Too bright for 2 dimensions: recent progress in advanced 3-dimensional microscopy of the kidney.

The kidney is a structurally and functionally complex organ responsible for the control of water, ion, and other solute homeostasis. Moreover, the kidneys excrete metabolic waste products and produce hormones, such as renin and erythropoietin. The functional unit of the kidney is the nephron, which is composed by a serial arrangement of a filter unit called the renal corpuscle and several tubular segments that modulate the filtered fluid by reabsorption and secretion. Within each kidney, thousands of nephrons are closely intermingled and surrounded by an intricate network of blood vessels and various interstitial cell types, including fibroblasts and immune cells. This complex tissue architecture is essential for proper kidney function. In fact, kidney disease is often reflected or even caused by a derangement of the histologic structures. Frequently, kidney histology is studied using microscopic analysis of 2-dimensional tissue sections, which, however, misses important 3-dimensional spatial information. Reconstruction of serial sections tries to overcome this limitation, but is technically challenging, time-consuming, and often inherently linked to sectioning artifacts. In recent years, advances in tissue preparation (e.g., optical clearing) and new light- and electron-microscopic methods have provided novel avenues for 3-dimensional kidney imaging. Combined with novel machine-learning algorithms, these approaches offer unprecedented options for large-scale and automated analysis of kidney structure and function. This review provides a brief overview of these emerging imaging technologies and presents key examples of how these approaches are already used to study the normal and the diseased kidney.

Deep learning is widely applicable to phenotyping embryonic development and disease.

Genome editing simplifies the generation of new animal models for congenital disorders. However, the detailed and unbiased phenotypic assessment of altered embryonic development remains a challenge. Here, we explore how deep learning (U-Net) can automate segmentation tasks in various imaging modalities, and we quantify phenotypes of altered renal, neural and craniofacial development in Xenopus embryos in comparison with normal variability. We demonstrate the utility of this approach in embryos with polycystic kidneys (pkd1 and pkd2) and craniofacial dysmorphia (six1). We highlight how in toto light-sheet microscopy facilitates accurate reconstruction of brain and craniofacial structures within X. tropicalis embryos upon dyrk1a and six1 loss of function or treatment with retinoic acid inhibitors. These tools increase the sensitivity and throughput of evaluating developmental malformations caused by chemical or genetic disruption. Furthermore, we provide a library of pre-trained networks and detailed instructions for applying deep learning to the reader's own datasets. We demonstrate the versatility, precision and scalability of deep neural network phenotyping on embryonic disease models. By combining light-sheet microscopy and deep learning, we provide a framework for higher-throughput characterization of embryonic model organisms. This article has an associated 'The people behind the papers' interview.