Toward Improving Treatment Planning Quality and Efficiency Using Knowledge Engineering and Autoplanning: A Study Based on NRG-HN001 Clinical Trial

Abstract

Purpose/Objective(s): To investigate whether CBCT and CT can be used simultaneously in radiomics analysis. To establish a batch correction method for radiomics in 2 similar image modalities. Materials/Methods: Four sites including rectum, bladder, femoral head, and lung were considered as regions of interest in this study. For each site, 10 treatment planning CT images were collected, and 10 CBCT images that came from the same site of the same patient were acquired at first radiation therapy fraction. A total of 253 radiomics features, which were selected by our test-retest study at rectum cancer CT (ICC>0.8), were calculated for both CBCT and CT images using a computer algorithm. Simple scaling (z-score) and nonlinear correction methods were applied to the CBCT radiomics features. The Pearson correlation coefficient was calculated to analyze the correlation between radiomics features of CBCT and CT images before and after correction. Cluster analysis of mixed data (for each site, 5 CT, and 5 CBCT data are randomly selected) was implemented to validate the feasibility to merge radiomics data from CBCT and CT. The consistency of clustering result and site grouping was verified by a chi-square test for different datasets, respectively.Results: For simple scaling, 234 of the 253 features have r>0.8 (P<0.05), among which 154 features have r>0.9 (P<0.05). For radiomics data after nonlinear correction, 240 of the 253 features have r>0.8 (P<0.05), among which 220 features have r>0.9 (P<0.05). Cluster analysis of mixed data shows that data of 4 sites was almost precisely separated for simple scaling (PZ5.41Â10 -7 , c 2 test) and nonlinear correction (PZ3.25Â10 -7 , c 2 test), which is similar to the cluster result of CT data (PZ7.19Â10 -8 , c 2 test).

A comprehensive evaluation of the quality and complexity of prostate IMRT and VMAT plans generated by an automated inverse planning tool

“…In addition to improvements in plan optimisation, automation of the planning process has been shown to improve overall plan quality leading to less inter-user variation as a result of user experience and expertise. [5][6][7] The Philips Pinnacle 3 treatment planning system's (Philips Radiation Oncology Systems, Fitchburg, WI) approach to automated planning is the commercially available Auto-Planning (AP) software. The structure of the AP process, described in detail by Hazell et al, 8 begins with a template incorporating prioritised objectives for target volumes and organs at risk (OARs) that are specified by the user.…”