This paper presents a generative statistical model for analyzing time series of planar shapes. Using elastic shape analysis, we separate object kinematics (rigid motions and speed variability) from morphological evolution, representing the latter through transported velocity fields (TVFs). A principal component analysis (PCA) based dimensionality reduction of the TVF representation provides a finite-dimensional Euclidean framework, enabling traditional time-series analysis. We then fit a vector auto-regressive (VAR) model to the TVF-PCA time series, capturing the statistical dynamics of shape evolution. To characterize morphological changes, we use VAR model parameters for model comparison, synthesis, and sequence classification. Leveraging these parameters, along with machine learning classifiers, we achieve high classification accuracy. Extensive experiments on cell motility data validate our approach, demonstrating its effectiveness in modeling and classifying migrating cells based on morphological evolution—marking a novel contribution to the field. • A novel method for statistical modeling and analysis of temporally-evolving shapes. • Elastic shape analysis represents a shape sequence by Euclidean time series. • Dynamic shape evolution is crucial aspect of cell migration in biology. • A detailed approach for modeling and classifying shape dynamics during cell motility.

The stiffness of cells and of their nuclei is a biomarker of several pathological conditions. Current measurement methods rely on invasive physical probes that yield one or two stiffness values for the whole cell. However, the internal distribution of cells is heterogeneous. We propose a framework to estimate maps of intracellular and intranuclear stiffness inside deforming cells from fluorescent image sequences. Our scheme requires the resolution of two inverse problems. First, we use a novel optical-flow method that penalizes the nuclear norm of the Hessian to favor deformations that are continuous and piecewise linear, which we show to be compatible with elastic models. We then invert these deformations for the relative intracellular stiffness using a novel system of elliptic PDEs. Our method operates in quasi-static conditions and can still provide relative maps even in the absence of knowledge about the boundary conditions. We compare the accuracy of both methods to the state of the art on simulated data. The application of our method to real data of different cell strains allows us to distinguish different regions inside their nuclei.

From meteorology to medical imaging and cell mechanics, many scientific domains use inverse problems (IPs) to extract physical measurements from image movement. To this end, motion estimation methods such as optical flow (OF) pre-process images into motion data to feed the IP, which then inverts for the measurements through a physical model. However, this combined OFIP pipeline exacerbates the ill-posedness inherent to each technique, propagating errors and preventing uncertainty quantification. We introduce a Bayesian PDE-constrained framework that transforms visual information directly into physical measurements in the context of probability distributions. The posterior mean is a constrained IP that tracks brightness while satisfying the physical model, thereby translating the aperture problem from the motion to the underlying physics; whereas the posterior covariance derives measurement error out of image noise. As we illustrate with traction force microscopy, our approach offers several advantages: more accurate reconstructions; unprecedented flexibility in experiment design (e.g., arbitrary boundary conditions); and the exclusivity of measurement error, central to empirical science, yet still unavailable under the OFIP strategy.

The method proposed in this paper is a robust combination of multi-task learning and unsupervised domain adaptation for segmenting amoeboid cells in microscopy. A highlight of this work is the manner in which the model's hyperparameters are estimated. The detriments of ad-hoc parameter estimation are well known, but this issue remains largely unaddressed in the context of CNN-based segmentation. Using a novel min-max formulation of the segmentation cost function our proposed method analytically estimates the model's hyperparameters, while simultaneously learning the CNN weights during training. This end-to-end framework provides a consolidated mechanism to harness the potential of multi-task learning to isolate and segment clustered cells from low contrast brightfield images, and it simultaneously leverages deep domain adaptation to segment fluorescent cells without explicit pixel-level re- annotation of the data. Experimental validations on multi-cellular images strongly suggest the effectiveness of the proposed technique, and our quantitative results show at least 15% and 10% improvement in cell segmentation on brightfield and fluorescence images respectively compared to contemporary supervised segmentation methods.

Deep learning has proven to be a very efficient tool to help pathologists analyze Whole Slide Images (WSI) toward automated classification or segmentation of detailed structures such as nuclei, glands or glomeruli. These objects are particularly relevant for disease diagnosis and staging. Many deep learning methods have shown impressive performance but are still imperfect, while manual segmentation has poor inter-rater agreement. In this paper, we propose a patch-level automated correction of a given baseline initial segmentation, based on deep-learning of segmentation errors and downstream local refinements. Results on the MoNuSeg and PanNuke test datasets show significant improvement of nuclei segmentation quality.

