Search

This chapter presents an overview of the application of local image filters for the problems of cell detection and tracking in microscopy images, and also extends their use to the joint tracking of motion and shape of cells in time-lapse videos. The use of cell tracking based on a detection-association approach has the advantage of simplicity but is limited by the initial detection. State modelling approaches that assume linear dynamics and Gaussian noise in the tracking estimation can make use of the Kalman filter. However, in real biological applications more complex models may be required, which may not be linear or Gaussian, invalidating the use of the Kalman filter. Particle filter-based tracking is applied when modelling nonlinear dynamics, as they are less restrictive in their assumptions. Cell morphology plays an important role on cell mobility more precisely in the directionality and randomness of the cell movement.

Computational methods used in microscopy cell image analysis have largely augmented the impact of imaging techniques, becoming fundamental for biological research. The understanding of cell regulation processes is very important in biology, and in particular confocal fluorescence imaging plays a relevant role for the in vivo observation of cells. However, most biology researchers still analyze cells by visual inspection alone, which is time consuming and prone to induce subjective bias. This makes automatic cell image analysis essential for large scale, objective studies of cells. While the classic approach for automatic cell analysis is to use image segmentation, for in vivo confocal fluorescence microscopy images of plants, such approach is neither trivial nor is it robust to image quality variations. To analyze plant cells in in vivo confocal fluorescence microscopy images with robustness and increased performance, we propose the use of local convergence filters (LCF). These filters are based in gradient convergence and as such can handle illumination variations, noise and low contrast. We apply a range of existing convergence filters for cell nuclei analysis of the Arabidopsis thaliana plant root tip. To further increase contrast invariance, we present an augmentation to local convergence approaches based on image phase information. Through the use of convergence index filters we improved the results for cell nuclei detection and shape estimation when compared with baseline approaches. Using phase congruency information we were able to further increase performance by 11% for nuclei detection accuracy and 4% for shape adaptation. Shape regularization was also applied, but with no significant gain, which indicates shape estimation was good for the applied filters.

To obtain development information of individual plant cells, it is necessary to perform in vivo imaging of the specimen under study, through time-lapse confocal microscopy. Automation of cell detection/marking process is important to provide research tools in order to ease the search for special events, such as cell division. In this paper we discuss an automatic cell detection approach for Arabidopsis thaliana based on segmentation, which selects the best cell candidates from a starting watershed-based image segmentation and improves the result by merging adjacent regions. The selection of individual cells is obtained using a support vector machine (SVM) classifier, based on a cell descriptor constructed from the shape and edge strength of the cells' contour. In addition we proposed a novel cell merging criterion based on edge strength along the line that connects adjacent cells' centroids, which is a valuable tool in the reduction of cell over-segmentation. The result is largely pruned of badly segmented and over-segmented cells, thus facilitating the study of cells. When comparing the results after merging with the basic watershed segmentation, we obtain 1.5% better coverage (increase in F-measure) and up to 27% better precision in correct cell segmentation.

This paper presents a novel approach for visual scene modeling and classification, investigating the combined use of text modeling methods and local invariant features. Our work attempts to elucidate 1) whether a textlike bag-of-visterms (BOV) representation (histogram of quantized local visual features) is suitable for scene (rather than object) classification, 2) whether some analogies between discrete scene representations and text documents exist, and 3) whether unsupervised, latent space models can be used both as feature extractors for the classification task and to discover patterns of visual co-occurrence. Using several data sets, we validate our approach, presenting and discussing experiments on each of these issues. We first show, with extensive experiments on binary and multiclass scene classification tasks using a 9,500-image data set, that the BOV representation consistently outperforms classical scene classification approaches. In other data sets, we show that our approach competes with or outperforms other recent more complex methods. We also show that Probabilistic Latent Semantic Analysis (PLSA) generates a compact scene representation, is discriminative for accurate classification, and is more robust than the BOV representation when less labeled training data is available. Finally, through aspect-based image ranking experiments, we show the ability of PLSA to automatically extract visually meaningful scene patterns, making such representation useful for browsing image collections. Quelhas P., Monay F., Odobez J.-M., Gatica-Perez D., Tuytelaars T., ''A thousand words in a scene'', IEEE transactions on pattern analysis and machine intelligence, vol. 29, no. 9, pp. 1575-1589, September 2007. ispartof: IEEE Transactions on pattern analysis and machine intelligence vol:29 issue:9 pages:1575-1589 ispartof: location:United States status: published

