Tracking multiple particles in fluorescence time-lapse microscopy images via probabilistic data association.

The IEEE International Symposium on Biomedical Imaging (ISBI) is a scientific conference dedicated to mathematical, algorithmic, and computational aspects of biological and biomedical imaging, across all scales of observation. It fosters knowledge transfer among different imaging communities and contributes to an integrative approach to biomedical imaging. ISBI is a joint initiative from the IEEE Signal Processing Society (SPS) and the IEEE Engineering in Medicine and Biology Society (EMBS). The 2018 meeting will include tutorials, and a scientific program composed of plenary talks, invited special sessions, challenges, as well as oral and poster presentations of peer-reviewed papers. High-quality papers are requested containing original contributions to the topics of interest including image formation and reconstruction, computational and statistical image processing and analysis, dynamic imaging, visualization, image quality assessment, and physical, biological, and statistical modeling. Accepted 4-page regular papers will be published in the symposium proceedings published by IEEE and included in IEEE Xplore. To encourage attendance by a broader audience of imaging scientists and offer additional presentation opportunities, ISBI 2018 will continue to have a second track featuring posters selected from 1-page abstract submissions without subsequent archival publication.

Melanoma is the most serious form of skin cancer, with more than 123,000 new cases worldwide each year. Reliable automatic melanoma screening system will be a great help for clinicians to detect malignant skin lesions as soon as possible. To address this problem, a computer-assisted approach to detecting melanoma using convolutional neural networks will enable effective and faster treatment of the disease. Many attempts have been made to use convolutional neural networks to solve this problem, but so far the performance in this aspect is not good. In this project, Xception and VGG-16 models will be fine-tuned on the IEEE International Symposium on Biomedical Imaging (ISBI) Official Skin Data Set 2016 and combined into an integrated framework to predict whether skin disease images are benign or malignant. Our experimental results show that the ensemble model can achieve better classification results and the proposed method is competitive in this field.

Recently, the incidence of skin cancer has increased considerably and is seriously threatening human health. Automatic detection of this disease, where early detection is critical to human life, is quite challenging. Factors such as undesirable residues (hair, ruler markers), indistinct boundaries, variable contrast, shape differences, and color differences in the skin lesion images make automatic analysis quite difficult. To overcome these challenges, a highly effective segmentation method based on a fully convolutional network (FCN) is presented in this paper. The proposed improved FCN (iFCN) architecture is used for the segmentation of full-resolution skin lesion images without any pre- or post-processing. It is to support the residual structure of the FCN architecture with spatial information. This situation, which creates a more advanced residual system, enables more precise detection of details on the edges of the lesion, and an analysis independent of skin color can be performed. It offers two contributions: determining the center of the lesion and clarifying the edge details despite the undesirable effects. Two publicly available datasets, the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 Challenge and PH2 datasets, are used to evaluate the performance of the iFCN method. The mean Jaccard index is 78.34%, the mean Dice score is 88.64%, and the mean accuracy value is 95.30% for the proposed method for the ISBI 2017 test dataset. Furthermore, the mean Jaccard index is 87.1%, the mean Dice score is 93.02%, and the mean accuracy value is 96.92% for the proposed method for the PH2 test dataset.

Explicit and tractable characterizations of the dynamical behavior of virus particles are pivotal for a thorough understanding of the infection mechanisms of viruses. This thesis deals with the problem of extracting symbolic representations of the dynamical behavior of fluorescent particles from fluorescence microscopy image sequences. The focus is on the behavior of virus particles such as fusion with the cell membrane. A numerical representation is obtained by tracking the particles in the image sequences. We have investigated probabilistic tracking approaches, including approaches based on the Kalman filter as well as based on particle filters. For reasons of efficiency and robustness, we developed a tracking approach based on the probabilistic data association (PDA) algorithm in combination with an ellipsoidal sampling scheme that exploits effectively the image data via parametric appearance models. To track objects in close proximity, we compute the support that each image position provides to each tracked object relative to the support provided to the object's neighbors. After tracking, the problem of mapping the trajectory information computed by the tracking approaches to symbolic representations of the behavior arises. To compute symbolic representations of behaviors related to the fusion of single virus particles with the cell membrane based on their intensity over time, we developed a layered probabilistic approach based on stochastic hybrid systems as well as hidden Markov models (HMMs). We use a maxbelief strategy to efficiently combine both representations. The layered approach describes the intensity, intensity models, and behaviors of single virus particles. We introduce models for the evolution of the intensity and the behavior. To compute estimates for the intensity, intensity models, and behaviors we use a hybrid particle filter and the Viterbi algorithm. The developed approaches have been applied to synthetic images as well as to real microscopy image sequences displaying human immunodeficiency virus (HIV-1) particles. We have performed an extensive quantitative evaluation of the performance and a comparison with several existing approaches. It turned out that our approaches outperform previous ones, thus yielding more accurate and more reliable information about the behavior of virus particles. Moreover, we have successfully applied our tracking approaches to 3D image sequences displaying herpes simplex virus (HSV) replication compartments. We also applied the tracking approaches to image data displaying microtubule tips and analyzed their motion. In addition, our tracking approaches were successfully applied to the 2D and 3D image data of a Particle Tracking Challenge.

