients were collected. Ten IMRT plans were generated for each data set and ranked based on different conformity indices. The coefficient of variance was calculated for each data set to compare the degree of variation from CIDD scores to other existing indices. Mixed-design ANOVA was performed to explore the impact of use of CAE system with CIDD on plan evaluation time.;Results: The CAE system with CIDD for automatic evaluation of IMRT plans for head-and-neck cancer was developed. The CAE-computed DVH results were in good agreement with manually extracted data to achieve a NRMSD less than 0.05%. With the aid of the CAE system, the per-region detection performance for small-size spots was greatly improved by 2.36-fold and 3.99-fold for experienced and inexperienced planners, respectively. Compared with other commonly used indices, the CIDD resulted in the largest coefficient of variance among 10 IMRT plans for each patient. The ANOVA results indicated that the evaluation time was significantly shortened by 1.88-fold than that without using the CAE system, regardless of the level of experience.;Conclusion: The CAE system with CIDD demonstrated good applicability of DICOM RT standard in data mining. The use of CAE system with CIDD could eliminate human errors and enhance efficiency in evaluating IMRT plans for head-and-neck cancer. By taking individual tumor geometry into account, the superiority of CIDD in plan discerning power was demonstrated.