Intensity-Mosaic: automatic panorama mosaicking of disordered images with insufficient features.

Purpose: Handling low-quality and few-feature medical images is a challenging task in automatic panorama mosaicking. Current mosaicking methods for disordered input images are based on feature point matching, whereas in this case intensity-based registration achieves better performance than feature-point registration methods. We propose a mosaicking method that enables the use of mutual information (MI) registration for mosaicking randomly ordered input images with insufficient features. Approach: Dimensionality reduction is used to map disordered input images into a low dimensional space. Based on the low dimensional representation, the image global correspondence can be recognized efficiently. For adjacent image pairs, we optimize the MI metric for registration. The panorama is then created after image blending. We demonstrate our method on relatively lower-cost handheld devices that acquire images from the retina in vivo, kidney ex vivo, and bladder phantom, all of which contain sparse features. Results: Our method is compared with three baselines: AutoStitch, "dimension reduction + SIFT," and "MI-Only." Our method compared to the first two feature-point based methods exhibits 1.25 (ex vivo microscope dataset) to two times (in vivo retina dataset) rate of mosaic completion, and MI-Only has the lowest complete rate among three datasets. When comparing the subsequent complete mosaics, our target registration errors can be 2.2 and 3.8 times reduced when using the microscopy and bladder phantom datasets. Conclusions: Using dimensional reduction increases the success rate of detecting adjacent images, which makes MI-based registration feasible and narrows the search range of MI optimization. To the best of our knowledge, this is the first mosaicking method that allows automatic stitching of disordered images with intensity-based alignment, which provides more robust and accurate results when there are insufficient features for classic mosaicking methods.

RetinaMatch: Efficient Template Matching of Retina Images for Teleophthalmology.

Retinal template matching and registration is an important challenge in teleophthalmology with low-cost imaging devices. However, the images from such devices generally have a small field of view (FOV) and image quality degradations, making matching difficult. In this paper, we develop an efficient and accurate retinal matching technique that combines dimension reduction and mutual information (MI), called RetinaMatch. The dimension reduction initializes the MI optimization as a coarse localization process, which narrows the optimization domain and avoids local optima. The effectiveness of RetinaMatch is demonstrated on the open fundus image database STARE with simulated reduced FOV and anticipated degradations, and on retinal images acquired by adapter-based optics attached to a smartphone. RetinaMatch achieves a success rate over 94% on human retinal images with the matched target registration errors below 2 pixels on average, excluding the observer variability, outperforming standard template matching solutions. In the application of measuring vessel diameter repeatedly, single pixel errors are expected. In addition, our method can be used in the process of image mosaicking with area-based registration, providing a robust approach when feature-based methods fail. To the best of our knowledge, this is the first template matching algorithm for retina images with small template images from unconstrained retinal areas. In the context of the emerging mixed reality market, we envision automated retinal image matching and registration methods as transformative for advanced teleophthalmology and long-term retinal monitoring.

64.1: Display Technologies for Therapeutic Applications of Virtual Reality.

A paradigm shift in image source technology for VR helmets is needed. Using scanning fiber displays to replace LCD displays creates lightweight, safe, low cost, wide field of view, portable VR goggles ideal for reducing pain during severe burn wound care in hospitals and possibly in austere combat-transport environments.

True three-dimensional displays that allow viewers to dynamically shift accommodation, bringing objects displayed at different viewing distances into and out of focus.

Under natural viewing conditions, viewers do not just passively perceive. Instead, they dynamically scan the visual scene by shifting their eye fixation and focus between objects at different viewing distances. In doing so, the oculomotor processes of accommodation (eye focus) and vergence (angle between lines of sight of two eyes) must be shifted synchronously to place new objects in sharp focus in the center of each retina. Accordingly, nature has reflexively linked accommodation and vergence, such that a change in one process automatically drives a matching change in the other. Conventional stereoscopic displays force viewers to try to decouple these processes, because while they must dynamically vary vergence angle to view objects at different stereoscopic distances, they must keep accommodation at a fixed distance--or else the entire display will slip out of focus. This decoupling generates eye fatigue and compromises image quality when viewing such displays. In an effort to solve this accommodation/vergence mismatch problem, we have built various prototype displays that can vary the focus of objects at different distances in a displayed scene to match vergence and stereoscopic retinal disparity demands and better simulate natural viewing conditions. By adjusting the focus of individual objects in a scene to match their stereoscopic retinal disparity, the cues to ocular accommodation and vergence are brought into agreement. As in natural vision, the viewer brings different objects into focus by shifting accommodation. As the mismatch between accommodation and vergence is decreased, natural viewing conditions are better simulated and eye fatigue should decrease.