Deep Learning Adapted Acceleration for Limited-view Photoacoustic Computed Tomography

TL;DR

This paper introduces a deep learning-enhanced model-based reconstruction method for limited-view photoacoustic tomography, achieving faster, higher-quality images with fewer iterations and demonstrating superior performance over existing techniques.

Contribution

A novel deep learning integrated variational model for rapid, high-quality limited-view PA image reconstruction with automatic parameter learning.

Findings

Outperforms existing methods with half-view data in simulations and real experiments.

Achieves high SSIM scores (over 0.94 in vivo) demonstrating robustness and accuracy.

Requires only three iterations for superior image quality.

Abstract

Photoacoustic imaging (PAI) is a non-invasive imaging modality that detects the ultrasound signal generated from tissue with light excitation. Photoacoustic computed tomography (PACT) uses unfocused large-area light to illuminate the target with ultrasound transducer array for PA signal detection. Limited-view issue could cause a low-quality image in PACT due to the limitation of geometric condition. The model-based method is used to resolve this problem, which contains different regularization. To adapt fast and high-quality reconstruction of limited-view PA data, in this paper, a model-based method that combines the mathematical variational model with deep learning is proposed to speed up and regularize the unrolled procedure of reconstruction. A deep neural network is designed to adapt the step of the gradient updated term of data consistency in the gradient descent procedure, which can obtain a high-quality PA image only with a few iterations. Note that all parameters and priors are automatically learned during the offline training stage. In experiments, we show that this method outperforms the other methods with half-view (180 degrees) simulation and real data. The comparison of different model-based methods show that our proposed scheme has superior performances (over 0.05 for SSIM) with same iteration (3 times) steps. Furthermore, an unseen data is used to validate the generalization of different methods. Finally, we find that our method obtains superior results (0.94 value of SSIM for in vivo) with a high robustness and accelerated reconstruction.