We propose an image based PDE-constrained optimisation framework to compute the dynamical quantities of a cell nucleus undergoing deformation. It allows retrieving the displacement, strain and stress at each pixel of the nuclear domain, as well as the traction force on the boundary. It is based on a mechanical model of the nuclear components and a pair of images documenting the deformation of the cell nucleus. To test our approach, we provide a warping method that produces a second image from an initial one along with the expected mechanical quantities. Both quantitative and qualitative analysis conclude for a significant and consistent improvement of our method over optical flow techniques.

In the context of tissue examination for breast cancer assessment, we propose a label-free imaging based on Optical Coherence Tomography (OCT) signal combined with a multiple instance learning (MIL) model to respond to a critical need for fast at point-of-care diagnosis: biopsy or surgery time. This new imaging, Dynamic Cell Imaging (DCI), is the time-resolved variant of Full-Field OCT (FFOCT) and offers an intra-cellular resolution of about 1 micron, together with optical sectioning and an improved cell contrast. In order to tackle the challenges of limited data and annotations, while remaining in the scope of interpretability, we design an instance-level MIL model with a focus on adapted data sampling. The interest of this method is that it incorporates task-specific feature learning and also produces instance predictions. For a dataset of 150 core-needle biopsies, we achieve a considerable improvement of more than 20 percentage points in specificity and about 10 in accuracy by leveraging intra-domain (as compared to extra-domain) pre-training.

This paper addresses the problem of characterizing statistical distributions of cellular shape populations using shape samples from microscopy image data. This problem is challenging because of the nonlinearity and high-dimensionality of shape manifolds. The paper develops an efficient, nonparametric approach using ideas from k-modal mixtures and kernel estimators. It uses elastic shape analysis of cell boundaries to estimate statistical modes and clusters given shapes around those modes. (Notably, it uses a combination of modal distributions and ANOVA to determine k automatically.) A population is then characterized as k-modal mixture relative to this estimated clustering and a chosen kernel (e.g., a Gaussian or a flat kernel). One can compare and analyze populations using the Fisher-Rao metric between their estimated distributions. We demonstrate this approach for classifying shapes associated with migrations of entamoeba histolytica under different experimental conditions. This framework remarkably captures salient shape patterns and separates shape data for different experimental settings, even when it is difficult to discern class differences visually.

Detection and analysis of informative keypoints is a fundamental problem in image analysis and computer vision. Keypoint detectors are omnipresent in visual automation tasks, and recent years have witnessed a significant surge in the number of such techniques. Evaluating the quality of keypoint detectors remains a challenging task owing to the inherent ambiguity over what constitutes a good keypoint. In this context, we introduce a reference based keypoint quality index which is based on the theory of spatial pattern analysis. Unlike traditional correspondence-based quality evaluation which counts the number of feature matches within a specified neighborhood, we present a rigorous mathematical framework to compute the statistical correspondence of the detections inside a set of salient zones (cluster cores) defined by the spatial distribution of a reference set of keypoints. We leverage the versatility of the level sets to handle hypersurfaces of arbitrary geometry, and develop a mathematical framework to estimate the model parameters analytically to reflect the robustness of a feature detection algorithm. Extensive experimental studies involving several keypoint detectors tested under different imaging scenarios demonstrate efficacy of our method to evaluate keypoint quality for generic applications in computer vision and image analysis.

Statistical analysis of shape evolution during cell migration is important for gaining insights into biological processes. This paper develops a time-series model for temporal evolution of cellular shapes during cell motility. It uses elastic shape analysis to represent and analyze shapes of cell boundaries (as planar closed curves), thus separating cell shape changes from cell kinematics. Specifically, it utilizes Transported Square-Root Velocity Field (TSRVF), to map non-Euclidean shape sequences into a Euclidean time series. It then uses PCA to reduce Euclidean dimensions and imposes a Vector Auto-Regression (VAR) model on the resulting low-dimensional time series. Finally, it presents some results from VAR-based statistical analysis: estimation of model parameters and diagnostics, synthesis of new shape sequences, and predictions of future shapes given past shapes.

This paper presents a multi-channel Extended Depth of Field (EDF) method for digital cytology based on the stationary wavelet transform. With a coefficient selection rule adapted to a precise color recovery, a sharp image can be reconstructed even on images with transparent overlapping cells. The precision and the color fidelity of the proposed method is analyzed. Moreover, an experiment demonstrating the necessity of volume analysis in cytology to achieve precise segmentation on cell clumps is conducted, and the importance of color fidelity in this context is asserted. The proposed method was tested on pap-stained urothelial cells and gray-scale cervical cells with important overlapping.

