SAS-Net: Scene-Appearance Separation Network for Robust Spatiotemporal Registration in Bidirectional Photoacoustic Microscopy

2026-02-06

AI Summary

In bidirectional scanning photoacoustic microscopy, domain shifts and geometric distortions induced by opposing scan directions violate the brightness constancy assumption underlying conventional registration methods. To address this challenge, this work proposes the first scene-appearance disentanglement framework, leveraging a deep neural network to separate domain-invariant scene content from domain-specific appearance features, thereby jointly achieving domain adaptation and spatial registration. The model is trained end-to-end with a multi-objective loss comprising scene consistency in the latent space, domain alignment, and cycle consistency. Evaluated on in vivo mouse cerebral vasculature imaging, the method achieves a normalized cross-correlation (NCC) of 0.961 and structural similarity (SSIM) of 0.894, with single-frame inference at 11.2 ms (86 fps), significantly outperforming existing approaches and enabling real-time applications.

Technology Category

• Computer Vision: Scene Analysis & Understanding
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

High-speed optical-resolution photoacoustic microscopy (OR-PAM) with bidirectional scanning enables rapid functional brain imaging but introduces severe spatiotemporal misalignment from coupled scan-direction-dependent domain shift and geometric distortion. Conventional registration methods rely on brightness constancy, an assumption violated under bidirectional scanning, leading to unreliable alignment. A unified scene-appearance separation framework is proposed to jointly address domain shift and spatial misalignment. The proposed architecture separates domain-invariant scene content from domain-specific appearance characteristics, enabling cross-domain reconstruction with geometric preservation. A scene consistency loss promotes geometric correspondence in the latent space, linking domain shift correction with spatial registration within a single framework. For in vivo mouse brain vasculature imaging, the proposed method achieves normalized cross-correlation (NCC) of 0.961 and structural similarity index (SSIM) of 0.894, substantially outperforming conventional methods. Ablation studies demonstrate that domain alignment loss is critical, with its removal causing 82% NCC reduction (0.961 to 0.175), while scene consistency and cycle consistency losses provide complementary regularization for optimal performance. The method achieves 11.2 ms inference time per frame (86 fps), substantially exceeding typical OR-PAM acquisition rates and enabling real-time processing. These results suggest that the proposed framework enables robust high-speed bidirectional OR-PAM for reliable quantitative and longitudinal functional imaging. The code will be publicly available at https://github.com/D-ST-Sword/SAS-Net

Problem

• spatiotemporal misalignment
• bidirectional scanning
• domain shift
• geometric distortion
• photoacoustic microscopy

Innovation

• scene-appearance separation
• spatiotemporal registration
• bidirectional photoacoustic microscopy
• domain shift correction
• real-time inference