System Combines Glass-Air Optical Fiber Imaging and Deep Learning to Capture Accurate, Real-Time Views of Biological Objects

Technology #34029

Questions about this technology? Ask a Technology Manager

Download Printable PDF

Image Gallery
Figure 1. The graphic (a) schematically illustrates an experimental incoherent light-illuminated DCNN-GALOF imaging system without distal optics. The light source is a low-cost LED. To quantify the amount of fiber bending (b) the offset distance was measured as the distance from the end of the bent fiber to the position of the straight fiber (equal to the length of the dashed line).Figure 2. Experimental results of cell imaging at different temperatures.Figure 3. Experimental results of cell imaging under bending.
Categories
Researchers
Shuo Pang, Ph.D.
External Link (www.creol.ucf.edu)
Axel Schulzgen, Ph.D.
External Link (www.creol.ucf.edu)
Yangyang Sun
Jian Zhao, Ph.D.
External Link (www2.creol.ucf.edu)
Managed By
John Miner
Assistant Director 407.882.1136
Patent Protection

US Patent Pending
Publications
A path to high-quality imaging through disordered optical fibers: a review
Applied Optics, Volume 58, Issue 13, Page D50-D60, Published on April 9, 2019
Cell Imaging Using Glass-Air Disordered Optical Fiber and Deep Learning Algorithms
Imaging and Applied Optics 2019 (COSI, IS, MATH, pcAOP), OSA Technical Digest (Optical Society of America, 2019), paper CW1A.2.
Deep Learning Imaging through Fully-Flexible Glass-Air Disordered Fiber
ACS Photonics , 2018 5 (10), 3930-3935, DOI: 10.1021/acsphotonics.8b00832
Deep Learning Cell Imaging through Anderson Localizing Optical Fibre
arXiv.org, arXiv:1812.00982v2 [physics.optics]

New approach can transmit artifact-free images of cell structures in vivo despite temperature fluctuations and optical fiber bending.

Researchers at the University of Central Florida have developed a lensless fiber-optic imaging system that overcomes the expense and complications associated with existing multicore and multimode fiber-based imaging systems (MCFs, MMFs). More robust, compact and durable, the UCF technology can produce artifact-free images and reach an imaging depth of up to several millimeters without any distal optics. The new system also tolerates bending and temperature changes better than MCFs and MMFs.

Thus, the UCF system has the potential for many endoscopic applications such as in vivo imaging of cell structures in humans and animals. Its unprecedented flexibility may also enable researchers to observe and capture images of real-time neuron activity in free-behaving objects. The innovation could help to reduce the size of image-transmitting endoscopes down to the diameter of the fiber itself and minimize penetration damage without degrading image quality. As a result, the fiber could collect artifact-free images of organs without touching them directly; thus, enabling a minimally invasive, high-performance imaging system.

In comparison, MCF/MMF-based systems produce artificial image pixelation and require distal bulk optical elements to capture images of objects that are located away from the fiber facet. Consequently, the systems are rather large, complex and costly. With regard to temperature sensitivity and bending, even minor changes (a few degrees Celsius) or slight fiber movement (a few hundred micrometers) can induce mode coupling and scramble the pre-calibrated transmission matrix, requiring access to the distal end of the fiber for recalibration.

Technical Details

The UCF fiber optical imaging system comprises two main parts: a disordered glass-air Anderson localized optical fiber (GALOF) that provides low-loss image transmission and a trained deep convolutional neural network (DCNN) of algorithms that enable the accurate reconstruction of raw images. The unique DCNN-GALOF combination offers advantages in resolution, depth perception, and environmental stability over conventional fiber-optic imaging methods. It also allows for physical movement of the specialty fiber without interruption of the real-time imaging process. Experimental results indicate that image quality and system performance are unaffected by a bending angle of approximately 3 degrees or by heating of up to 50 degrees Celsius.

In one example application of the system, the imaging fiber is a meter-long GALOF made of air and silica glass (to create the random refractive index structure—though other oxide glass mixtures are usable). It uses no distal optics. The system employs incoherent light (a low-cost LED) to illuminate various structures of human red blood cells. Within the system, a DCNN model is tailored (trained) to reconstruct and classify images. Instead of relying on known models and priors, the DCNN undergoes a training process using a large dataset collected from samples of the cell structures. In this way, it directly learns the underlying physics of the imaging transmission system without any advanced knowledge. In effect, it optimizes the network and enables it to reconstruct and classify the input images even if a particular type of image is not in the training data set. The trained DCNN is a precise approximation of the mapping function between the measured imaging data and the input imaging data and therefore enables a prediction process that takes less than one second.

Partnering Opportunity

The research team is looking for partners to develop the technology further for commercialization.

Stage of Development

Demonstration system available.

Benefits

  • Low cost
  • Reconstructed images are of high quality and artifact-free
  • Works without distal optical elements
  • Tolerates bending and temperature variations far better than other technologies

Applications

  • Endoscopes for humans, engines, nuclear power plants
  • Remote image capture