计算机科学
卷积神经网络
图像复原
人工智能
成像体模
深度学习
计算机视觉
光学
扩散
光子
图像(数学)
物理
模式识别(心理学)
图像处理
热力学
作者
Xuanxuan Zhang,Jiapei Cui,Yunfei Jia,Peng Zhang,Fan Song,Xu Cao,Jiulou Zhang,Lin Zhang,Guanglei Zhang
摘要
Optical macroscopic imaging techniques have shown great significance in the investigations of biomedical issues by revealing structural or functional information of living bodies through the detection of visible or near-infrared light derived from different mechanisms. However, optical macroscopic imaging techniques suffer from poor spatial resolution due to photon diffusion in biological tissues. This dramatically restricts the application of optical imaging techniques in numerous situations. In this paper, an image restoration method based on deep learning is proposed to eliminate the blur caused by photon diffusion in optical macroscopic imaging. Two blurry images captured at orthogonal angles are used as the additional information to ensure the uniqueness of the solution and restore the small targets at deep locations. Then a fully convolutional neural network is proposed to accomplish the image restoration, which consists of three sectors: V-shaped network for central view, V-shaped network for side views, and synthetical path. The two V-shaped networks are concatenated to the synthetical path with skip connections to generate the output image. Simulations as well as phantom and mouse experiments are implemented. Results indicate the effectiveness of the proposed method.
科研通智能强力驱动
Strongly Powered by AbleSci AI