# Geometric and dosimetric evaluation of auto-segmentation of brain arteriovenous malformations using multimodal imaging in stereotactic radiosurgery

## TL;DR

This paper introduces a deep learning method to automatically segment brain arteriovenous malformations using multimodal imaging, improving efficiency and protecting white matter tracts during radiation therapy.

## Contribution

A novel two-stage deep learning model combining 2D U-Net and 3D self-attention mechanisms for accurate and efficient bAVM segmentation in radiosurgery planning.

## Key findings

- The model achieved a DSC of 0.84 ± 0.05 and strong dosimetric concordance with manual contours.
- Minimal differences in white matter tract inclusion and dosimetric parameters between automated and manual segmentation were observed.
- The method preserves clinical fidelity while improving operational efficiency in radiosurgery planning.

## Abstract

Optimizing radiation dose to protect white matter (WM) tracts during stereotactic radiosurgery (SRS) of brain arteriovenous malformations (bAVMs) necessitates the integration of diffusion tensor imaging (DTI)-based WM tractography to delineate WM tracts and establish dose constraints. Conventional manual delineation of perilesional targets demonstrated significant operational inefficiency, primarily attributed to the complex structural interdigitation between pathological vasculature and eloquent brain areas.

This study aimed to develop a two-stage deep learning (DL) method that combines a two-dimensional (2D) U-Net detection-aided and three-dimensional (3D) self-attention segmentation model for automatic bAVM segmentation. This method focuses on improving efficiency in clinical practice while protecting WM tracts using multimodal imaging and WM tractography in SRS.

We analyzed imaging data from 191 patients who underwent CyberKnife-based SRS at Huashan Hospital, Fudan University, with bAVMs closely adjacent to WM tracts. A total of 153 patients were used to construct a two-stage DL model to segment the bAVMs on multimodal imaging and WM tractography, while the remaining 38 patients were utilized to validate the model's performance. We introduced spatial and channel attention modules in the U-Net variant, along with a versatile “Attentional ResBlock,” achieving parameter efficiency through cross-dimensional interaction while preserving model fidelity. The accuracy of the auto-segmented contours is evaluated using geometric indices and dosimetric endpoints.

Our proposed model demonstrated superior segmentation performance, achieving a dice similarity coefficient (DSC) of 0.84 ± 0.05, sensitivity of 0.92 ± 0.09, and F2-score of 0.79 ± 0.08. Furthermore, it attained a low Hausdorff distance (4.55 ± 1.14 mm) and mean surface distance (0.53 ± 0.08 mm), indicating exceptional boundary delineation precision. The difference in the proportion of WM tracts within the target region between manual and our automated contours is minimal (0.08 ± 0.13). Meanwhile, strong concordance is observed between auto-segmented and manually contoured targets across the majority of dosimetric endpoints, with a mean difference of 0.46 Gy. The received dose of WM tracts in the two comparison plans also has an acceptable representation of dosimetric parameters (R2 = 0.92 for Dmean and 0.88 for V1Gy). Dose exposition of the organ at risk (OAR) shows no statistically significant differences in treatment plans with auto-segmentation targets compared to regular plans.

The reliable bAVM automated-segmentation method has been validated and may support SRS planning for bAVMs and thus avoid neurological sequelae after SRS in considering WM tracts protection.