Clinical Use of a Commercial Artificial Intelligence-Based Software for Autocontouring in Radiation Therapy: Geometric Performance and Dosimetric Impact.

Purpose: When autocontouring based on artificial intelligence () is used in the radiotherapy () workflow, the contours are reviewed and eventually adjusted by a radiation oncologist before an RT treatment plan is generated, with the purpose of improving dosimetry and reducing both interobserver variability and time for contouring. The purpose of this study was to evaluate the results of application of a commercial AI-based autocontouring for , assessing both geometric accuracies and the influence on optimized dose from automatically generated contours after review by human operator.

Materials And Methods: A commercial autocontouring system was applied to a retrospective database of 40 patients, of which 20 were treated with radiotherapy for prostate cancer (PCa) and 20 for head and neck cancer (). Contours resulting from were compared against contours reviewed by human operator and human-only contours using Dice similarity coefficient (), Hausdorff distance (), and relative volume difference (). Dosimetric indices such as , , and normalized plan quality metrics were used to compare dose distributions from RT plans generated from structure sets contoured by humans assisted by against plans from manual contours. The reduction in contouring time obtained by using automated tools was also assessed. A Wilcoxon rank sum test was computed to assess the significance of differences. Interobserver variability of the comparison of manual vs. AI-assisted contours was also assessed among two radiation oncologists for PCa.

Results: For PCa, AI-assisted segmentation showed good agreement with expert radiation oncologist structures with average among patients ≥ 0.7 for all structures, and minimal radiation oncology adjustment of structures ( of adjusted versus structures ≥ 0.91). For , results of comparison between manual and contouring varied considerably e.g., 0.77 for oral cavity and 0.11-0.13 for brachial plexus, but again, adjustment was generally minimal ( of adjusted against contours 0.97 for oral cavity, 0.92-0.93 for brachial plexus). The difference in dose for the target and organs at risk were not statistically significant between human and AI-assisted, with the only exceptions of D to the anal canal and to the brachial plexus. The observed average differences in plan quality for PCa and cases were 8% and 6.7%, respectively. The dose parameter changes due to interobserver variability in PCa were small, with the exception of the anal canal, where large dose variations were observed. The reduction in time required for contouring was 72% for PCa and 84% for .

Conclusions: When an autocontouring system is used in combination with human review, the time of the RT workflow is significantly reduced without affecting dose distribution and plan quality.