The range gate pull off (RGPO) and the velocity gate pull off (VGPO) are two kinds of common electronic countermeasure techniques used to defeat or degrade tracking radars. For countering the RGPO or VGPO, the extended Kalman filter (EKF) with a new modified probabilistic data association (PDA) is proposed in this paper. It takes full advantage of the fact that for the case of low measurement noise, the measurements for the RGPO/VGPO have virtually the same Doppler velocity/range as those of the true target. This method uses the difference between the Doppler velocity and tracking velocity of the Kalman filter to weight the probability of every measurement so that less weight is given to the false measurement. The simulations show that for the case of low measurement noise, the EKF method with the new modified PDA can counter the RGPO or VGPO, and works better than the EKF with the standard PDA.

Object-Oriented Environment for Assessing Tracking Algorithms

ADS-B and radar will coexist for a long time in the future. For the ADS-B and multi-radar asynchronous track fusion problem in the air traffic control system, an ADS-B and radar fusion architecture and an asynchronous multi-sensor track fusion algorithm based on augmented state interacting multiple model(IMM) filter with probability data association(PDA) are proposed in this paper. The fusion algorithm is developed by applying the standard IMM approach, the PDA technique, and asynchronous measurement updating to a state-augmented system for the target motion. The state vector is augmented to include the past states which correspond to those asynchronous measurements. A PDA filter for parallel sensor processing is developed for target tracking under clutter. Real data from the ADS-B equipped aircraft and radar are used to test the performance of the algorithm. The simulation result shows that the track accuracy can be improved by this algorithm and the performance is comparable with the distributed multi-rate track fusion algorithm.

Variable Structure Multiple Model (VSMM) estimation generalizes Multiple Model (MM) estimation by assuming that the set of models used for MM estimation is time varying. By using VSMM estimation, a large model set which may cover all possible target maneuvers can be used without significant increase of computational load, while maintaining a reasonable estimation accuracy. Various implementable VSMM algorithms, like Model Group Switching (MGS), Likely Model Set (LMS) and Minimal Sub-Model-Set Switching (MSMSS) using the Interacting Multiple Model (IMM) algorithm with a sub-model-set adaptation logic have appeared in the recent literature. However, the use of these algorithms for tracking maneuvering target in clutter has not been explored. In presence of clutter, one need to use data association technique to differentiate target originated measurement from clutter. The probabilistic data association (PDA) has been popularly adopted to many algorithms for tracking in clutter. In this paper, we integrate PDA technique with MSMSS and propose a VSIMM-PDA algorithm for maneuvering target tracking in clutter. A new grating technique to account for potential model errors is used. A numeric example via multiple Monte Carlo runs, which compares the performance of the new algorithm to a standard IMM-PDA in terms of Root Mean Squared error (RMS) and percentage of track loss, is presented.© (2003) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

A Kalman filtering (KF) approach to on-line musical beat tracking with probabilistic data association (PDA) is investigated in this work. We first formulate the beat tracking process as a linear dynamic system of beat progression, and then apply the Kalman filtering algorithm to the dynamic system in estimating the time-varying tempo and beat locations. Musical beat tracking using traditional Kalman filtering is however not reliable in the presence of tempo fluctuations and expressive timing deviations. To address this problem, we adopt data association techniques to assign probability masses to all possible beat interpretations, and then locate the true beat according to the weighting. Two methods are proposed. The first one (PDA-I) weighs the distance between the candidate observation and the predicted beat location while the second method (PDA-II) considers not only the distance but also the onset intensity in weight selection. Superior performance of the proposed beat tracking algorithm is demonstrated with simulation results on the Music Information Retrieval Evaluation Exchange (MIREX) 2006 beat tracking competition practice dataset and the Billboard Top-10 database.

Pedestrian tracking with a single motion model and a single cue cannot be robust against combination of changes of target motion and appearance, caused by either static or dynamic changes in surrounding environments. Different from previous work, this paper proposes to refer to both multiple motion models and cues to improve accuracy of single pedestrian tracking. By integrating the compensated motion model into model filtering of interacting multiple model particle filter (IMMPF) and updating mode probabilities using the state with the maximum color based likelihood weight, the interacting stage of IMMPF generates more accurate approximation of the mixed a priori probability distribution of the target state. Within the search window centering at the predicted state of the constant velocity (CV) model of IMMPF, feature matching of scale- and rotation-invariant feature descriptors helps locate the target. Experimental results show that the proposed scheme is robust against the change of target motion, occlusion, rotation, scaling, and illumination variations. The average RMSE and overlap ratio of the proposed scheme significantly outperforms color based IMMPF using compensated motion model and fast L1-tracker.

