Frame-rate spatial referencing based on invariant indexing and alignment with application to online retinal image registration

This paper describes an algorithm to continually and accurately estimate the absolute location of a diagnostic or surgical tool (such as a laser) pointed at the human retina, from a series of image frames. We treat the problem as a registration problem using diagnostic images to build a spatial map of the retina and then registering each online image against this map. Since the image location where the laser strikes the retina is easily found, this registration determines the position of the laser in the global coordinate system defined by the spatial map. For each online image, the algorithm computes similarity invariants, locally valid despite the curved nature of the retina, from constellations of vascular landmarks. These are detected using a high-speed algorithm that iteratively traces the blood vessel structure. Invariant indexing establishes initial correspondences between landmarks from the online image and landmarks stored in the spatial map. Robust alignment and verification steps extend the similarity transformation computed from these initial correspondences to a global, high-order transformation. In initial experimentation, the method has achieved 100 percent success on 1024 /spl times/ 1024 retina images. With a version of the tracing algorithm optimized for speed on 512 /spl times/ 512 images, the computation time is only 51 milliseconds per image on a 900MHz PentiumIII processor and a 97 percent success rate is achieved. The median registration error in either case is about 1 pixel.     

Automatic Summarization of Changes in Biological Image Sequences Using Algorithmic Information Theory

An algorithmic information-theoretic method is presented for object-level summarization of meaningful changes in image sequences. Object extraction and tracking data are represented as an attributed tracking graph (ATG). Time courses of object states are compared using an adaptive information distance measure, aided by a closed-form multidimensional quantization. The notion of meaningful summarization is captured by using the gap statistic to estimate the randomness deficiency from algorithmic statistics. The summary is the clustering result and feature subset that maximize the gap statistic. This approach was validated on four bioimaging applications: 1) It was applied to a synthetic data set containing two populations of cells differing in the rate of growth, for which it correctly identified the two populations and the single feature out of 23 that separated them; 2) it was applied to 59 movies of three types of neuroprosthetic devices being inserted in the brain tissue at three speeds each, for which it correctly identified insertion speed as the primary factor affecting tissue strain; 3) when applied to movies of cultured neural progenitor cells, it correctly distinguished neurons from progenitors without requiring the use of a fixative stain; and 4) when analyzing intracellular molecular transport in cultured neurons undergoing axon specification, it automatically confirmed the role of kinesins in axon specification.     

A feature-based technique for joint, linear estimation ofhigh-order image-to-mosaic transformations: mosaicing the curved humanretina

An algorithm for constructing image mosaics from multiple, uncalibrated, weak-perspective views of the human retina is presented and analyzed. It builds on an algorithm for registering pairs of retinal images using a noninvertible, 12-parameter, quadratic image transformation model and hierarchical, robust estimation. The major innovation presented is a linear, feature-based, noniterative method for jointly estimating consistent transformations of all images onto the mosaic "anchor image." Constraints for this estimation are derived from pairwise registration both directly with the anchor image and indirectly between pairs of nonanchor images. An incremental, graph-based technique constructs the set of registered image pairs used in the solution. The estimation technique allows images that do not overlap the anchor frame to be successfully mosaiced, a valuable capability for mosaicing images of the retinal periphery. Experimental analysis on data sets from 16 eyes shows the average overall median transformation error in final mosaic to be 0.76 pixels. The technique is simpler, more accurate, and offers broader coverage than previously published methods     

Representing and computing regular languages on massively parallelnetworks

A general method is proposed for incorporating rule-based constraints corresponding to regular languages into stochastic inference problems, thereby allowing for a unified representation of stochastic and syntactic pattern constraints. The authors' approach establishes the formal connection of rules to Chomsky grammars and generalizes the original work of Shannon on the encoding of rule-based channel sequences to Markov chains of maximum entropy. This maximum entropy probabilistic view leads to Gibbs representations with potentials which have their number of minima growing at precisely the exponential rate that the language of deterministically constrained sequences grow. These representations are coupled to stochastic diffusion algorithms, which sample the language-constrained sequences by visiting the energy minima according to the underlying Gibbs probability law. This coupling yields the result that fully parallel stochastic cellular automata can be derived to generate samples from the rule-based constraint sets. The production rules and neighborhood state structure of the language of sequences directly determine the necessary connection structures of the required parallel computing surface. Representations of this type have been mapped to the DAP-510 massively parallel processor consisting of 1024 mesh-connected bit-serial processing elements for performing automated segmentation of electron-micrograph images.     

A computational model for C. elegans locomotory behavior: application to multiworm tracking.

