Search

Purpose: The aim of this study is to compare two different methods for auto-contouring for prostate radiation therapy. On the one hand Atlas-Based segmentation, on the other a deep-learning Artificial Intelligence (AI) based method by means of the recently developed software module Contour ProtégéAI ofMIM Maestro (MIM Software Inc., Cleveland, OH, USA). Methods: Ten patients with prostate cancer treated at the Radiotherapy Unit of S.Stefano Hospital of Prato (IT) were selected retrospectively by specific inclusion criteria. To make a comparison between the auto-segmentation methods in prostate radiation therapy the manual contouring was used as a reference, called Gold Standard. Similarity indices, like as Dice Similarity Coefficient (DSC) and Mean Distance to Agreement (MDA), are used to compare AI and Atlas-based contours with Gold Standard contours. Results: Data analysis show a significant difference in results obtained by Atlas based segmentation and AI. Significant differences in DSC and MDA (in terms of mean and SD) values between the two automatic methods of segmentation are present in the prostate (Mean DSC AI 0.78 ± 0.07 vs Atlas-based 0.64 ± 0.10; Mean MDA AI 1.42 ± 0.34 vs Atlas-based 6.56 ± 2.85) and rectum (Mean DSC AI 0.86 ± 0.05 vs Atlas-based 0.58 ± 0.13; Mean MDA AI 1.89 ± 0.53 vs Atlas-based 3.75 ± 1.51). There is not a significant difference in segmentation of both femurs. Even for empty bladder both methods give good results. Conclusion: In summary in the case of prostate treatment the use of software Contour ProtégéAI is extremely valid and the superiority in terms of accuracy of this method in comparison with the Atlas-based one has been shown. [ABSTRACT FROM AUTHOR]