MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Automatic Location and Size Selection of Round Applicators for AccuBoost Treatments

F West1,2*, S Roles1,2, J Patrick2,3, R Munbodh2,3, M Rivard2,3, J Hepel2,3, K Leonard2,3, D Wazer2,3, Z Saleh2,3, (1) University of Rhode Island, Kingston, RI, (2) Rhode Island Hospital, Providence, RI, (3) Warren Alpert Medical School of Brown University, Providence

Presentations

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

Room: AAPM ePoster Library

Purpose: AccuBoost is a complex brachytherapy procedure for breast treatment. This technique requires a radiation oncologist to manually select applicator grid location and size by overlaying transparencies over a mammographic image to encompass surgical clips and the resected tumor bed. An algorithm was developed in MATLAB™ to automate selection of round applicators based on clip locations and underlying image features.

Methods: A total of 42 mammograms among ten patients were analyzed. Images were pre-processed by masking the imprinted localization grid and regions around the grid. A threshold was applied to isolate high-intensity pixels and generate a binary image. A set of morphological operations including region dilation, filling and smoothing were performed to segment the different regions. The segmented regions were classified as either surgical clips or miscellaneous objects based on different characteristics (area, perimeter, eccentricity, circularity, major/minor axis lengths and pixel intensity values). The applicator center location was determined by calculating the centroid of the detected clips. The applicator size was determined with the smallest circle that encompassed all clips plus a 1-cm margin.

Results: The algorithm correctly identified 187 of 196 true clips (95.4%) while mislabeling 10 of 197 identified clips (5.1%). Applicator location was correctly predicted for 20 of 42 fractions, and was within 0.5-cm of the physician-selected location for 33 of 42 fractions. Applicator size was correctly predicted for 20 of 42 fractions.

Conclusion: The proposed algorithm provided a method to objectively determine applicator location and size for AccuBoost treatments and may serve as a tool for independent checks. The discrepancy between the manual and quantitative determinations of applicator size and location suggests that the methodology may be further improved by considering radiomic features of breast tissue in addition to clip location when determining applicator center and size.

Funding Support, Disclosures, and Conflict of Interest: Drs. Rivard and Wazer are minor shareholders of Advanced Radiation Therapy, LLC (Tewksbury, MA) the manufacturer of the AccuBoost system.

Keywords

Brachytherapy, Breast, Mammography

Taxonomy

TH- Brachytherapy: Treatment planning using machine learning/automation

Contact Email