바로가기  >

Abstract
Acoustic-resolution photoacoustic microscopy (AR-PAM) enables visualization of biological tissues at depths of several millimeters with superior optical absorption contrast. However, the lateral resolution and sensitivity of AR-PAM are generally lower than those of optical-resolution PAM (OR-PAM) owing to the intrinsic physical acoustic focusing mechanism. Here, we demonstrate a computational strategy with two generative adversarial networks (GANs) to perform semi/unsupervised reconstruction with high resolution and sensitivity in AR-PAM by maintaining its imaging capability at enhanced depths. The b-scan PAM images were prepared as paired (for semi-supervised conditional GAN) and unpaired (for unsupervised CycleGAN) groups for label-free reconstructed AR-PAM b-scan image generation and training. The semi/unsupervised GANs successfully improved resolution and sensitivity in a phantom and in vivo mouse ear test with ground truth. We also confirmed that GANs could enhance resolution and sensitivity of deep tissues without the ground truth.

그림 (a, b) 마우스 귀 미세 혈관의 광음향 현미경 영상과 깊이 영상. (i) 저해상도 원본 광음향 현미경 영상, (ii) cGAN 영상 출력 결과, (iii) CycleGAN 영상 출력 결과, (iv) 고해상도 원본 영상

Affiliations

Thanh Dat Le 1, Jung-Joon Min 2, Changho Lee 3 4
1Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, 61186, Korea.
2Department of Nuclear Medicine, Chonnam National University Medical School and Hwasun Hospital, 264, Seoyang-ro, Hwasun-eup, Hwasun-gun, 58128, Jeollanam-do, Korea.
3Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, 61186, Korea. ch31037@jnu.ac.kr.
4Department of Nuclear Medicine, Chonnam National University Medical School and Hwasun Hospital, 264, Seoyang-ro, Hwasun-eup, Hwasun-gun, 58128, Jeollanam-do, Korea. ch31037@jnu.ac.kr.