Detecting and segmenting individual cells from microscopy images is critical to various life science applications. Traditional cell segmentation tools are often ill-suited for applications in brightfield microscopy due to poor contrast and intensity heterogeneity, and only a small subset are applicable to segment cells in a cluster. In this regard, we introduce a novel supervised technique for cell segmentation in a multitask learning paradigm. A combination of a multi-task loss, based on the region and cell boundary detection, is employed for an improved prediction efficiency of the network. The learning problem is posed in a novel min-max framework which enables adaptive estimation of the hyper-parameters in an automatic fashion. The region and cell boundary predictions are combined via morphological operations and active contour model to segment individual cells. The proposed methodology is particularly suited to segment touching cells from brightfield microscopy images without manual interventions. Quantitatively, we observe an overall Dice score of 0.93 on the validation set, which is an improvement of over 15.9% on a recent unsupervised method, and outperforms the popular supervised U-net algorithm by at least 5.8% on average.

We introduce a novel paradigm for statistical analysis of spatial signals, applied to colocalization studies in bioimaging. Quantitative assessment of the spatial colocalization of different molecules in microscopy provides important functional information on cellular processes. By reducing objects (molecules or cluster of molecules) to their position (points), existing methods are predominantly restricted to point-based analyses, and scale poorly to applications involving large, asymmetric and complex-in-shape objects. We address this issue, and propose a statistical model for shape-based colocalization analysis. Our solution is a generalization of the Ripley's K-function for arbitrary shapes, and provides a method to statistically interpret the coupling of molecules to biological objects which are implicitly represented via level set embedding. Compared to the state-of-the-art, our solution is efficient and generic, and establishes the theoretical basis for an one-fits-all approach to tackle the heterogeneous challenges in robust interpretation of molecular association in biology. The efficacy of our method is established via synthetic simulations, and a practical application is also described to measure the statistical accumulation of synaptic molecules' spots near the cell's boundary of cultured neurons.

This paper reviews the state-of-the-art in denoising methods for biological microscopy images and introduces a new and original sparsity-based algorithm. The proposed method combines total variation (TV) spatial regularization, enhancement of low-frequency information, and aggregation of sparse estimators and is able to handle simple and complex types of noise (Gaussian, Poisson, and mixed), without any a priori model and with a single set of parameter values. An extended comparison is also presented, that evaluates the denoising performance of the thirteen (including ours) state-of-the-art denoising methods specifically designed to handle the different types of noises found in bioimaging. Quantitative and qualitative results on synthetic and real images show that the proposed method outperforms the other ones on the majority of the tested scenarios.

The accurate detection of filamentous structures in fluorescence microscopy, such as stained cytoskeleton and cilia, is an important technical issue in bioimage analysis. We propose here a two-steps approach that combines image thresholding in steerable wavelets domain and minimal path reconstruction to robustly detect and quantify filaments in their entire length. Indeed, the first steerable transformation enhances bright and anisotropic structures such as stained filaments, but local variations of fluorescence intensity often leads to line breaks in segmented filaments. We thus used a minimal path algorithm in a second step to close these gaps and reconstruct the whole filaments. Thereafter, we used our two-steps approach to detect and quantify the flagellum of the parasite Typanosoma brucei at a population level.

The behavior and performance of denoising algorithms are governed by one or several parameters, whose optimal settings depend on the content of the processed image and the characteristics of the noise, and are generally designed to minimize the mean squared error (MSE) between the denoised image returned by the algorithm and a virtual ground truth. In this paper, we introduce a new Poisson-Gaussian unbiased risk estimator (PG-URE) of the MSE applicable to a mixed Poisson-Gaussian noise model that unifies the widely used Gaussian and Poisson noise models in fluorescence bioimaging applications. We propose a stochastic methodology to evaluate this estimator in the case when little is known about the internal machinery of the considered denoising algorithm, and we analyze both theoretically and empirically the characteristics of the PG-URE estimator. Finally, we evaluate the PG-URE-driven parametrization for three standard denoising algorithms, with and without variance stabilizing transforms, and different characteristics of the Poisson-Gaussian noise mixture.

The deformation process orchestrated by the cell machinery is particularly complex and characterized by shape changes at multiple geometrical scales to drive cell deformation and movement. Precise cell shape description tools have become necessary to detect shape changes in a robust manner to allow subsequent morpho-dynamic profiling. Here we investigate the use of spherical wavelets to perform a multi-scale analysis of the cell shape, in order to automatically detect and track protrusions at the cell surface. Examples on real biological data highlight encouraging results and open the way to a powerful description of the cell deformation process.

