Sparse Reconstruction of Optical Doppler Tomography with Alternative State Space Model and Attention

2024-04-26

AI Summary

To address the bottlenecks of slow acquisition speed and large data storage in optical Doppler tomography (ODT) caused by high-density A-scan sampling, this paper proposes ASSAN, a sparse reconstruction framework that achieves high-fidelity blood flow B-scan reconstruction from a drastically reduced number of raw A-scans. Methodologically, ASSAN introduces a novel alternating modeling paradigm: a one-dimensional state-space model (SSM) captures depth-wise structural priors along the A-line; gated self-attention models inter-scan correlations along the B-line; and axially separable 1D convolutions enhance local feature representation. Evaluated on real animal experimental data, ASSAN significantly outperforms existing sparse ODT reconstruction methods. At equivalent reconstruction fidelity, it reduces A-scan sampling rates substantially—thereby simultaneously improving reconstruction accuracy, computational efficiency, and storage compression.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Optical coherence Doppler tomography (ODT) is an emerging blood flow imaging technique. The fundamental unit of ODT is the 1D depth-resolved trace named raw A-scans (or A-line). A 2D ODT image (B-scan) is formed by reconstructing a cross-sectional flow image via Doppler phase-subtraction of raw A-scans along B-line. To obtain a high-fidelity B-scan, densely sampled A-scans are required currently, leading to prolonged scanning time and increased storage demands. Addressing this issue, we propose a novel sparse ODT reconstruction framework with an Alternative State Space Attention Network (ASSAN) that effectively reduces raw A-scans needed. Inspired by the distinct distributions of information along A-line and B-line, ASSAN applies 1D State Space Model (SSM) to each A-line to learn the intra-A-scan representation, while using 1D gated self-attention along B-line to capture the inter-A-scan features. In addition, an effective feedforward network based on sequential 1D convolutions along different axes is employed to enhance the local feature. In validation experiments on real animal data, ASSAN shows clear effectiveness in the reconstruction in comparison with state-of-the-art reconstruction methods.

Problem

• Reduces A-scans needed for high-fidelity ODT imaging
• Improves sparse reconstruction with state space and attention
• Addresses prolonged scanning time and storage demands

Innovation

• Uses 1D State Space Model for A-line representation
• Applies 1D gated self-attention for B-line features
• Employs sequential 1D convolutions for local enhancement