Learning-Based Optical Fiber Cell Imaging

Real-time visualization of cell morphology and tissue architecture in vivo are of great importance to biomedical research and clinical practice, yet it is a formidable task for conventional microscopy. Fiber-optic imaging systems (FOISs), with miniature size and flexible image transfer capabilities, have been applied for this purpose, but they are limited by poor compatibility with broadband illumination, bulky distal optics, low imaging quality and speed, and extreme sensitivity to perturbations. Current limitations are mainly due to the physical properties of optical fibers and image processing techniques. Widely used optical fibers, such as multicore optical fibers and multimode optical fibers, suffer from strong mode coupling and low mode densities.

The glass–air Anderson localizing optical fiber (GALOF) is a potential solution to break through current limitations in the next generation of FOISs. Although the GALOF is also a highly multimodal system, the modes are strongly localized in the transverse plane and show single-mode-like properties, such as nearly diffraction-limited beam quality. In contrast to conventional multicore or multimode optical fibers, the GALOF is exceptionally robust to perturbations and compatible with broadband illuminations, due to the wavelength independence of the transverse Anderson localization.

Recently, a team of researchers led by Axel Schülzgen at CREOL, the College of Optics and Photonics at the University of Central Florida, and Jian Zhao at the Boston University Photonics Center has developed a new FOIS enabled by integrating image processing based on a deep convolutional neural network (DCNN) with a GALOF. Their DCNN-GALOF system represents a simple, robust, and low-cost configuration. This novel FOIS transmits almost artefact-free video-rate cell images at high imaging speeds (~20 Hz) utilizing broadband and incoherent light-emitting diode illumination. The high-quality imaging process is able to tolerate both strong mechanical bending and large temperature variations. The imaging depth can reach several millimeters from the fiber facet even without any distal-end optics, and its lensless imaging capability minimizes collateral penetration damage for living objects. In addition, the learning capability of this system can be transferred among different types of cells without any retraining process, which increases its potential as a highly functionalized imaging tool.

a) Schematic of the imaging process through the DCNN-GALOF system. b) Cell imaging results of different types of cells.

This work dramatically boosts the system performance of state-of-the-art FOISs and gets FOISs closer to the demanding requirements of real-world applications. Future FOISs based on the DCNN-GALOF combination should have the potential to probe biological objects in vivo. Such tools could assist with answering fundamental scientific questions as well as improving the accuracy of clinical practitioners' diagnoses.

Read the original research article in the peer-reviewed, open-access journal Advanced Photonics: J. Zhao et al., "Deep learning cell imaging through Anderson localizing optical fiber," Adv. Photon. 1(6) 066001 (2019). https://doi.org/10.1117/1.AP.1.6.066001