Immunogold particle detection is a time-consuming task where a single image containing almost a thousand particles can take several hours to annotate. In this work we present a framework for the automatic detection of immunogold particles that can leverage significantly the burden of this manual task. Our proposal applies a Laplacian of Gaussian (LoG) filter to provide its detection estimates to a Stacked Denoising Autoencoder (SdA). This learning model endowed with the capability to extract higher order features provides a robust performance to our framework. For the validation of our framework, a new dataset was created. Based on our work, we determined that solely the LoG detector attained more than 74.1 % of accuracy and, when combined with a SdA the accuracy is improved by at most 11.4 %.

Evaluation of parasite infection indexes on in vitro cell cultures is a practice commonly employed by biomedical researchers to address biological questions or to test the efficacy of novel anti-parasitic compounds. In the case of Leishmania infantum, infection indexes are usually determined either by visual inspection of cells directly under the microscope or by counting digital images using appropriate software. In either case assessment of infection indexes is time consuming, thus motivating the creation of automatic image analysis approaches.

The automatic analysis of cancer cells has gained increasing relevance given the amount of data that biology researchers have to analyze. However, most biology researchers still analyze cells by visual inspection alone, which is time consuming and prone to induce subjective bias. This makes automatic cell image analysis essential for large scale, objective studies of cells.

The automatic analysis of cell mobility has gained increasing relevance given the enormous amount of data that biology researchers have currently to analyze. However, most biology researchers still analyze cells by visual inspection alone, which is time consuming and prone to induce subjective bias. This makes automatic cell’s mobility analysis essential for large scale, objective studies of cells. To evaluate cancer cell’s mobility, biologists establish in vitro assays with cancer cells seeded on native surfaces or on surfaces coated with extracellular matrix components, recording time-lapse brightfield microscopy images. In such analysis only through the use of quantitative automatic analysis tools is it possible to gather evidence to firmly support biological findings.

Evaluation of parasite infection indexes on in vitro cell cultures is a practice commonly employed by biomedical researchers to address biological questions or to test the efficacy of novel anti-parasitic compounds. In the particular case of Leishmania infantum, a unicellular parasite that parasitizes macrophages, infection indexes are usually determined either by visual inspection of cells directly under the microscope or by counting digital images using appropriate software. In either case assessment of infection indexes is time consuming, thus motivating the creation of automatic image analysis approaches that allow large scale studies of Leishmania-infected macrophage cultures. We propose a fully automated method for automatic evaluation of parasite infection indexes through the segmentation of individual macrophages nucleus and cytoplasm, as well as the segmentation and co-localization of the parasites in the image. To perform such analysis with robustness and increased performance we propose the use of local image filters tuned to the specific size of the objects to detect, in conjunction with image segmentation approaches. The objects size estimation is then improved through a learning feedback loop. Cytoplasm is detected by seeded watershed segmentation. Our approach obtains, for 86 images from 4 experiments, an average parasite infection index evaluation error of 2.3%.

Cell tracking is a fundamental problem for studying live cell dynamics. A novel approach for low frame rate cell tracking in fluorescent microscopy image is herein proposed. The method is based on sliding band filter detection and Delaunay triangulation sub-graph matching. With this approach we can track a large amount of small cells without their motion model and not relying on cell motion continuity between consecutive images. The effectiveness and robustness of the method were validated by visual inspection and on a ground truth dataset.

