Cascade neural approximating for few-shot super-resolution photoacoustic angiography

被引:5
|
作者
Ma, Yuanzheng [1 ,2 ]
Xiong, Kedi [1 ,2 ,3 ]
Hou, Xuefei [3 ]
Zhang, Wuyu [1 ,2 ]
Chen, Xin [1 ,2 ]
Li, Ling [3 ]
Yang, Sihua [1 ,2 ,3 ]
机构
[1] South China Normal Univ, MOE Key Lab Laser Life Sci, Coll Biophoton, Guangzhou 510631, Peoples R China
[2] South China Normal Univ, Inst Laser Life Sci, Coll Biophoton, Guangzhou 510631, Peoples R China
[3] South China Normal Univ, Coll Biophoton, Guangdong Prov Key Lab Laser Life Sci, Guangzhou 510631, Peoples R China
基金
中国国家自然科学基金;
关键词
NETWORKS;
D O I
10.1063/5.0100424
中图分类号
O59 [应用物理学];
学科分类号
摘要
High-resolution photoacoustic angiography images are reconstructed from undersampled images with the help of a super-resolution deep neural network, enhancing the ability of the photoacoustic angiography systems to image dynamic processes in living tissues. However, image degradations are difficult to estimate due to a lack of knowledge of the point spread function and noise sources, resulting in poor generalization capability of the trained super-resolution model. In this work, a high-order residual cascade neural network was developed to reconstruct high-resolution vascular images, which is a neural approximating approach used to remove image degradations of photoacoustic angiography. To handle overfitting in training super-resolution model with a limited dataset, we proposed a BicycleGAN based image synthesis method in data preparation, achieving a strong regularization by forging realistic photoacoustic vascular images that act to essentially increase the training dataset. The quantitative analysis of the reconstructed results shows that the high-order residual cascade neural network surpassed the other residual super-resolution neural networks. Most importantly, we demonstrated that the generalized model could be achieved despite the limited training dataset, promising to be a methodology for few-shot super-resolution photoacoustic angiography.
引用
收藏
页数:7
相关论文
共 50 条
  • [41] DOVE: Doodled vessel enhancement for photoacoustic angiography super resolution
    Ma, Yuanzheng
    Zhou, Wangting
    Ma, Rui
    Wang, Erqi
    Yang, Sihua
    Tang, Yansong
    Zhang, Xiao-Ping
    Guan, Xun
    Medical Image Analysis, 2024, 94
  • [42] Super-Resolution Photoacoustic Microscopy via Modified Phase Compounding
    Amjadian, Mohammadreza
    Mostafavi, Seyed Masood
    Chen, Jiangbo
    Wang, Lidai
    Luo, Zhengtang
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2022, 41 (11) : 3411 - 3420
  • [43] Erratum: Super-resolution photoacoustic imaging through a scattering wall
    Donald B. Conkey
    Antonio M. Caravaca-Aguirre
    Jake D. Dove
    Hengyi Ju
    Todd W. Murray
    Rafael Piestun
    Nature Communications, 6
  • [44] Super-Resolution Photoacoustic Microscopy Using Structured-Illumination
    Amjadian, Mohammadreza
    Mostafavi, Seyed Masood
    Chen, Jiangbo
    Kavehvash, Zahra
    Zhu, Jingyi
    Wang, Lidai
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2021, 40 (09) : 2197 - 2207
  • [45] Super-resolution photoacoustic microscopy using blind structured illumination
    Murray, Todd W.
    Haltmeier, Markus
    Berer, Thomas
    Leiss-Holzinger, Elisabeth
    Burgholzer, Peter
    OPTICA, 2017, 4 (01): : 17 - 22
  • [46] Super-resolution photoacoustic fluctuation imaging with multiple speckle illumination
    Chaigne, Thomas
    Gateau, Jerome
    Allain, Marc
    Katz, Ori
    Gigan, Sylvain
    Sentenac, Anne
    Bossy, Emmanuel
    OPTICA, 2016, 3 (01): : 54 - 57
  • [47] FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization
    Yang, Jiawei
    Pavone, Marco
    Wang, Yue
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 8254 - 8263
  • [48] Towards Few-Shot Self-explaining Graph Neural Networks
    Peng, Jingyu
    Liu, Qi
    Yue, Linan
    Zhang, Zaixi
    Zhang, Kai
    Sha, Yunhao
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES-RESEARCH TRACK, PT VI, ECML PKDD 2024, 2024, 14946 : 109 - 126
  • [49] SANS: Setwise Attentional Neural Similarity Method for Few-Shot Recommendation
    Zhang, Zhenghao
    Lu, Tun
    Li, Dongsheng
    Zhang, Peng
    Gu, Hansu
    Gu, Ning
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2021), PT III, 2021, 12683 : 69 - 84
  • [50] Few-Shot Semantic Segmentation via Frequency Guided Neural Network
    Rao, Xiya
    Lu, Tao
    Wang, Zhongyuan
    Zhang, Yanduo
    IEEE SIGNAL PROCESSING LETTERS, 2022, 29 : 1092 - 1096