Abstract Motivation: In developmental biology, quantitative tools to extract features from fluorescence microscopy images are becoming essential to characterize organ morphogenesis at the cellular level. However, automated image analysis in this context is a challenging task, owing to perturbations induced by the acquisition process, especially in organisms where the tissue is dense and opaque. Results: We propose an automated framework for the segmentation of 3D microscopy images of highly cluttered environments such as developing tissues. The approach is based on a partial differential equation framework that jointly takes advantage of the nuclear and cellular membrane information to enable accurate extraction of nuclei and cells in dense tissues. This framework has been used to study the developing mouse heart, allowing the extraction of quantitative information such as the cell cycle duration; the method also provides qualitative information on cell division and cell polarity through the creation of 3D orientation maps that provide novel insight into tissue organization during organogenesis. Availability: The proposed framework is free, open-source and available on the Icy platform (http://www.icy.bioimageanalysis.org/). Contact: [email protected] or [email protected] Supplementary information: Supplementary data are available at Bioinformatics online.

In this paper, we present a method for simultaneously tracking thousands of targets in biological image sequences, which is of major importance in modern biology. The complexity and inherent randomness of the problem lead us to propose a unified probabilistic framework for tracking biological particles in microscope images. The framework includes realistic models of particle motion and existence and of fluorescence image features. For the track extraction process per se, the very cluttered conditions motivate the adoption of a multiframe approach that enforces tracking decision robustness to poor imaging conditions and to random target movements. We tackle the large-scale nature of the problem by adapting the multiple hypothesis tracking algorithm to the proposed framework, resulting in a method with a favorable tradeoff between the model complexity and the computational cost of the tracking procedure. When compared to the state-of-the-art tracking techniques for bioimaging, the proposed algorithm is shown to be the only method providing high-quality results despite the critically poor imaging conditions and the dense target presence. We thus demonstrate the benefits of advanced Bayesian tracking techniques for the accurate computational modeling of dynamical biological processes, which is promising for further developments in this domain.

We aim at analysing fluorescence microscopy sequences of moving cells, so as to estimate the velocities that define the movement, the forces that drive this movement, and the pressure that characterises the material state. We use an optical flow method constrained by Stokes flow mechanics equations that define the dynamics of a fluid that is incompressible, homogeneous and viscous. We present a finite element formulation that leads to a quadratic programming problem. We apply the method to real biological data of amoebas observed by fluorescence microscopy.

The theory of compressed sensing (CS) predicts that random (or pseudo-random) linear measurements together with non-linear reconstruction can be used to sample and recover structured signals in a compressive manner. Lots of previous results demonstrated the efficiency of CS in recovering 2D images acquired using dedicated CS devices (single-pixel camera, accelerated MRI, etc…). In this paper, we investigate how this framework can be extended to perform an efficient joint reconstruction of a sequence of time-correlated 2D images, using 3D total variation regularization. We also evaluate the performances of this framework on test sequences issued from the bio-imaging field.

Structured illumination microscopy is a recent imaging technique that aims at going beyond the classical optical resolution by reconstructing high-resolution (HR) images from low-resolution (LR) images acquired through modulation of the transfer function of the microscope. The classical implementation has a number of drawbacks, such as requiring a large number of images to be acquired and parameters to be manually set in an ad-hoc manner that have, until now, hampered its wide dissemination. Here, we present a new framework based on a Bayesian inverse problem formulation approach that enables the computation of one HR image from a reduced number of LR images and has no specific constraints on the modulation. Moreover, it permits to automatically estimate the optimal reconstruction hyperparameters and to compute an uncertainty bound on the estimated values. We demonstrate through numerical evaluations on simulated data and examples on real microscopy data that our approach represents a decisive advance for a wider use of HR microscopy through structured illumination.

In this paper, we propose an empirical review of the conditions under which the compressed sensing framework allows to achieve exact image reconstruction. After a short presentation of the theoretical results related to this subject, we investigate the relevance and the limits of these theoretical results through several numerical reconstructions of some benchmark images. In particular, we discuss quantitative and qualitative artifacts that affect the reconstructed image when reducing the number of measurements in the Fourier domain. Finally, we conclude our study by extending our results to some real microscopic images.

Image filtering methods are crucial in a large number of applications where the relevant information is either noisy or partially missing. More particularly in 3D microscopy, cell membranes appear as structures of co-dimension 2, and suffer from discontinuities in intensity and orientation. Anisotropic PDE-based approaches offer an elegant solution to these problems, by integrating spatial and orientation information in a flexible and robust manner. In this work we propose a new tensor-based anisotropic model specifically adapted to 2D planar structures able to perform noise reduction and contrast enhancement simultaneously. Evaluation on synthetic and real data as well as comparison with previous works show that the model is well adapted for cell membrane structures.

