Making sense of blobs, whorls, and shades: methods for label-free, inverse imaging in bright-field optical microscopy.

Despite its long history and widespread use, conventional bright-field optical microscopy has received recent attention as an excellent option to perform accurate, label-free, imaging of biological objects. As with any imaging system, bright-field produces an ill-defined representation of the specimen, in this case characterized by intertwined phase and amplitude in image formation, invisibility of phase objects at exact focus, and both positive and negative contrast present in images. These drawbacks have prevented the application of bright-field to the accurate imaging of unlabeled specimens. To address these challenges, a variety of methods using hardware, software or both have been developed, with the goal of providing solutions to the inverse imaging problem set in bright-field. We revise the main operating principles and characteristics of bright-field microscopy, followed by a discussion of the solutions (and potential limitations) to reconstruction in two dimensions (2D). We focus on methods based on conventional optics, including defocusing microscopy, transport of intensity, ptychography and deconvolution. Advances to achieving three-dimensional (3D) bright-field imaging are presented, including methods that exploit multi-view reconstruction, physical modeling, deep learning and conventional digital image processing. Among these techniques, optical sectioning in bright-field microscopy (OSBM) constitutes a direct approach that captures z-image stacks using a standard microscope and applies digital filters in the spatial domain, yielding inverse-imaging solutions in 3D. Finally, additional techniques that expand the capabilities of bright-field are discussed. Label-free, inverse imaging in conventional optical microscopy thus emerges as a powerful biophysical tool for accurate 2D and 3D imaging of biological samples.