Establishment of data-domain sharing database for generative artificial intelligence-based photoacoustic tomography

The utilization of generative artificial intelligence models, such as GAN and diffusion model, is increasingly pervasive in the field of image processing. Generative models effectively learn the distribution of photoacoustic data to optimize and enhance image quality, demonstrating superior performance in photoacoustic tomography (PAT). While most image optimization efforts in PAT occur within the image domain, improving the quality of image reconstruction could be better achieved through direct optimization in the data-domain. However, the majority of publicly available datasets are currently based on the image domain, and the high cost and complexity of PAT systems contribute to a shortage of publicly available datasets in the data-domain. To address this issue, this study has established a data-domain sharing database. The dataset consists of photoacoustic signals captured from various samples at different sparse views using a self-designed and constructed system. This work aims to mitigate the deficiencies in data-domain database for PAT, thereby fostering the development of generative artificial intelligence in data-domain of photoacoustic imaging.