Latent Spaces Enable Transformer-Based Dose Prediction in Complex Radiotherapy Plans

TL;DR

This paper introduces LDFormer, a two-stage latent transformer model that predicts complex lung SABR dose distributions efficiently, outperforming existing methods and aiding clinical decision-making.

Contribution

The novel LDFormer framework leverages latent spaces and transformer architecture to improve dose prediction accuracy and speed for multi-lesion lung SABR plans.

Findings

Outperforms state-of-the-art GAN in dose conformality

Generates 3D dose predictions in under 30 seconds

Shows improved performance with overlapping lesions

Abstract

Evidence is accumulating in favour of using stereotactic ablative body radiotherapy (SABR) to treat multiple cancer lesions in the lung. Multi-lesion lung SABR plans are complex and require significant resources to create. In this work, we propose a novel two-stage latent transformer framework (LDFormer) for dose prediction of lung SABR plans with varying numbers of lesions. In the first stage, patient anatomical information and the dose distribution are encoded into a latent space. In the second stage, a transformer learns to predict the dose latent from the anatomical latents. Causal attention is modified to adapt to different numbers of lesions. LDFormer outperforms a state-of-the-art generative adversarial network on dose conformality in and around lesions, and the performance gap widens when considering overlapping lesions. LDFormer generates predictions of 3-D dose distributions in under 30s on consumer hardware, and has the potential to assist physicians with clinical decision making, reduce resource costs, and accelerate treatment planning.