High-Resolution Image Processing of Probe-Based Confocal Laser Endomicroscopy Based on Multistage Neural Networks and Cross-Channel Attention Module
Open Access
Abstract
Probe-based confocal laser endomicroscopy (pCLE) is a subcellular in vivo imaging technique that generates diagnostic images revealing malignant structural modifications in epithelial tissues. In the clinical diagnosis of probe confocal laser endomicroscopy (pCLE), the image background generally has the problems of dynamic blur or information loss, which is not conducive to achieving high-resolution and clear pCLE imaging. In recent years, deep learning technology has achieved remarkable results in image deblurring. For the task of recovering high-resolution pCLE images, the current methods still suffer from the following drawbacks: it is difficult to choose a strategy to make CNN converge at a deeper level and mainstream methods cannot handle the complex balance between spatial details and high-level feature information well when reconstructing clear images. In order to solve the problem, we propose a new cross-channel attention, multistage, high-resolution pCLE image deblurring structure. This methodology improves the supervised attention mechanism, enhances the ability of feature extraction and fusion capabilities, and improves the quality of image deblurring by adding cross-channel attention module (CAM) into the multistage neural networks’ architecture. The experimental results show that the average peak signal-to-noise ratio (PSNR) of the proposed model on the dataset is as high as 29.643 dB, and the structural similarity (SSIM) reaches 0.855. This method is superior to the prior algorithms in the visualization of recovered images, and the edge and texture details of the restored pCLE images are clearer.Keywords
Funding Information
- National Natural Science Foundation of China (62375026, IPOC2021ZT06)
- Fund of the State Key Laboratory of IPOC (BUPT) (62375026, IPOC2021ZT06)
This publication has 35 references indexed in Scilit:
- Content-aware image restoration: pushing the limits of fluorescence microscopyNature Methods, 2018
- Deep learning-based detection of motion artifacts in probe-based confocal laser endomicroscopy imagesInternational Journal of Computer Assisted Radiology and Surgery, 2018
- FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image DenoisingIEEE Transactions on Image Processing, 2018
- Single-frame 3D fluorescence microscopy with ultraminiature lensless FlatScopeScience Advances, 2017
- Error bounds for approximations with deep ReLU networksNeural Networks, 2017
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image DenoisingIEEE Transactions on Image Processing, 2017
- Line-scanning fiber bundle endomicroscopy with a virtual detector slitBiomedical Optics Express, 2016
- High speed, line-scanning, fiber bundle fluorescence confocal endomicroscopy for improved mosaickingBiomedical Optics Express, 2015
- Fast image/video upsamplingACM Transactions on Graphics, 2008
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004