Variational deformable models have proven over the past decades a high efficiency for segmentation and tracking in 2-D sequences. Yet, their application to 3-D time-lapse images has been hampered by discretization issues, heavy computational loads and lack of proper user visualization and interaction, limiting their use for routine analysis of large data-sets. We propose here to address these limitations by reformulating the problem entirely in the discrete domain using 3-D active meshes, which express a surface as a discrete triangular mesh, and minimize the energy functional accordingly. By performing computations in the discrete domain, computational costs are drastically reduced, whilst the mesh formalism allows to benefit from real-time 3-D rendering and other GPU-based optimizations. Performance evaluations on both simulated and real biological data sets show that this novel framework outperforms current state-of-the-art methods, constituting a light and fast alternative to traditional variational models for segmentation and tracking applications.

This paper presents a new method to accelerate the automatic tracking of multiple articulated objects in video sequences. The tracking method exploits the physics modeling of the articulated objects. The physics approach has numerous advantages such as the capability to let multiple models interact when tracking simultaneously multiple objects. Solving the tracking problem is generally done with an iterative scheme involving the computation of numerous forces, which usually turns out to be time consuming. This paper tackles the computational cost bottleneck by introducing a multi scale decomposition of the force maps. At each step of the tracking optimization scheme the multiple force maps are efficiently combined using a quadtree structure to recover the resulting forces. We demonstrate through multiple experiments that our results are both exact and drastically faster than the standard computation scheme.

In this paper we present a new procedure for tracking bi-directional objects in kymographs. The proposed technique is based on a novel adaptive and directional band-pass filtering method which allows us to separate particles which move in opposite directions. The filtering method exploits the curvelet analysis of the kymograph image to automatically adapt to the objects trails characteristics and select oriented features. The separation of bi-directional objects in separated images allows us to reliably detect and track fluorescent particles in fluorescence image sequences, despite numerous crossroad points in the kymograph space. The new abilities provided by the proposed technique are highlighted by the analysis of biological images which were previously impossible to analyze reliably.

We introduce two approaches to improve an existing color segmentation technique based on a Split and Merge quantization process for the study of stained histological images. We propose to modify the merge criterion : first, we include a spatial constraints heuristic; then we suggest the use of supervision and a more elaborated visual features representation. We tested these approaches on a renal biopsies dataset to automatically quantify interstitial fibrosis and show that supervision brings very significant improvements.

This paper presents a general method for detecting curvilinear structures, like filaments or edges, in noisy images. This method relies on a novel technique, the feature-adapted beamlet transform (FABT) which is the main contribution of this paper. It combines the well-known Beamlet transform (BT), introduced by Donoho , with local filtering techniques in order to improve both detection performance and accuracy of the BT. Moreover, as the desired feature detector is chosen to belong to the class of steerable filters, our transform requires only O(Nlog(N)) operations, where N = n(2) is the number of pixels. Besides providing a fast implementation of the FABT on discrete grids, we present a statistically controlled method for curvilinear objects detection. To extract significant objects, we propose an algorithm in four steps: 1) compute the FABT, 2) normalize beamlet coefficients, 3) select meaningful beamlets thanks to a fast energy-based minimization, and 4) link beamlets together in order to get a list of objects. We present an evaluation on both synthetic and real data, and demonstrate substantial improvements of our method over classical feature detectors.

This paper presents a novel approach to track multiple articulated objects in a video sequence. The key idea is to define a model of the object using a set of geometrical primitives linked by physical constraints, and exploit physics engines to solve these constraints while the model adapts to the object under the influence of local mean-shift processes. This novel approach to object tracking has numerous advantages: the model provides rich geometric information about the object at the articulation level; multiple touching objects are implicitly distinguished using collision detection strategies; physics engines are able to efficicently manage both image-based and model-based constraints simultaneously for a neglectable computational cost, suggesting their potential interest for many more image processing applications.

Particle detection and tracking methods generally assume a simplistic image model that is rarely valid when imaging biological processes in fluorescence microscopy. The tracking task may become nearly impossible when complex biological structures are visible and interfere with the signal of interest. To address this limitation we have adapted a source separation technique based on sparsity principles to the characteristics of fluorescent biological images. Since it allows the discrimination of objects with different morphologies, we present an approach to detect and track particles that exploits its results. The tracking algorithm resolves particles that temporarily aggregate by exploiting the proposed model of image. We prove in a real case the ability of the method to track numerous particles in a complex and dynamic background, something which was not feasible until now, hence offering new tools to document interactions between cellular compartments.