A computational approach is presented for modeling and quantifying the structure and dynamics of the nematode C. elegans observed by time-lapse microscopy. Worm shape and conformations are expressed in a decoupled manner. Complex worm movements are expressed in terms of three primitive patterns--peristaltic progression, deformation, and translation. The model has been incorporated into algorithms for segmentation and simultaneous tracking of multiple worms in a field, some of which may be interacting in complex ways. A recursive Bayesian filter is used for tracking. Unpredictable behaviors associated with interactions are resolved by multiple-hypothesis tracking. Our algorithm can track worms of diverse sizes and conformations (coiled/uncoiled) in the presence of imaging artifacts and clutter, even when worms are overlapping with others. A two-observer performance assessment was conducted over 16 image sequences representing wild-type and uncoordinated mutants as a function of worm size, conformation, presence of clutter, and worm entanglement. Overall detected tracking failures were 1.41%, undetected tracking failures were 0.41%, and segmentation errors were 1.11% of worm length. When worms overlap, our method reduced undetected failures from 12% to 1.75%, and segmentation error from 11% to 5%. Our method provides the basis for reliable morphometric and locomotory analysis of freely behaving worm populations.     

Automated image analysis technologies for biological 3D light microscopy

Techniques for three-dimensional (3D) light microscopy of a wide variety of biological specimens are rapidly maturing. The next advances are to improve image contrast, make image resolution as isotropic as possible, and perform quantitative analysis. This article discusses methods of automatic image analysis and blind deconvolution to compensate for the microscope's point-spread function (impulse response). Special emphasis is given to quantitative analysis based on adaptive segmentation, the results of which can be used to quantify and trace individual structures, and to montage high-resolution fields as well as the results of image analysis on these fields into a wide-area view with an associated computer database representation. We exploit the specific advantages accruing from the 3D nature of the data to achieve new capabilities not possible with 2D imaging. Fundamental and practical challenges in this area and our progress to date including automated segmentation, cell counting, neuron tracing, mosaic synthesis, “blind” deconvolution of large 3D images, and high-speed computation are presented. © 1997 John Wiley & Sons, Inc. Int J Imaging Syst Technol, 8, 240–254, 1997     

On Providing Support for Protocol Adaptation in Mobile Wireless Networks

The availability of variety of communication devices offers a choice among networks with vastly different characteristics. No single protocol or application can be expected to perform well over all these networks. A mobile host is likely to encounter these different networks and needs to adapt accordingly. The problem of adapting to a changing network environment is further complicated, because changes in network conditions are usually transparent to higher layers of the protocol stack. In order to allow automatic adaptation of applications and protocols, awareness of link conditions and network environment is necessary. In this paper, we present a uniform mechanism based on ICMP messages for providing information about the environment to the protocol stack. We also show how protocols can adapt to changes in the environment, and in particular, demonstrate dynamic fine tuning of some of the well known protocols such as UDP and TCP. Performance measurements demonstrate that our framework imposes little overheads and improves protocol performance under changing network conditions.     

Integrated services packet networks with mobile hosts: Architecture and performance

This paper considers the support of real-time services to mobile users in an Integrated Services Packet Network. In the currently existing architectures, the service guarantees provided to the mobile hosts are mobility dependent, i.e., mobile hosts experience wide variation in the quality of service and often service disruption when hosts move from one location to another. The network performance degrades significantly when mobile hosts are provided with mobility independent service guarantees. In this paper we have proposed a service model for mobile hosts that can support adaptive applications which can withstand service degradation and disruption, as well as applications which require mobility independent service guarantees. We describe an admission control scheme for implementing this service model and evaluate its performance by simulation experiments. Simulation results show that, if sufficient degree of multiplexing of the mobility dependent and independent services are allowed, the network does not suffer any significant performance degradation and in particular our admission control scheme achieves high utilization of network resources.     

Median-based robust algorithms for tracing neurons from noisy confocal microscope images

This paper presents a method to exploit rank statistics to improve fully automatic tracing of neurons from noisy digital confocal microscope images. Previously proposed exploratory tracing (vectorization) algorithms work by recursively following the neuronal topology, guided by responses of multiple directional correlation kernels. These algorithms were found to fail when the data was of lower quality (noisier, less contrast, weak signal, or more discontinuous structures). This type of data is commonly encountered in the study of neuronal growth on microfabricated surfaces. We show that by partitioning the correlation kernels in the tracing algorithm into multiple subkernels, and using the median of their responses as the guiding criterion improves the tracing precision from 41% to 89% for low-quality data, with a 5% improvement in recall. Improved handling was observed for artifacts such as discontinuities and/or hollowness of structures. The new algorithms require slightly higher amounts of computation, but are still acceptably fast, typically consuming less than 2 seconds on a personal computer (Pentium III, 500 MHz, 128 MB). They produce labeling for all somas present in the field, and a graph-theoretic representation of all dendritic/axonal structures that can be edited. Topological and size measurements such as area, length, and tortuosity are derived readily. The efficiency, accuracy, and fully-automated nature of the proposed method makes it attractive for large-scale applications such as high-throughput assays in the pharmaceutical industry, and study of neuron growth on nano/micro-fabricated structures. A careful quantitative validation of the proposed algorithms is provided against manually derived tracing, using a performance measure that combines the precision and recall metrics.