Abstract
Pulsed laser diodes are used in photoacoustic tomography (PAT) as excitation sources because of their low cost, compact size, and high pulse repetition rate. In combination with multiple single-element ultrasound transducers (SUTs) the imaging speed of PAT can be improved. However, during PAT image reconstruction, the exact radius of each SUT is required for accurate reconstruction. Here we developed a novel deep learning approach to alleviate the need for radius calibration. We used a convolutional neural network (fully dense U-Net) aided with a convolutional long short-term memory block to reconstruct the PAT images. Our analysis on the test set demonstrates that the proposed network eliminates the need for radius calibration and improves the peak signal-to-noise ratio by ${\sim}{{73}}\%$ without compromising the image quality. In vivo imaging was used to verify the performance of the network.
© 2021 Optical Society of America
Full Article | PDF ArticleMore Like This
Sandeep Kumar Kalva, Zhe Zhi Hui, and Manojit Pramanik
J. Opt. Soc. Am. A 35(5) 764-771 (2018)
Zijian Deng, Wenzhao Li, and Changhui Li
Opt. Lett. 41(12) 2859-2862 (2016)
Sudeep Mondal, Subhadip Paul, Navjot Singh, and Ratan K Saha
Biomed. Opt. Express 14(11) 5817-5832 (2023)