# Brain-Oct-Pvt: A Physics-Guided Transformer with Radial Prior and Deformable Alignment for Neurovascular Segmentation

## TL;DR

This paper introduces Brain-OCT-PVT, a new deep learning model for neurovascular imaging that improves accuracy by adapting to the unique structure of OCT data.

## Contribution

The novel Brain-OCT-PVT model incorporates radial priors and deformable alignment to better handle neurovascular OCT segmentation.

## Key findings

- Brain-OCT-PVT achieves a Dice score of 95.06% on clinical OCT data.
- The model's specialized loss function improves boundary detection and handles class imbalance effectively.

## Abstract

The primary objective of this study is to develop a specialized deep learning framework specifically adapted for the unique physical characteristics of neurovascular Optical Coherence Tomography (OCT) imaging. Although Polyp-PVT, originally designed for polyp segmentation, shows promise for OCT analysis, it faces limitations in neurovascular applications. The default RGB input wastes resources on duplicated grayscale data, while its fixed-scale fusion struggles with vascular curvature variations. Furthermore, the attention mechanism fails to capture radial vessel patterns, and geometric constraints limit thin boundary detection. To address these challenges, we propose Brain-OCT-PVT with key innovations: a single-channel input stem reducing parameters by two-thirds; a Radial Intensity Module (RIM) using polar transforms and angular convolution to model annular structures; and a Deformable Cross-scale Fusion Module (D-CFM) with learnable offsets. The Boundary-aware Attention Module (BAM) combines Laplace edge detection with Swin-Transformer for sub-pixel consistency. A specialized loss function combines Dice Similarity Coefficient (Dice), BoundaryIoU on 2-pixel dilated edges, and Focal Tversky to handle extreme class imbalance. Evaluation on 13 clinical cases achieves a Dice score of 95.06% and an 95% Hausdorff Distance (HD95) of 0.269 mm, demonstrating superior performance compared to existing approaches.