A cross-layer, near-optimal soft-decision equalization approach for frequency selective multiinput multioutput (MIMO) communication systems is proposed in this paper. With the help of iterative processing, two detection and estimation schemes based on second-order statistics are harmoniously put together to yield a two-part receiver structure: local multiuser detection (MUD) using soft-decision probabilistic data association (PDA) detection, and dynamic noise-interference tracking using Kalman filtering. The proposed Kalman-PDA approach performs local MUD within a subblock of the received data instead of over the whole data set, to reduce the computational load. At the same time, all the interference affecting the local subblock, including both multiple access and intersymbol interference, is properly modeled as the state vector of a linear system, and dynamically tracked by Kalman filtering. The performance of Kalman-PDA is further enhanced by applying a simple automatic repeat request (ARQ) protocol. The ARQ-aided MIMO detection algorithm can adjust to any preset retransmission rate to ensure a desired performance and data-rate trade-off.

Particle filters can provide better results than Kalman filter based algorithms in the problems where the nonlinear elements are dominant. In this study the problem of tracking an airborne platform using radar measurements, which has nonlinearities both in measurement and system models is considered. Different models are used for different target maneuvers; extended Kalman filter (EKF), interacting multiple model (IMM) structure and multiple model particle filter are compared on a sample scenario.

A single-sensor, single-target mixture reduction (MR) data association algorithm is extended for use in multisensor, multitarget tracking situations. MR is extended for tracking an arbitrary number of targets using an arbitrary number of sensors under the assumption that the sensor measurement errors are independent across sensors. Like the single-sensor, single-target MR algorithm, which gives better performance than the probabilistic data association (PDA) filter, the multisensor, multitarget MR extensions give similar improvements in performance compared to the joint PDA (JPDA) and multisensor JPDA (MSJPDA) algorithms. Further, in the formulations for the multisensor and multitarget MR algorithms, the equations for the calculation of the data association probabilities have been put in the same form as for the JPDA, thus allowing previously developed fast JPDA computational techniques to be applicable. N the problem of tracking targets in random clutter, the optimal Bayesian solution leads to Gaussian mixture distributions that consist of an exponentially increasing number of components.1 In practice, the number of components in each mixture is kept in check by approximating it with fewer components. The nearest neighbor (NN) approximation reduces each target's mixture to its largest component.13 The joint probabilistic data association (JPDA) approximation merges the components of each target's mixture into a single Gaussian component.1'4 However, when there are several significant, well-spaced components in the original mixture, important information may be lost by using the NN or JPDA methods. A more flexible approximation method for single-sensor, single-target tracking, known as mixture reduction (MR), has been proposed by Salmond.5 This MR algorithm preserves the mean and covariance of the original mixture of components, successively merging components until the number of components is reduced to some userspecified limit. In this paper, we first review Salmond's MR algorithm for single-sensor tracking of a single target in clutter. We then derive extensions to Salmond's MR algorithm for use in tracking multiple targets and when there are measurements available from multiple sensors. Just as the single-sensor, single-target MR algorithm gives better performance5 than the probabilistic data association (PDA) filter, the multisensor, multitarget MR extensions are shown to give similar improvements in performance as compared to the JPDA and multisensor JPDA (MSJPDA)6 algorithms. Extension of the MR algorithm for tracking of multiple targets is necessary for use in realistic tracking scenarios where there are usually many targets that need to be tracked. Moreover, many current tracking systems have been designed with multiple sensors, thus requiring the further extension to a multisensor algorithm. The paper is organized as follows. In Sec. II, the target dynamics and measurement equations are defined. We review the singlesensor, single-target MR algorithm5 in Sec. Ill, and we extend the algorithm to the multitarget and multisensor cases in Sec. IV and V, respectively. In Sec. VI, simulation results evaluating the performances of the MR extensions are presented. Finally, concluding remarks are given in Sec. VII.

A standard algorithm based on the Kalman Filter and used for tracking multiple targets in a noisy environment has been applied to analysing the motion of cells in video images. The method, known as Probabilistic Data Association, is computationally efficient, allowing simultaneous monitoring of many cells at video frame rates of 25 Hz. The present study uses the tracking procedure to investigate the motion of human sperm cells. Extensions to allow the tracking of many hundreds of cells at video rates using a massively data parallel computer are explained. The procedure is well suited for real time tracking of other visualised biological events. >

Accurate tracking of elite athletes for performance monitoring allows sports scientists to optimize training to gain a competitive edge. An important challenge in this application is that the maneuverability of the athletes is high and the traditional Kalman filter (KF) will not provide satisfactory tracking accuracy. Further, high update rates, of the order of tens of updates per second for each player, are often required and hence, the tracking algorithm considered should be computationally efficient. In this paper we propose a computationally efficient multiple model particle filter (MM-PF) algorithm for tracking maneuvering objects. It uses a Gaussian proposal density based on the unscented KF and a deterministic sampling technique and provides tracking accuracy similar to that of the augmented MM-PF, but with much lower computational cost. The performance of the proposed algorithm was verified using simulations and data collected in field trials. The trials were conducted with the Australian Institute of Sport using a localization system we have designed.