A Feature based Reconstruction Model for Fluorescence Microscopy Image Denoising

Image Analysis Algorithm-Based Platform for Determining Micron and Higher Aggregate Size Distribution of Therapeutic IgG Using Brightfield and Fluorescence Microscope Images

A platform for determining size distribution of micron (1-100 μm) and larger (> 100 μm) aggregates of therapeutic IgG has been established by using image processing algorithms for brightfield and fluorescence microscope images. The algorithm for brightfield images involved conversion to grayscale followed by pixel-based and size-based thresholding. Morphological operations were then applied and the size distribution of aggregates were extracted. Fluorescence images of the aggregates of mAb tagged by a fluorescent dye were captured using widefield fluorescence microscope, confocal laser scanning microscope, and Cytell Cell Imaging System and the images were processed using a series of denoising steps followed by thresholding and morphological operations. The samples were subjected to different stresses, among which the aggregates were visible in the microscope for sample subjected to bubbling, stirring, and temperature. The images of these aggregates were effectively denoised and the size distribution of aggregates was analyzed using the algorithm. The overall aggregate size distribution obtained by image processing ranged in the micron and higher size range. The size obtained from brightfield image processing was validated using images of liquid chromatography resins. Further, the aggregate size distribution obtained using image processing was compared with experimental techniques such as Mastersizer 2000 and Micro Flow Imaging. It was found that analysis of IgG aggregates using image processing could serve as an orthogonal methodology to the existing approaches.

DETECTOR: structural information guided artifact detection for super-resolution fluorescence microscopy image

Super-resolution fluorescence microscopy, with a spatial resolution beyond the diffraction limit of light, has become an indispensable tool to observe subcellular structures at a nanoscale level. To verify that the super-resolution images reflect the underlying structures of samples, the development of robust and reliable artifact detection methods has received widespread attention. However, the existing artifact detection methods are prone to report false alert artifacts because it relies on absolute intensity mismatch between the wide-field image and resolution rescaled super-resolution image. To solve this problem, we proposed DETECTOR, a structural information-guided artifact detection method for super-resolution images. It detects artifacts by computing the structural dissimilarity between the wide-field image and the resolution rescaled super-resolution image. To focus on structural similarity, we introduce a weight mask to weaken the influence of strong autofluorescence background and proposed a structural similarity index for super-resolution images, named MASK-SSIM. Simulations and experimental results demonstrated that compared with the state-of-the-art methods, DETECTOR has advantages in detecting structural artifacts in super-resolution images. It is especially suitable for wide-field images with strong autofluorescence background and super-resolution images of single molecule localization microscopy (SMLM). DETECTOR has extreme sensitivity to the weak signal region. Moreover, DETECTOR can guide data collection and parameter tuning during image reconstruction.

Novel semi-automated fluorescence microscope imaging algorithm for monitoring IgG aggregates in serum

Analysis of therapeutic IgG aggregates in serum is a potential area of investigation as it can give deeper insights about the function, immunogenic issues and protein interaction associated with the aggregates. To overcome various complexities associated with the existing analytical techniques for analyzing aggregates in serum, a novel florescence microscopy-based image processing approach was developed. The monoclonal antibody (mAb) was tagged with a fluorescent dye, fluorescein isothiocyanate (FITC). Aggregates, generated by stirring, were spiked into serum and images were captured at various time points. After denoising, thresholding by weighted median, 1D Otsu, and 2D Otsu was attempted and a modified 2D Otsu, a new mode of thresholding, was developed. This thresholding method was found to be highly effective in removing noises and retaining analyte sizes. Out of 0–255, the optimized threshold value obtained for the images discussed in modified 2D Otsu was 9 while 2D Otsu’s overestimated values were 38 and 48. Other morphological operations were applied after thresholding and the area, perimeter, circularity, and radii of the aggregates in these images were calculated. The proposed algorithm offers an approach for analysis of aggregates in serum that is simpler to implement and is complementary to existing approaches.

Artefact removal in ground truth deficient fluctuations-based nanoscopy images using deep learning

Image denoising or artefact removal using deep learning is possible in the availability of supervised training dataset acquired in real experiments or synthesized using known noise models. Neither of the conditions can be fulfilled for nanoscopy (super-resolution optical microscopy) images that are generated from microscopy videos through statistical analysis techniques. Due to several physical constraints, a supervised dataset cannot be measured. Further, the non-linear spatio-temporal mixing of data and valuable statistics of fluctuations from fluorescent molecules that compete with noise statistics. Therefore, noise or artefact models in nanoscopy images cannot be explicitly learned. Here, we propose a robust and versatile simulation-supervised training approach of deep learning auto-encoder architectures for the highly challenging nanoscopy images of sub-cellular structures inside biological samples. We show the proof of concept for one nanoscopy method and investigate the scope of generalizability across structures, and nanoscopy algorithms not included during simulation-supervised training. We also investigate a variety of loss functions and learning models and discuss the limitation of existing performance metrics for nanoscopy images. We generate valuable insights for this highly challenging and unsolved problem in nanoscopy, and set the foundation for the application of deep learning problems in nanoscopy for life sciences.

Fast and accurate sCMOS noise correction for fluorescence microscopy

The rapid development of scientific CMOS (sCMOS) technology has greatly advanced optical microscopy for biomedical research with superior sensitivity, resolution, field-of-view, and frame rates. However, for sCMOS sensors, the parallel charge-voltage conversion and different responsivity at each pixel induces extra readout and pattern noise compared to charge-coupled devices (CCD) and electron-multiplying CCD (EM-CCD) sensors. This can produce artifacts, deteriorate imaging capability, and hinder quantification of fluorescent signals, thereby compromising strategies to reduce photo-damage to live samples. Here, we propose a content-adaptive algorithm for the automatic correction of sCMOS-related noise (ACsN) for fluorescence microscopy. ACsN combines camera physics and layered sparse filtering to significantly reduce the most relevant noise sources in a sCMOS sensor while preserving the fine details of the signal. The method improves the camera performance, enabling fast, low-light and quantitative optical microscopy with video-rate denoising for a broad range of imaging conditions and modalities.

Scientific complementary metal-oxide semiconductor (sCMOS) cameras have advanced the imaging field, but they often suffer from additional noise compared to CCD sensors. Here the authors present a content-adaptive algorithm for the automatic correction of sCMOS-related noise for fluorescence microscopy.