https://scholars.lib.ntu.edu.tw/handle/123456789/615818
標題: | Patch-Based U-Net Model for Isotropic Quantitative Differential Phase Contrast Imaging | 作者: | Li, An-Cin Vyas, Sunil Lin, Yu-Hsiang YI-YOU HUANG HSUAN-MING HUANG YUAN LUO |
關鍵字: | Microscopy; Transfer functions; Imaging; Phase measurement; Image reconstruction; Biomedical measurement; Computer architecture; Coded-illumination; deep neural network; differential phase contrast; patch-based; quantitative phase imaging; U-net model; CycleGAN; NEURAL-NETWORKS | 公開日期: | 2021 | 出版社: | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | 卷: | 40 | 期: | 11 | 起(迄)頁: | 3229 | 來源出版物: | IEEE transactions on medical imaging | 摘要: | Quantitative differential phase-contrast (qDPC) imaging is a label-free phase retrieval method for weak phase objects using asymmetric illumination. However, qDPC imaging with fewer intensity measurements leads to anisotropic phase distribution in reconstructed images. In order to obtain isotropic phase transfer function, multiple measurements are required; thus, it is a time-consuming process. Here, we propose the feasibility of using deep learning (DL) method for isotropic qDPC microscopy from the least number of measurements. We utilize a commonly used convolutional neural network namely U-net architecture, trained to generate 12-axis isotropic reconstructed cell images (i.e. output) from 1-axis anisotropic cell images (i.e. input). To further extend the number of images for training, the U-net model is trained with a patch-wise approach. In this work, seven different types of living cell images were used for training, validation, and testing datasets. The results obtained from testing datasets show that our proposed DL-based method generates 1-axis qDPC images of similar accuracy to 12-axis measurements. The quantitative phase value in the region of interest is recovered from 66% up to 97%, compared to ground-truth values, providing solid evidence for improved phase uniformity, as well as retrieved missing spatial frequencies in 1-axis reconstructed images. In addition, results from our model are compared with paired and unpaired CycleGANs. Higher PSNR and SSIM values show the advantage of using the U-net model for isotropic qDPC microscopy. The proposed DL-based method may help in performing high-resolution quantitative studies for cell biology. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/615818 | ISSN: | 0278-0062 | DOI: | 10.1109/TMI.2021.3091207 |
顯示於: | 醫學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。