MENU

Click here to

√ó

Are you sure ?

Yes, do it No, cancel

A Method for Automatic Optimization of Breast Electronic Tissue Compensation Treatment Plans Based On the Breast Radius and Separation

A Podgorsak1,2*, L Kumaraswamy3, (1) University at Buffalo, Buffalo, NY, (2) Roswell Park Comprehensive Cancer Center, Buffalo, NY, (3) Novant Health, Winston-Salem, NC

Presentations

(Sunday, 7/12/2020)   [Eastern Time (GMT-4)]

Room: AAPM ePoster Library

Purpose: To develop and assess an automated technique for the optimization of breast electronic tissue compensation (ECOMP) treatment plans based on the breast radius and separation.

Methods: Ten ECOMP courses planned and delivered at our institute were retrospectively collected for this work. For each patient, pre-treatment CT-simulation images were anonymized and input to a framework for automatic estimation of the size and shape of the breast for each axial slice using the elliptical Hough Transform. Optimal treatment fluence was estimated based on the breast radius and separation, and a total beam fluence map for both medial and lateral fields was output. These maps were then imported into the Eclipse Treatment Planning System, and used to calculate a dose distribution. The resulting distribution was compared to the original treatment hand-optimized by a medical dosimetrist. Two additional comparisons were performed, the first by generating plans assuming a single tissue penetration depth determined by averaging the breast radius and separation over the entire treatment volume, and the second generating plans assuming a three-region breast model (superior, middle, inferior) and averaging breast radius and separation within the regions to obtain three tissue penetration depths. Comparisons between treatment plans used the dose homogeneity index (HI, lower number is better).

Results: HI was non-inferior between our automatic algorithm (HI=12.6) and the dosimetrist plans (HI=9.9) (p-value>0.05), and was better than plans obtained using a single penetration depth (HI =7.0) (p-value<0.05) and three penetration depths (HI=15.6) (p-value>0.05) averaged over the 10 collected courses. Our automatic algorithm takes approximately 20 seconds for treatment plan generation and runs without user input, which compares favorably with the dosimetrist plans that can take up to 30 minutes of attention for full optimization.

Conclusion: This work indicates the potential clinical utility for an automated technique for the optimization of ECOMP breast treatments.

Download ePoster [PDF]

Keywords

Treatment Planning, CT, Breast

Taxonomy

TH- External Beam- Photons: Treatment planning using machine learning/Knowledge Based Planning/automation

Contact Email