In plant development biology, the study of the structure of the plant's root is fundamental for the understanding of the regulation and interrelationships of cell division and cellular differentiation. This is based on the high connection between cell length and progression of cell differentiation and the nuclear state. However, the need to analyse a large amount of images from many replicate roots to obtain reliable measurements motivates the development of automatic tools for root structure analysis. We present a novel automatic approach to detect cell files, the main structure in plant roots, and extract the length of the cells in those files. This approach is based on the detection of local cell file characteristic symmetry using a wavelet based image symmetry measure. The resulting detection enables the automatic extraction of important data on the plant development stage and of characteristics for individual cells. Furthermore, the approach presented reduces in more than 90% the time required for the analysis of each root, improving the work of the biologist and allowing the increase of the amount of data to be analysed for each experimental condition. While our approach is fully automatic a user verification and editing stage is provided so that any existing errors may be corrected. Given five test images it was observed that user did not correct more than 20% of all automatically detected structure, while taking no more than 10% of manual analysis time to do so.

Plant development is orchestrated by transcription factors whose expression has become observable in living plants through the use of fluorescence microscopy. However, the exact quantification of expression levels is still not solved and most analysis is only performed through visual inspection. With the objective of automating the quantification of cell nuclei fluorescence we present a new approach to detect cell nuclei in 3D fluorescence confocal microscopy, based on the use of the sliding band convergence filter (SBF). The SBF filter detects cell nuclei and estimate their shape with high accuracy in each 2D image plane. For 3D detection, individual 2D shapes are joined into 3D estimates and then corrected based on the analysis of the fluorescence profile. The final nuclei detection’s precision/recall are of 0.779/0.803 respectively, and the average Dice’s coefficient of 0.773.

The study of cell nuclei is fundamental for plant cell Biology research. To obtain information at cellular level, researchers image cells' nuclei which were modified with fluorescence proteins, through laser scanning confocal microscopy. These images are normally noisy and suffer from high background fluorescence, making grey-scale segmentation approaches inadequate for a usable detection. To obtain a successful detection even at low contrast we investigate the use of a particular convergence filter, the Symmetric Sliding Band filter (SSBF), for cell detection. This filter is based on gradient convergence and not intensity. As such it can detect low contrast cell nuclei which otherwise would be lost in the background noise. Due to the characteristics of cell nuclei morphology, a symmetry constrain is integrated in the filter which corrects some inadequate detections and results in a filter response that is more discriminative. We evaluate the use of this filter for cell nuclei detection on the Arabidopsis thaliana root tip, where the nuclei were stained using yellow fluorescence protein. The resulting cell nuclei detection precision is 89%.

We present a novel approach for contextual classification of image patches in complex visual scenes, based on the use of histograms of quantized features and probabilistic aspect models. Our approach uses context in two ways: (1) by using the fact that specific learned aspects correlate with the semantic classes, which resolves some cases of visual polysemy often present in patch-based representations, and (2) by formalizing the notion that scene context is image-specific—what an individual patch represents depends on what the rest of the patches in the same image are. We demonstrate the validity of our approach on a man-made versus natural patch classification problem. Experiments on an image collection of complex scenes show that the proposed approach improves region discrimination, producing satisfactory results and outperforming two noncontextual methods. Furthermore, we also show that co-occurrence and traditional (Markov random field) spatial contextual information can be conveniently integrated for further improved patch classification.

In vivo observation of cells in the Arabidopsis thaliana root, by time-lapse confocal microscopy, is central to biology research. The research herein described is based on large amount of image data, which must be analyzed to determine the location and state of individual cells. Automating the process of cell tracking is an important step to create tools which will facilitate the analysis of cellspsila evolution through time. Here we introduce a confocal tracking system designed in two stages. At the image acquisition stage, we track the area under analysis based on point-to-point correspondences and motion estimation. After image acquisition, we compute cell-to-cell correspondences through time. The final result is a temporal structured information about each cell.

In vivoobservation and tracking of the Arabidopsis thalianaroot meristem, by time-lapse confocal microscopy, is important to understand mechanisms like cell division and elongation. The research herein described is based on a large amount of image data, which must be analyzed to determine the location and state of cells. The automation of the process of cell detection/marking is an important step to provide research tools for the biologists in order to ease the search for special events, such as cell division. This paper discusses a hybrid approach for automatic cell segmentation, which selects the best cell candidates from a starting watershed-based image segmentation and improves the result by merging adjacent regions. The selection of individual cells is obtained using a Support Vector Machine (SVM) classifier, based on the shape and edge strength of the cells' contour. The merging criterion is based on edge strength along the line that connects adjacent cells' centroids. The resulting segmentation is largely pruned of badly segmented and over-segmented cells, thus facilitating the study of cell division.

