Dc-EEMF: Pushing depth-of-field limit of photoacoustic microscopy via decision-level constrained learning

2025-05-29

AI Summary

Traditional optical-resolution photoacoustic microscopy (OR-PAM) suffers from limited depth-of-field (DoF) due to Gaussian beam illumination, hindering high-fidelity structural resolution along the axial direction. To overcome this DoF bottleneck, we propose a decision-level constrained end-to-end multifocal image fusion framework. Our method introduces a novel decision-level focus-characteristic constraint that enforces physical consistency in depth-dependent response; integrates channel-adaptive spatial-frequency features to suppress fusion artifacts; and employs a U-Net–driven perceptual loss jointly optimizing spatial structural fidelity and spectral consistency. This lightweight, fully end-to-end trainable architecture requires no ground-truth labels or post-processing, preserving sub-micron lateral resolution while significantly extending the effective DoF. Extensive experimental and numerical validations demonstrate robust performance across diverse preclinical and clinical imaging scenarios.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

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
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Photoacoustic microscopy holds the potential to measure biomarkers' structural and functional status without labels, which significantly aids in comprehending pathophysiological conditions in biomedical research. However, conventional optical-resolution photoacoustic microscopy (OR-PAM) is hindered by a limited depth-of-field (DoF) due to the narrow depth range focused on a Gaussian beam. Consequently, it fails to resolve sufficient details in the depth direction. Herein, we propose a decision-level constrained end-to-end multi-focus image fusion (Dc-EEMF) to push DoF limit of PAM. The DC-EEMF method is a lightweight siamese network that incorporates an artifact-resistant channel-wise spatial frequency as its feature fusion rule. The meticulously crafted U-Net-based perceptual loss function for decision-level focus properties in end-to-end fusion seamlessly integrates the complementary advantages of spatial domain and transform domain methods within Dc-EEMF. This approach can be trained end-to-end without necessitating post-processing procedures. Experimental results and numerical analyses collectively demonstrate our method's robust performance, achieving an impressive fusion result for PAM images without a substantial sacrifice in lateral resolution. The utilization of Dc-EEMF-powered PAM has the potential to serve as a practical tool in preclinical and clinical studies requiring extended DoF for various applications.

Problem

• Extends depth-of-field in photoacoustic microscopy imaging
• Overcomes limited depth range in conventional OR-PAM
• Enhances image fusion without sacrificing lateral resolution

Innovation

• Decision-level constrained end-to-end multi-focus fusion
• Lightweight siamese network with artifact-resistant features
• U-Net-based perceptual loss for seamless fusion