Multiple hypothesis tracking (MHT) is a preferred technique for solving the data association problem in modern multiple targets tracking systems. However its computational cost is generally considered prohibitive for tracking numerous objects in cluttered environments due to numerous targets and spurious measurements. We present in this paper a new MHT formulation in which target perceivability is modeled whereby automatic early track termination and false measurements exclusion reduce the problem complexity and improve the method robustness to clutter. Moreover we propose a MHT implementation exploiting the tree structure of the potential tracks to take full advantages of parallel computing technologies. We provide experimental results showing that both the track model and algorithmic design make the algorithm fast and robust even in highly complex situations such as tracking numerous particles in fluorescent microscopy images.

In this paper we propose a Compressed Sensing-based image acquisition and recovery method that combines Fourier magnitude measurements and Fourier phase estimation for sequential microscopy image acquisition. The main idea is to combine sequential Optical Fourier Transform (OTF) magnitude measurements with Fourier phase estimation from complete keyframes acquisition. For images with homogeneous objects and background, Compressed Sensing (CS) provides indeed an optimal reconstruction framework from a set of random projections in Fourier domain, while constraining bounded variations in the spatial domain. As in many others optical systems, in microscopy we can observe the magnitude of the Fourier coefficients. However, getting the phase of these coefficients can be an very expensive task. Initial experiments simulating the proposed microscopy image acquisition protocol confirm the feasibility of the CS computational framework to recover image sequences in microscopy with a very high frame rate while preserving high SNR levels.

We present a new feature-aided tracking algorithm dedicated to the task of tracking multiple and closely-spaced biological particles. We propose a new function to score associations, based on kinetic models, and enriched with an additional feature. This feature is based on adaptive profiles and the physical properties of the acquisition system. A key property is that this feature definition allows to resolve the challenging task of tracking particles that appear fused. Results on simulations show improved performances over existing methods both on tracking and on the resolution of fused particles.

Tracking nano-metric particles in a biological environment is a very difficult task because of the low signal intensity and the high mobility of these small objects. The task becomes nearly impossible for classical tracking procedures when the targets are labeled with a marker that is not strictly specific, because in this case dynamic structures in the cell are also visible. To address this limitation, we propose to use a source separation technique based on sparsity principles which allows the discrimination of objects with different morphologies. We prove in a real case that tracking in the source separated images allows to track particles that interact with other sources, something which was not feasible until now. This capability opens up new perspectives for the analysis documenting intricate interactions between cellular compartments.

Cellular endocytosis is a mechanism of great interest in biology, for it regulates the communication between the cell and the external medium. With recent advances in fluorescence microscopy, endocytosis has become a popular candidate for image-based high content screening campains. In this context, we have developed an automated framework comprising robust cell segmentation using coupled shape-constrained active contours and efficient endosome extraction using an isotropic undecimated wavelet transform. The resulting method has few parameters and is able to analyze tens of cells per image in the order of seconds. Validation is performed by experimentally confirming previously published results obtained through manual analysis.

In this paper, we propose a new method to reconstruct high resolution images from structured illumination microscopy. It consists of estimating the illumination pattern parameters with a multiscale analysis in the Fourier domain and filtering the significative features with a statistical test. Our method is fast and automatic, aiming at being computationally effective for in vivo biomedical applications.

This paper addresses the problem of detecting features running along lines or piecewise constant curves. Our method is adapted either for common image features like edges or ridges as well as any kind of features that can be designed by a priori knowledge. The main contribution of this paper is to unify the well-known Beamlet transform, introduced by Donoho et al, with linear filtering technique in order to define what we call the feature-adapted Beamlet transform. If the desired feature is chosen to belong to the class of steerable filters, our method can be achieved in linear time and can be easily implemented on a parallel machine. We present some experimental results both on edge- and ridge-like features that demonstrate the substantial improvement over classical feature detectors.

This paper presents a new method for computing the feature-adapted Radon and beamlet transforms in a fast and accurate way. These two transforms can be used for detecting features running along lines or piecewise constant curves. The main contribution of this paper is to unify the fast slant stack method, introduced in [2], with linear filtering technique in order to define what we call the feature-adapted fast slant stack. If the desired feature is chosen to belong to the class of steerable filters, our method can be achieved in 0(N log(iV)), where N = n2is the number of pixels. This new method leads to an efficient implementation of both feature-adapted radon and beamlet transforms, that outperforms our previous works. Our method has been developed in the context of biological imaging to detect image features lying along curves like edges or ridges as well as any kind of features that can be designed by a priori knowledge.