In vivo observation and tracking of cell division in the Arabidopsis thaliana root meristem, by time-lapse confocal microscopy, is central to biology research. The research herein described is based on large amount of image data, which must be analyzed to determine the location and state of cells. The possibility of automating the process of cell detection/marking is an important step to provide research tools to the biologists in order to ease the search for a special event as cell division. This paper discusses an automatic cell segmentation method, which selects the best cell candidates from a starting watershed based image segmentation. The selection of individual cells is obtained using a support vector machine (SVM) classifier, based on the shape and edge strength of the cells' contour. The resulting segmentation is largely pruned of badly segmented cells, which can reduce the false positive detection of cell division. This is a good result on its own and a starting point for improvement of cell segmentation methodology.

In the past, quantized local descriptors have been shown to be a good base for the representation of images, that can be applied to a wide range of tasks. However, current approaches typically consider only one level of quantization to create the final image representation. In this view they somehow restrict the image description to one level of visual detail. We propose to build image representations from multi-level quantization of local interest point descriptors, automatically extracted from the images. The use of this new multi-level representation will allow for the description of fine and coarse local image detail in one framework. To evaluate the performance of our approach we perform scene image classification using a 13-class data set. We show that the use of information from multiple quantization levels increases the classification performance, which suggests that the different granularity captured by the multi-level quantization produces a more discriminant image representation. Moreover, by using a multi-level approach, the time necessary to learn the quantization models can be reduced by learning the different models in parallel.

We present a novel approach for contextual segmentation of complex visual scenes, based on the use of bags of local invariant features (visterms) and probabilistic aspect models. Our approach uses context in two ways: (1) by using the fact that specific learned aspects correlate with the semantic classes, which resolves some cases of visual polysemy, and (2) by formalizing the notion that scene context is image-specific -what an individual visterm represents depends on what the rest of the visterms in the same bag represent too-. We demonstrate the validity of our approach on a man-made vs. natural visterm classification problem. Experiments on an image collection of complex scenes show that the approach improves region discrimination, producing satisfactory results, and outperforming a non-contextual method. Furthermore, through the later use of a Markov Random Field model, we also show that co-occurrence and spatial contextual information can be conveniently integrated for improved visterm classification.

We propose the use of latent space models applied to local invariant features for object classification. We investigate whether using latent space models enables to learn patterns of visual co-occurrence and if the learned visual models improve performance when less labeled data are available. We present and discuss results that support these hypotheses. Probabilistic Latent Semantic Analysis (PLSA) automatically identifies aspects from the data with semantic meaning, producing unsupervised soft clustering. The resulting compact representation retains sufficient discriminative information for accurate object classification, and improves the classification accuracy through the use of unlabeled data when less labeled training data are available. We perform experiments on a 7-class object database containing 1776 images.

This paper presents an improved tracking based method for retinal vessel segmentation that uses blood vessel morphology to adapt the tracking parameters. The method includes branching detection and avoidance methods. A bi-level threshold method, based on local vessel information, is used for segmentation. Tracking is based on Kalman filtering. The results are compared with existing ground truth. It is concluded that ground truth segmentation is not easily comparable.

This paper presents a novel approach for visual scene representation, combining the use of quantized color and texture local invariant features (referred to here as {\em visterms}) computed over interest point regions. In particular we investigate the different ways to fuse together local information from texture and color in order to provide a better {\em visterm} representation. We develop and test our methods on the task of image classification using a 6-class natural scene database. We perform classification based on the {\em bag-of-visterms} (BOV) representation (histogram of quantized local descriptors), extracted from both texture and color features. We investigate two different fusion approaches at the feature level: fusing local descriptors together and creating one representation of joint texture-color visterms, or concatenating the histogram representation of both color and texture, obtained independently from each local feature. On our classification task we show that the appropriate use of color improves the results w.r.t. a texture only representation.