Journal of biomedical optics
Benchmarking deep learning-based reconstruction methods for photoacoustic computed tomography with clinically relevant synthetic datasets
By Chen P, Park S, Jeong G and 3 others.
Abstract
Significance
Deep learning (DL)-based image reconstruction methods for photoacoustic computed tomography (PACT) have developed rapidly in recent years. However, most existing methods have not employed standardized datasets, and their evaluations rely on traditional image quality (IQ) metrics that may lack clinical relevance. The absence of a standardized framework for clinically meaningful IQ assessment hinders fair comparison and raises concerns about the reproducibility and reliability of reported advancements in PACT.
Aim
A benchmarking framework is proposed that provides open-source, anatomically plausible synthetic datasets and evaluation strategies for DL-based acoustic inversion methods in PACT. Approach: The datasets each include over 10,000 two-dimensional (2D) stochastic breast objects with clinically relevant lesions and paired measurements at varying modeling complexity. The evaluation strategies incorporate both traditional and task-based IQ measures to assess fidelity and clinical utility. A preliminary benchmarking study is conducted to demonstrate the framework's utility by comparing DL-based and physics-based reconstruction methods.