Fluorescence microscopy images are contaminated by photon and readout noises, and hence can be described by mixed-Poisson-Gaussian (MPG) processes. In this paper, a new variance stabilizing transform (VST) is designed to convert a filtered MPG process into a near Gaussian process with a constant variance. This VST is then combined with the isotropic undecimated wavelet transform leading to a multiscale VST (MS-VST). We demonstrate the usefulness of MS-VST for image denoising and spot detection in fluorescence microscopy. In the first case, we detect significant Gaussianized wavelet coefficients under the control of a false discovery rate. A sparsity-driven iterative scheme is proposed to properly reconstruct the final estimate. In the second case, we show that the MS-VST can also lead to a fluorescent-spot detector, where the false positive rate of the detection in pure noise can be controlled. Experiments show that the MS-VST approach outperforms the generalized Anscombe transform in denoising, and that the detection scheme allows efficient spot extraction from complex background.

Following an overview of image analysis applications in 2D and 3D dynamic biological microscopy, we present work developed in our laboratory dedicated to two central aspects of cell biology of infection, cell shape and motility analysis and particle tracking. We describe a fully automatic segmentation and tracking method designed to enable quantitative analyses of cellular shape and motion from 4D (3D+t) microscopy data. To get at a better understanding of pathogens/host cell interactions and to document infectious disease processes in living systems, it is necessary to characterise the dynamic properties of pathogens. We describe a method to detect and track multiple moving biological spot-like particles showing different kind of dynamics in image sequences acquired through multidimensional fluorescence microscopy

Automatic segmentation and tracking of biological objects from dynamic microscopy data is of great interest for quantitative biology. A successful framework for this task are active contours, curves that iteratively minimize a cost function, which contains both data-attachment terms and regularization constraints reflecting prior knowledge on the contour geometry. However the choice of these latter terms and of their weights is largely arbitrary, thus requiring time-consuming empirical parameter tuning and leading to sub-optimal results. Here, we report on a first attempt to use regularization terms based on known biophysical properties of cellular membranes. The present study is restricted to 2D images and cells with a simple to skeletal cortex underlying the membrane. We describe our new active contour model and its implementation, and show a first application to real biological images. The obtained segmentation is slightly better than standard active contours, however the main advantage lies in the self-consistent and automated determination of the weights of regularization terms. This encouraging result will lead us to extend the approach to 3D and more complex cells.

We propose a method to detect and track multiple moving biological spot-like particles showing different kinds of dynamics in image sequences acquired through multidimensional fluorescence microscopy. It enables the extraction and analysis of information such as number, position, speed, movement, and diffusion phases of, e.g., endosomal particles. The method consists of several stages. After a detection stage performed by a three-dimensional (3-D) undecimated wavelet transform, we compute, for each detected spot, several predictions of its future state in the next frame. This is accomplished thanks to an interacting multiple model (IMM) algorithm which includes several models corresponding to different biologically realistic movement types. Tracks are constructed, thereafter, by a data association algorithm based on the maximization of the likelihood of each IMM. The last stage consists of updating the IMM filters in order to compute final estimations for the present image and to improve predictions for the next image. The performances of the method are validated on synthetic image data and used to characterize the 3-D movement of endocytic vesicles containing quantum dots.

We propose an extension of parametric active contours designed to track nonoccluding objects transiently touching each other, a task where both parametric and single level set-based methods usually fail. Our technique minimizes a cost functional that depends on all contours simultaneously and includes a penalty for contour overlaps. This scheme allows us to take advantage of known constraints on object topology, namely, that objects cannot merge. The coupled contours preserve the identity of previously isolated objects during and after a contact event, thus allowing segmentation and tracking to proceed as desired.

Cell migrations and deformations play essential roles in biological processes, such as parasite invasion, immune response, embryonic development, and cancer. We describe a fully automatic segmentation and tracking method designed to enable quantitative analyses of cellular shape and motion from dynamic three-dimensional microscopy data. The method uses multiple active surfaces with or without edges, coupled by a penalty for overlaps, and a volume conservation constraint that improves outlining of cell/cell boundaries. Its main advantages are robustness to low signal-to-noise ratios and the ability to handle multiple cells that may touch, divide, enter, or leave the observation volume. We give quantitative validation results based on synthetic images and show two examples of applications to real biological data.

