FastCellpose: A Fast and Accurate Deep-Learning Framework for Segmentation of All Glomeruli in Mouse Whole-Kidney Microscopic Optical Images.

Automated evaluation of all glomeruli throughout the whole kidney is essential for the comprehensive study of kidney function as well as understanding the mechanisms of kidney disease and development. The emerging large-volume microscopic optical imaging techniques allow for the acquisition of mouse whole-kidney 3D datasets at a high resolution. However, fast and accurate analysis of massive imaging data remains a challenge. Here, we propose a deep learning-based segmentation method called FastCellpose to efficiently segment all glomeruli in whole mouse kidneys. Our framework is based on Cellpose, with comprehensive optimization in network architecture and the mask reconstruction process. By means of visual and quantitative analysis, we demonstrate that FastCellpose can achieve superior segmentation performance compared to other state-of-the-art cellular segmentation methods, and the processing speed was 12-fold higher than before. Based on this high-performance framework, we quantitatively analyzed the development changes of mouse glomeruli from birth to maturity, which is promising in terms of providing new insights for research on kidney development and function.

Deep self-learning enables fast, high-fidelity isotropic resolution restoration for volumetric fluorescence microscopy.

One intrinsic yet critical issue that troubles the field of fluorescence microscopy ever since its introduction is the unmatched resolution in the lateral and axial directions (i.e., resolution anisotropy), which severely deteriorates the quality, reconstruction, and analysis of 3D volume images. By leveraging the natural anisotropy, we present a deep self-learning method termed Self-Net that significantly improves the resolution of axial images by using the lateral images from the same raw dataset as rational targets. By incorporating unsupervised learning for realistic anisotropic degradation and supervised learning for high-fidelity isotropic recovery, our method can effectively suppress the hallucination with substantially enhanced image quality compared to previously reported methods. In the experiments, we show that Self-Net can reconstruct high-fidelity isotropic 3D images from organelle to tissue levels via raw images from various microscopy platforms, e.g., wide-field, laser-scanning, or super-resolution microscopy. For the first time, Self-Net enables isotropic whole-brain imaging at a voxel resolution of 0.2 × 0.2 × 0.2 µm3, which addresses the last-mile problem of data quality in single-neuron morphology visualization and reconstruction with minimal effort and cost. Overall, Self-Net is a promising approach to overcoming the inherent resolution anisotropy for all classes of 3D fluorescence microscopy.

Differential synthetic illumination based on multi-line detection for resolution and contrast enhancement of line confocal microscopy.

Line confocal (LC) microscopy is a fast 3D imaging technique, but its asymmetric detection slit limits resolution and optical sectioning. To address this, we propose the differential synthetic illumination (DSI) method based on multi-line detection to enhance the spatial resolution and optical sectioning capability of the LC system. The DSI method allows the imaging process to simultaneously accomplish on a single camera, which ensures the rapidity and stability of the imaging process. DSI-LC improves X- and Z-axis resolution by 1.28 and 1.26 times, respectively, and optical sectioning by 2.6 times compared to LC. Furthermore, the spatially resolved power and contrast are also demonstrated by imaging pollen, microtubule, and the fiber of the GFP fluorescence-labeled mouse brain. Finally, Video-rate imaging of zebrafish larval heart beating in a 665.6 × 332.8 µm2 field-of-view is achieved. DSI-LC provides a promising approach for 3D large-scale and functional imaging in vivo with improved resolution, contrast, and robustness.

Axial resolution and imaging contrast enhancement in inverted light-sheet microscopy by natural illumination modulation.

Inverted light-sheet microscopy (ILSM) is widely employed for fast large-volume imaging of biological tissue. However, the scattering especially in an uncleared sample, and the divergent propagation of the illumination beam lead to a trade-off between axial resolution and imaging depth. Herein, we propose naturally modulated ILSM (NM-ILSM) as a technique to improve axial resolution while simultaneously maintaining the wide field-of-view (FOV), and enhancing imaging contrast via background suppression. Theoretical derivations, simulations, and experimental imaging demonstrate 15% axial resolution increases, and fivefold greater image contrast compared with conventional ILSM. Therefore, NM-ILSM allows convenient imaging quality improvement for uncleared tissue and could extend the biological application scope of ILSM.

Cryo-fluorescence micro-optical sectioning tomography for volumetric imaging of various whole organs with subcellular resolution.

Optical visualization of complex microstructures in the entire organ is essential for biomedical research. However, the existing methods fail to accurately acquire the detailed microstructures of whole organs with good morphological and biochemical preservation. This study proposes a cryo-fluorescence micro-optical sectioning tomography (cryo-fMOST) to image whole organs in three dimensions (3D) with submicron resolution. The system comprises a line-illumination microscope module, cryo-microtome, three-stage refrigeration module, and heat insulation device. To demonstrate the imaging capacity and wide applicability of the system, we imaged and reconstructed various organs of mice in 3D, including the healthy tongue, kidney, and brain, as well as the infarcted heart. More importantly, imaged brain slices were performed sugar phosphates determination and fluorescence in situ hybridization imaging to verify the compatibility of multi-omics measurements. The results demonstrated that cryo-fMOST is capable of acquiring high-resolution morphological details of various whole organs and may be potentially useful for spatial multi-omics.

Deep-learning-based whole-brain imaging at single-neuron resolution.

Obtaining fine structures of neurons is necessary for understanding brain function. Simple and effective methods for large-scale 3D imaging at optical resolution are still lacking. Here, we proposed a deep-learning-based fluorescence micro-optical sectioning tomography (DL-fMOST) method for high-throughput, high-resolution whole-brain imaging. We utilized a wide-field microscope for imaging, a U-net convolutional neural network for real-time optical sectioning, and histological sectioning for exceeding the imaging depth limit. A 3D dataset of a mouse brain with a voxel size of 0.32 × 0.32 × 2 µm was acquired in 1.5 days. We demonstrated the robustness of DL-fMOST for mouse brains with labeling of different types of neurons.

Deep learning optical-sectioning method.

Current optical-sectioning methods require complex optical system or considerable computation time to improve imaging quality. Here we propose a deep learning-based method for optical sectioning of wide-field images. This method only needs one pair of contrast images for training to facilitate reconstruction of an optically sectioned image. The removal effect of background information and resolution that is achievable with our technique is similar to traditional optical-sectioning methods, but offers lower noise levels and a higher imaging depth. Moreover, reconstruction speed can be optimized to 14 Hz. This cost-effective and convenient method enables high-throughput optical sectioning techniques to be developed.