SAM2-Aug: Prior knowledge-based Augmentation for Target Volume Auto-Segmentation in Adaptive Radiation Therapy Using Segment Anything Model 2

TL;DR

This paper introduces SAM2-Aug, an enhanced segmentation model for adaptive radiation therapy that leverages prior images and robust prompts to improve tumor segmentation accuracy and generalization across different datasets.

Contribution

The paper presents novel prior knowledge-based augmentation strategies that significantly improve SAM2's performance and robustness in tumor segmentation tasks for ART.

Findings

SAM2-Aug achieved Dice scores of 0.86, 0.89, and 0.90 on liver, abdomen, and brain datasets.

The model outperformed existing convolutional, transformer-based, and prompt-driven models.

Incorporating prior images and prompt augmentation enhances segmentation accuracy and generalizability.

Abstract

Purpose: Accurate tumor segmentation is vital for adaptive radiation therapy (ART) but remains time-consuming and user-dependent. Segment Anything Model 2 (SAM2) shows promise for prompt-based segmentation but struggles with tumor accuracy. We propose prior knowledge-based augmentation strategies to enhance SAM2 for ART. Methods: Two strategies were introduced to improve SAM2: (1) using prior MR images and annotations as contextual inputs, and (2) improving prompt robustness via random bounding box expansion and mask erosion/dilation. The resulting model, SAM2-Aug, was fine-tuned and tested on the One-Seq-Liver dataset (115 MRIs from 31 liver cancer patients), and evaluated without retraining on Mix-Seq-Abdomen (88 MRIs, 28 patients) and Mix-Seq-Brain (86 MRIs, 37 patients). Results: SAM2-Aug outperformed convolutional, transformer-based, and prompt-driven models across all datasets, achieving Dice scores of 0.86(liver), 0.89(abdomen), and 0.90(brain). It demonstrated strong generalization across tumor types and imaging sequences, with improved performance in boundary-sensitive metrics. Conclusions: Incorporating prior images and enhancing prompt diversity significantly boosts segmentation accuracy and generalizability. SAM2-Aug offers a robust, efficient solution for tumor segmentation in ART. Code and models will be released at https://github.com/apple1986/SAM2-Aug.