Bayesian target tracking methods consist of filtering successive measurements coming from a detector. Linear and nonlinear Gaussian Bayesian filters are well adapted to estimate the successive a posteriori state distributions of a single moving target from a sequence of observations. However, when tracking several targets in a cluttered environment, previous techniques must be combined with dedicated procedures for validating and associating the measurements to their predictions. Gating validation techniques are used to increase the reliability of the association technique by retaining only the measurements that could be originated from predicted measurements. In standard techniques, the only constraint imposed on the gate is to contain the correct measurement. However, as the shape of the validation gate is related to the covariance of the transition noise, it is of major importance to estimate it in a reliable manner. We therefore review several methods to update the covariance of transition noise and we propose a new one that enables the validation gate to be adapted both to the smoothly evolving dynamic of a moving target and to an abruptly changing dynamic. All the methods are compared for performance on microscopy image sequences which typically contain objects that abruptly change their behavior.

A method which allows for the first time to perform automatically the detection and the tracking of microscopic objects directly from three dimensional image data is presented. It enables to analyse biological moving objects in three dimensional fluorescence image sequences coming from biological immunomicroscopy experiments, and get quantitative data such as the number of objects, their position, movement phases and speed. After a detection step is performed through the multiscale analysis of images using a shift-invariant wavelet transform, the tracking is achieved using a Kalman filter and an association which enable the position of the moving objects to be predicted, refined and updated. Trajectories are analysed in terms of different parameters relevant for the motility analysis of biological objects.

This paper presents a segmentation and tracking method for quantitative analysis of cell dynamics from in vitro videomicroscopy data. The method is based on parametric active contours and includes several adaptations that address important difficulties of cellular imaging, particularly the presence of low-contrast boundary deformations known as pseudopods, and the occurence of multiple contacts between cells. First, we use an edge map based on the average intensity dispersion that takes advantage of relative background homogeneity to facilitate the detection of both pseudopods and interfaces between adjacent cells. Second, we introduce a repulsive interaction between contours that allows correct segmentation of objects in contact and overcomes the shortcomings of previously reported techniques to enforce contour separation. Our tracking technique was validated on a realistic data set by comparison with a manually defined ground-truth and was successfully applied to study the motility of amoebae in a biological research project.

We present a method to detect and count spots in three dimensional fluorescence images coming from biological immunomicroscopy experiments. It is based on the multiscale product of subband images resulting from a undecimated three dimensional wavelet transform decomposition of the original 3D image, after thresholding of non-significant coefficients. The multiscale product of the filtered wavelet coefficients, which allows the multiscale peaks due to spots to be enhanced while reducing noise, combines information coming from different levels of resolution and gives a clear and distinctive characterization of the spots. The effectiveness of the method is illustrated on microscopy images of yeast cells.

We present a complete framework for automating the objective and reliable assessment of biological objects motility. We address, in the context of one particular application, some of the main problems in dealing with the automatic tracking of biological objects, which are: (1) the robust segmentation of individual objects which is quite often hindered by the poor contrast of the imaging technique; (2) the proper initialisation of multiple objects description; and (3) the problem of temporary object aggregation, during which objects loose their individuality. We have implemented the active contour model based on the gradient vector field model (Xu and Prince, 1998) and adapted it in order to overcome some of its limitations in dealing with biological related objects. Results are presented of the analysis of video sequences of a living amoeba.

We present a method to detect and track multiple moving biological objects in images acquired by video microscopy. The automatic detection is based upon the correlation of the image with a filter which varies adaptively to represent an object as it moves and deforms. The tracking is performed using a Kalman filter and a cost function which enable the position of the moving objects to be predicted, refined and updated. The efficiency of the method has been tested on real biological image sequences and is illustrated by results obtained from the analysis of typical biological video microscopy sequences.

We present a method whereby the extraction of spots from grey-level biological images is accomplished by globally transforming the image and by locally and adaptatively modifying the transformed image. The method is based upon selectively filtering an undecimated wavelet decomposition of the image through the use of wavelet coefficient thresholding and correlation. Since spots are big local discontinuities in the image, the proposed strategy is to trace and to reinforce their wavelet signature across a number of resolution levels and to use the resulting information to accomplish recognition. Results are presented for the analysis of typical immunofluorescence and colloidal particles immunolabelled images.

A segmentation method using a peak analysis algorithm for threshold selection is presented. It is based on the detection of the zero-crossings and the local extrema of a wavelet transform which give a complete characterization of the peaks in the histogram. These values are used for the unsupervised selection of a sequence of thresholds describing a coarse-to-fine analysis of histogram variation. The results of using the proposed technique are presented in the case of different images.