What question did this study set out to answer?

This research aims to enhance dose prediction and beam angle optimization using a vision transformer model for BNCT.

March 1, 2026Open Access

Vision transformer model-based dose prediction and beam angle optimization for BNCT

Key Points

This research aims to enhance dose prediction and beam angle optimization using a vision transformer model for BNCT.
Evaluated a clinical dataset for dose prediction accuracy using a vision transformer model.
Calculated Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) for GTV and skin.
Analyzed gamma passing rates for treatment validation post-optimization.
Achieved MAE below 0.6 Gy and MAPE below 2% for GTV; MAE under 0.15 Gy and MAPE below 3.5% for skin.
Gamma passing rates exceeded 90% for 2 mm/2% and 97% for 3 mm/3%.
Post-optimization, minimum voxel dose of GTV increased by 1.8 Gy without increasing maximum voxel dose of organs at risk.

Abstract

On a clinical dataset, the proposed model achieved a Mean Absolute Error (MAE) below 0.6 Gy and Mean Absolute Percentage Error (MAPE) below 2% for GTV; for skin, MAE was under 0.15 Gy and MAPE below 3.5%. The average gamma passing rates exceeded 90% (2 mm/2%) and 97% (3 mm/3%). After optimization, the minimum voxel dose of the GTV increased by an average of 1.8 Gy, while the maximum voxel dose of the organs at risk (OARs) did not increase. Significance. The proposed method has accurate dose prediction and efficient optimization ability, with results validated by MC simulations. It offers a potential application for clinical automated BNCT treatment planning design and optimization.

Vision transformer model-based dose prediction and beam angle optimization for BNCT

Key Points

Abstract

Cite This Study