LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction

TL;DR

LENAS introduces a novel neural architecture search and ensemble method with knowledge distillation for improved 3D radiotherapy dose prediction, reducing complexity while enhancing accuracy.

Contribution

It combines neural architecture search with knowledge distillation to create diverse, high-performing models and a compact student network for efficient dose prediction.

Findings

Outperforms state-of-the-art methods on public datasets.

Effectively balances model diversity and accuracy.

Reduces inference complexity with a student network.

Abstract

Radiation therapy treatment planning requires balancing the delivery of the target dose while sparing normal tissues, making it a complex process. To streamline the planning process and enhance its quality, there is a growing demand for knowledge-based planning (KBP). Ensemble learning has shown impressive power in various deep learning tasks, and it has great potential to improve the performance of KBP. However, the effectiveness of ensemble learning heavily depends on the diversity and individual accuracy of the base learners. Moreover, the complexity of model ensembles is a major concern, as it requires maintaining multiple models during inference, leading to increased computational cost and storage overhead. In this study, we propose a novel learning-based ensemble approach named LENAS, which integrates neural architecture search with knowledge distillation for 3D radiotherapy dose prediction. Our approach starts by exhaustively searching each block from an enormous architecture space to identify multiple architectures that exhibit promising performance and significant diversity. To mitigate the complexity introduced by the model ensemble, we adopt the teacher-student paradigm, leveraging the diverse outputs from multiple learned networks as supervisory signals to guide the training of the student network. Furthermore, to preserve high-level semantic information, we design a hybrid-loss to optimize the student network, enabling it to recover the knowledge embedded within the teacher networks. The proposed method has been evaluated on two public datasets, OpenKBP and AIMIS. Extensive experimental results demonstrate the effectiveness of our method and its superior performance to the state-of-the-art methods.