An International Validation of Knowledge-Based Planning
A Babier1*, B Zhang1, R Mahmood1, V G L Alves2, A Barragan Montero3, J Beaudry4, C Cardenas5, Y Chang6, Z Chen7, J Chun8, H Eraso9, E Faustmann10, S Gaj11, S Gay5, M Gronberg5, J He12, G Heilemann13, S Hira14, Y Huang15, F Ji16, D Jiang16, J Jimenez Giraldo9, H Lee17, J Lian18, K Liu19, S Liu16, K Marixa9, J Marrugo9, K Miki20, T Netherton5, D Nguyen21, H Nourzadeh22, A Osman23, Z Peng6, J Quinto Munoz9, C Ramsl10, D Rhee5, J Rodriguez Arciniegas9, H Shan24, J V Siebers2, M H Soomro2, K Sun25, A Usuga Hoyos9, C Valderrama9, R Verbeek26, E Wang7, S Willems27, Q Wu16, X Xu18, S Yang28, L Yuan29, S Zhu30, L Zimmermann13, K L Moore31, T G Purdie32, A L McNiven32, T C Y Chan1, (1) University of Toronto, Toronto, CA, (2) University of Virginia Health System, Charlottesville, VA, (3) Universite Catholique de Louvain, Brussels, BE, (4) Memorial Sloan Kettering Cancer Center, New York, NY, (5) University of Texas MD Anderson Cancer Center, Houston, TX, (6) University of Science and Technology of China, Hefei, ,CN, (7) WolHelp Technology (Shenzhen) Co Ltd, CN, (8) Yonsei University, Seoul, KR, (9) National University Of Colombia, CO, (10) Vienna University Of Technology, Vienna, AT, (11) Cleveland Clinic, Cleveland, OH, (12) Shanghai Jiao Tong University, Shanghai, CN, (13) Medical University Of Vienna, Vienna, AT, (14) Johns Hopkins University, Baltimore, MD, (15) Peking University Cancer Hospital & Institute, Beijing, CN, (16) Anhui University, Hefei, CN, (17) Massachusetts General Hospital, Boston, MA, (18) University of North Carolina, Chapel Hill, NC, (19) Taiwan Ai Labs, Taipei, TW, (20) Hiroshima University, Hiroshima, JP, (21) UT Southwestern Medical Center, Dallas, TX, (22) Thomas Jefferson University, Philadelphia, PA, (23) Al-Neelain University, Khartoum, SD, (24) Fudan University, Shanghai, CN, (25) Studio Vodels, Atlanta, GA, (26) Aalto University, Espoo, FI, (27) KU Leuven, Leuven, BE, (28) Sichuan University, Chengdu, CN, (29) Virginia Commonwealth University Medical Center, Richmond, VA, (30) Henry Ford Health System, Detroit, MI (31) UC San Diego, La Jolla, CA, (32) Princess Margaret Cancer Centre, Toronto, CA
Presentations
TH-F-TRACK 5-3 (Thursday, 7/29/2021) 4:30 PM - 5:30 PM [Eastern Time (GMT-4)]
Purpose: To carry out a large international validation of how dose prediction quality translates to plan quality in a radiotherapy knowledge-based planning (KBP) process.
Methods: We collected dose predictions for head-and-neck cancer radiotherapy from 21 different research groups internationally who participated in the OpenKBP Grand Challenge. Each research group used the same training dataset (n=200) and validation dataset (n=40) to develop their methods. These methods predicted dose on a testing dataset (n=100), and those 2100 unique dose predictions were input to a previously published plan optimization method to generate 2100 treatment plans. The predictions and plans were compared to the ground truth dose via: (1) error, the mean absolute voxel-by-voxel difference in dose; and (2) quality, the mean and maximum deviation across 23 dose-volume histogram (DVH) criteria.
Results: The range in median prediction error among the top 20 methods was 2.3Gy to 12.0Gy, which was 6.8Gy wider than the range in median plan error of 2.1Gy to 5.0Gy. One method also achieved significantly lower prediction error (P<0.05; one-sided Wilcoxon test) than all the other methods, however, it generated plans with error that was not significantly lower than 28.6% of the other methods. Additionally, predicted dose was consistently lower quality than plan dose. Half (n=1050) of all predictions and plans had an average deviation that was 0.1Gy worse and 0.8Gy better than the ground truth dose, respectively. Similarly, half of all predictions had a maximum deviation that was 3.7Gy worse than the ground truth dose, which was 1.0Gy worse than half of all plans.
Conclusion: Many dose prediction methods can achieve low error, however, optimization often improves upon the predictions and eliminates significant differences between prediction methods. Thus, it is critical that we improve the optimization stage in KBP to get better utility out of the existing high-quality dose prediction methods.
Handouts
Keywords
Optimization, Treatment Planning, Radiation Therapy
Taxonomy
Contact Email