SU‐E‐T‐274: Evaluation of Atlas‐Based Segmentation Algorithms: VelocityAI vs. MIMvista

Purpose: IMRT is driven by volumetric segmentation, thus greater care and accuracy are necessary when contouring structures. The contouring process requires staff experience and ample time. We have evaluated the performance of two commercial atlas‐based segmentation algorithms. Methods: VelocityAI and MIMvista were compared. Twenty‐one IMRT head and neck cases were randomly and retrospectively chosen. These cases included their respective CT scans and physician‐drawn structures. The twenty‐one cases were divided into two sets: one to create the atlas (eleven) and the other to test the atlas on (ten). In MIMvista the atlas was created using the in‐software tool and setting the most representative patient as the template. In VelocityAI the atlas was created using all ten cases to create an average patient atlas. The averaging used on the ten cases for the VelocityAI atlas was created using the STAPLE algorithm (provided by Velocity Medical Solutions).Results: Twelve OARs were compared to physician‐drawn structures using the Dice similarity coefficient (DSC). VelocityAI and MIMvista performed quite well on the brain, brainstem, spinal cord and eyes with mean DSCs ranging between 0.770– 0.947 for VelocityAI and 0.647– 0.978 for MIMvista. Neither program performed too well on the esophagus, larynx, oral cavity, parotids and sphincter muscle with mean DSCs ranging between 0.348– 0.690 for VelocityAI and 0.389–0.709 for MIMvista Conclusions: This work revealed that neither of the software truly outperformed the other. MIMvista did yield slightly better structures, yet the problem is that much modification is required to render the structures valid. VelocityAI and MIMvista both have great potential and can be used to provide a quick draft of structures, which may reduce physician‐contouring time.