Skip to main content

Abstract P4-12-10: Clinical implementation of the machine learning-based automated treatment planning tool for whole breast radiotherapy

Publication ,  Conference
Yoo, S; Sheng, Y; Blitzblau, R; Catalano, S; Morrison, J; O'Neill, L; Yin, F; Wu, QJ
Published in: Cancer Research
February 15, 2020

Objectives: The machine learning (ML)-based automated treatment planning tool has been developed and evaluated for whole breast radiotherapy. This study implemented the tool in clinic and compared plan quality and planning efficiency with the manual treatment process for whole breast radiotherapy using irregular surface compensator technique.Methods: This study involved two phases. The 1st phase was to evaluate and the 2nd phase was to implement in the clinic. In the 1st phase, thirty whole breast or chest wall cases were planned by using the irregular surface compensator technique with fluence maps manually and iteratively edited to achieve uniform dose distribution to the target by planners. Patients were treated with these manual plans after physician’s approval. The evaluation phase thus compared our in-house ML-based automated treatment planning tool implemented in Eclipse Scripting Application Programming Interface (ESAPI) to these manual plans. The ML-based planning tool generated the fluence maps with the same beam parameters such as beam energy, gantry angle, collimator angle, and aperture shape as manual plans. Breast or chest wall clinical target volume (CTV) coverage based on the percentage CTV volume receiving 95% of the prescribed dose (V95%) and high-dose volume based on V105% were compared to evaluate the plan quality as well as the planning efficiency. Two-tailed Wilcoxon Signed-Rank test was performed to test the null hypothesis that the two planning schemes yield equivalent plan quality.In the 2nd phase, the planners used the automated planning tool for fourteen plans (twelve patients) followed by manual fluence modification as needed. Physicians reviewed and approved the plans, and patients were treated.Results: For the 1st phase, the mean planning time was 110.2 min with standard deviation (SD) of 62.8 min for the manual planning with the range from 25 to 270 min, and 6.4 min with SD of 2.1 min for the automated planning with the range from 4 to 12 min (p<0.01). CTV mean V95% was 96.7% (SD: 5.0%) for the manual planning and 96.7% (SD: 4.8%) for the automated planning (p=0.89). CTV mean V105% was 21.6% (SD: 29.8%) for the manual planning and 20.4% (SD: 30.5%) for the automated planning (p=0.22). Differences in doses to heart and lungs were negligible between the paired plans as the two planning schemes used the same beam parameters.For the 2nd phase, the mean planning time was 16.4 min (SD: 9.1 min) and the mean time for additional manual editing was 12.7 min (SD: 12.5 min). The mean total treatment planning time was 29.1 min (SD: 14.8 min).). CTV mean V95% was 97.2% (SD: 4.2%) and mean V105% was 8.2 % (SD: 3.6%). The manual post modifications were added by the planners with intention to improve the target coverage or to reduce high doses, yet, the difference between the plans without and without the manual post modification was negligible.Conclusion: The ML-based automated treatment planning tool through Varian ESAPI has been successfully implemented for clinical use going through two phases of study. Abiding to the same plan quality as manual process, the automated tool significantly reduced the planning time as the ML-based tool automate the iterative fluence editing process.Citation Format: Sua Yoo, Yang Sheng, Rachel Blitzblau, Suzanne Catalano, Jay Morrison, Leigh O'Neill, Fangfang Yin, Q. Jackie Wu. Clinical implementation of the machine learning-based automated treatment planning tool for whole breast radiotherapy [abstract]. In: Proceedings of the 2019 San Antonio Breast Cancer Symposium; 2019 Dec 10-14; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2020;80(4 Suppl):Abstract nr P4-12-10.

Duke Scholars

Published In

Cancer Research

DOI

EISSN

1538-7445

ISSN

0008-5472

Publication Date

February 15, 2020

Volume

80

Issue

4_Supplement

Publisher

American Association for Cancer Research (AACR)

Related Subject Headings

  • Oncology & Carcinogenesis
  • 3211 Oncology and carcinogenesis
  • 3101 Biochemistry and cell biology
  • 1112 Oncology and Carcinogenesis
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Yoo, S., Sheng, Y., Blitzblau, R., Catalano, S., Morrison, J., O’Neill, L., … Wu, Q. J. (2020). Abstract P4-12-10: Clinical implementation of the machine learning-based automated treatment planning tool for whole breast radiotherapy. In Cancer Research (Vol. 80). American Association for Cancer Research (AACR). https://doi.org/10.1158/1538-7445.sabcs19-p4-12-10
Yoo, Sua, Yang Sheng, Rachel Blitzblau, Suzanne Catalano, Jay Morrison, Leigh O’Neill, Fangfang Yin, and Q Jackie Wu. “Abstract P4-12-10: Clinical implementation of the machine learning-based automated treatment planning tool for whole breast radiotherapy.” In Cancer Research, Vol. 80. American Association for Cancer Research (AACR), 2020. https://doi.org/10.1158/1538-7445.sabcs19-p4-12-10.
Yoo S, Sheng Y, Blitzblau R, Catalano S, Morrison J, O’Neill L, et al. Abstract P4-12-10: Clinical implementation of the machine learning-based automated treatment planning tool for whole breast radiotherapy. In: Cancer Research. American Association for Cancer Research (AACR); 2020.
Yoo, Sua, et al. “Abstract P4-12-10: Clinical implementation of the machine learning-based automated treatment planning tool for whole breast radiotherapy.” Cancer Research, vol. 80, no. 4_Supplement, American Association for Cancer Research (AACR), 2020. Crossref, doi:10.1158/1538-7445.sabcs19-p4-12-10.
Yoo S, Sheng Y, Blitzblau R, Catalano S, Morrison J, O’Neill L, Yin F, Wu QJ. Abstract P4-12-10: Clinical implementation of the machine learning-based automated treatment planning tool for whole breast radiotherapy. Cancer Research. American Association for Cancer Research (AACR); 2020.

Published In

Cancer Research

DOI

EISSN

1538-7445

ISSN

0008-5472

Publication Date

February 15, 2020

Volume

80

Issue

4_Supplement

Publisher

American Association for Cancer Research (AACR)

Related Subject Headings

  • Oncology & Carcinogenesis
  • 3211 Oncology and carcinogenesis
  • 3101 Biochemistry and cell biology
  • 1112 Oncology and Carcinogenesis