Simultaneous dose distribution and fluence prediction for nasopharyngeal carcinoma IMRT

• Published in: Radiation oncology (London, England) Vol. 18; no. 1; p. 110
• Main Authors: Li, Yongbao, Cai, Wenwen, Xiao, Fan, Zhou, Xuanru, Cai, Jiajun, Zhou, Linghong, Dou, Wen, Song, Ting
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 04-07-2023; BioMed Central; BMC
• Subjects: Analysis; Cancer therapies; Care and treatment; Coders; Computed tomography; CT imaging; Diagnosis; Dose distribution prediction; Dosimetry; Fluence; Fluence prediction; Humans; IMRT; Intensity-modulated radiotherapy; Machine learning; Nasopharyngeal cancer; Nasopharyngeal carcinoma; Nasopharyngeal Carcinoma - radiotherapy; Nasopharyngeal Neoplasms - radiotherapy; Optimization; Patient outcomes; Patients; Planning; Predictions; Prostate; Radiation; Radiation dosimetry; Radiation therapy; Radiotherapy Dosage; Radiotherapy Planning, Computer-Assisted - methods; Radiotherapy, Intensity-Modulated - methods; Shared encoder network; Similarity; Throat cancer; China; Nasopharyngeal carcinoma; Fluence prediction; Shared encoder network; IMRT; Dose distribution prediction
• ISSN: 1748-717X; 1748-717X
• DOI: 10.1186/s13014-023-02287-4

Current intensity-modulated radiation therapy (IMRT) treatment planning is still a manual and time/resource consuming task, knowledge-based planning methods with appropriate predictions have been shown to enhance the plan quality consistency and improve planning efficiency. This study aims to develop a novel prediction framework to simultaneously predict dose distribution and fluence for nasopharyngeal carcinoma treated with IMRT, the predicted dose information and fluence can be used as the dose objectives and initial solution for an automatic IMRT plan optimization scheme, respectively.
We proposed a shared encoder network to simultaneously generate dose distribution and fluence maps. The same inputs (three-dimensional contours and CT images) were used for both dose distribution and fluence prediction. The model was trained with datasets of 340 nasopharyngeal carcinoma patients (260 cases for training, 40 cases for validation, 40 cases for testing) treated with nine-beam IMRT. The predicted fluence was then imported back to treatment planning system to generate the final deliverable plan. Predicted fluence accuracy was quantitatively evaluated within projected planning target volumes in beams-eye-view with 5 mm margin. The comparison between predicted doses, predicted fluence generated doses and ground truth doses were also conducted inside patient body.
The proposed network successfully predicted similar dose distribution and fluence maps compared with ground truth. The quantitative evaluation showed that the pixel-based mean absolute error between predicted fluence and ground truth fluence was 0.53% ± 0.13%. The structural similarity index also showed high fluence similarity with values of 0.96 ± 0.02. Meanwhile, the difference in the clinical dose indices for most structures between predicted dose, predicted fluence generated dose and ground truth dose were less than 1 Gy. As a comparison, the predicted dose achieved better target dose coverage and dose hot spot than predicted fluence generated dose compared with ground truth dose.
We proposed an approach to predict 3D dose distribution and fluence maps simultaneously for nasopharyngeal carcinoma patients. Hence, the proposed method can be potentially integrated in a fast automatic plan generation scheme by using predicted dose as dose objectives and predicted fluence as a warm start.