A deep learning-based stripe self-correction method for stitched microscopic images

Abstract

The stitched fluorescence microscope images inevitably exist in various types of stripes or artifacts caused by uncertain factors such as optical devices or specimens, which severely affects the image quality and downstream quantitative analysis. In this paper, we present a deep learning-based Stripe Self-Correction method, so-called SSCOR. Specifically, we propose a proximity sampling scheme and adversarial reciprocal self-training paradigm that enable SSCOR to utilize stripe-free patches sampled from the stitched microscope image itself to correct their adjacent stripe patches. Comparing to off-the-shelf approaches, SSCOR can not only adaptively correct non-uniform, oblique, and grid stripes, but also remove scanning, bubble, and out-of-focus artifacts, achieving the state-of-the-art performance across different imaging conditions and modalities. Moreover, SSCOR does not require any physical parameter estimation, patch-wise manual annotation, and raw stitched information in the correction process, which provides an intelligent image quality optimization solution for microscopist or even microscope company, and facilitates more precise biomedical applications for researchers.

Supercontinuum intrinsic fluorescence imaging heralds free view of living systems

“…In a real-time fashion ( 43 ), UDVD may enable intraoperative assessment in surgical oncology ( 45 ). Also, the stripe self-correction of mosaicking-assisted image acquisition ( 46 ) helps reveal a novel large-scale structure of rat suprachiasmatic nucleus (figs. S22, S23) while 2PIF/4PIF visualization can improve targeted patching in 3D over THG triage ( 47 ) (Fig.…”

A universal and effective variational method for destriping: application to light-sheet microscopy, FIB-SEM and remote sensing images

“…We will concentrate on these categories, as they generalize well to several imaging methods and variations in image structures and stripe appearance. Additional approaches are average filtering [20,21], histogram matching [22,23], spline interpolation [24] and recently neural networks [25][26][27][28]. However, these are usually tailored for a specific appearance of images and stripes such that they are harder to transfer to other scenarios.…”

Enhancement of the resolution for low-quality fluorescence microscopy image by novel computational method

“…Fluorescence microscopy is the most commonly used technique for observation the dynamics of specific molecular labelled biological structures and is an indispensable tool in biomedical research. [1][2][3] However, due to the optical diffraction limit, there exists an upper bound on the image resolution obtained through conventional fluorescence imaging techniques. 4 The emergence of super-resolution fluorescence microscopy has provided sufficient details for the visualization of numerous subcellular structures, breaking this constraint and fundamentally revolutionizing the field of biological imaging.…”