Unsupervised Learning for Enhanced Computed Photoacoustic Microscopy

被引:0
|
作者
Yang, Lulin [1 ]
Chen, Wenjing [1 ]
Kou, Tingdong [1 ]
Li, Chenyang [2 ]
You, Meng [2 ]
Shen, Junfei [1 ]
机构
[1] Sichuan Univ, Coll Elect & Informat Engn, Chengdu 610065, Peoples R China
[2] Sichuan Univ, West China Hosp Stomatol, Dept Oral Med Imaging, State Key Lab Oral Dis,Natl Clin Res Ctr Oral Dis, Chengdu 610041, Peoples R China
关键词
photoacoustic imaging; photoacoustic microscopy; unsupervised learning; TOMOGRAPHY;
D O I
10.3390/electronics13040693
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Photoacoustic microscopy (PAM) is a medical-imaging technique with the merits of high contrast and resolution. Nevertheless, conventional PAM scans specimens in a diameter-by-diameter fashion, resulting in a time-consuming process. Furthermore, deep-learning-based PAM image enhancement necessitates acquiring ground-truth data for training purposes. In this paper, we built an optical-resolution photoacoustic microscopy system and introduced an innovative unsupervised-learning algorithm. First, we enhanced the rotational-scanning method, transitioning from a diameter-by-diameter approach to a sector-by-sector one, significantly reducing imaging time (from 280 s to 109 s). Second, by establishing a metric for unsupervised learning, we eliminated the need for collecting reliable and high-quality ground truth, which is a challenging task in photoacoustic microscopy. A total of 324 pairs of datasets (mouse ears) were collected for unsupervised learning, with 274 for training and 50 for testing. Additionally, carbon-fiber data were sampled for lateral resolution and contrast evaluation, as well as the effective rate evaluation of the algorithm. The enhanced images demonstrated superior performance compared with that of maximum projection, both subjectively and objectively. A 76% improvement in the lateral resolution was observed. The effective rate of the algorithm was measured to be 100%, which was tested on 50 random samples. The technique presented in this paper holds substantial potential for image postprocessing and opens new avenues for unsupervised learning in photoacoustic microscopy.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] Photoacoustic computed microscopy
    Lei Yao
    Lei Xi
    Huabei Jiang
    [J]. Scientific Reports, 4
  • [2] Photoacoustic computed microscopy
    Yao, Lei
    Xi, Lei
    Jiang, Huabei
    [J]. SCIENTIFIC REPORTS, 2014, 4
  • [3] Enhanced resolution and sensitivity acoustic-resolution photoacoustic microscopy with semi/unsupervised GANs
    Le, Thanh Dat
    Min, Jung-Joon
    Lee, Changho
    [J]. SCIENTIFIC REPORTS, 2023, 13 (01)
  • [4] Enhanced resolution and sensitivity acoustic-resolution photoacoustic microscopy with semi/unsupervised GANs
    Thanh Dat Le
    Jung-Joon Min
    Changho Lee
    [J]. Scientific Reports, 13
  • [5] Optical resolution photoacoustic computed microscopy
    Qi, Weizhi
    Liang, Xiao
    Ji, Yaoyao
    Liu, Chengbo
    Xi, Lei
    [J]. OPTICS LETTERS, 2021, 46 (02) : 372 - 375
  • [6] Multiscale photoacoustic microscopy and computed tomography
    Wang, Lihong V.
    [J]. NATURE PHOTONICS, 2009, 3 (09) : 503 - 509
  • [7] Multiscale photoacoustic microscopy and computed tomography
    Wang L.V.
    [J]. Nature Photonics, 2009, 3 (9) : 503 - 509
  • [8] Tutorial on photoacoustic microscopy and computed tomography
    Wang, Lihong V.
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS, 2008, 14 (01) : 171 - 179
  • [9] Machine-learning enhanced photoacoustic computed tomography in a limited view configuration
    Deng, Handi
    Wang, Xuanhao
    Cai, Chuangjian
    Luo, Jianwen
    Ma, Cheng
    [J]. ADVANCED OPTICAL IMAGING TECHNOLOGIES II, 2019, 11186
  • [10] Wide-field photoacoustic-computed microscopy
    Jiang, Bowen
    Yang, Xiaoquan
    Li, Xiangping
    Cao, Yaoyu
    [J]. 2017 ASIA COMMUNICATIONS AND PHOTONICS CONFERENCE (ACP), 2017,