Ilker Ersoy

Efficient feature extraction and likelihood fusion for vehicle tracking in low frame rate airborne video

Very large format video or wide-area motion imagery (WAMI) acquired by an airborne camera sensor array is characterized by persistent observation over a large field-of-view with high spatial resolution but low frame rates (i.e. one to ten frames per second). Current WAMI sensors have sufficient coverage and resolution to track vehicles for many hours using just a single airborne platform. We have developed an interactive low frame rate tracking system based on a derived rich set of features for vehicle detection using appearance modeling combined with saliency estimation and motion prediction. Instead of applying subspace methods to very high-dimensional feature vectors, we tested the performance of feature fusion to locate the target of interest within the prediction window. Preliminary results show that fusing the feature likelihood maps improves detection but fusing feature maps combined with saliency information actually degrades performance.

Cell segmentation using Hessian-based detection and contour evolution with directional derivatives

The large amount of data produced by biological live cell imaging studies of cell behavior requires accurate automated cell segmentation algorithms for rapid, unbiased and reproducible scientific analysis. This paper presents a new approach to obtain precise boundaries of cells with complex shapes using ridge measures for initial detection and a modified geodesic active contour for curve evolution that exploits the halo effect present in phase-contrast microscopy. The level set contour evolution is controlled by a novel spatially adaptive stopping function based on the intensity profile perpendicular to the evolving front. The proposed approach is tested on human cancer cell images from LSDCAS and achieves high accuracy even in complex environments.

Moving object segmentation using the flux tensor for biological video microscopy

Time lapse video microscopy routinely produces terabyte sized biological image sequence collections, especially in high throughput environments, for unraveling cellular mechanisms, screening biomarkers, drug discovery, image-based bioinformatics, etc. Quantitative movement analysis of tissues, cells, organelles or molecules is one of the fundamental signals of biological importance. The accurate detection and segmentation of moving biological objects that are similar but nonhomogeneous is the focus of this paper. The problem domain shares similarities with multimedia video analytics. The grayscale structure tensor fails to disambiguate between stationary and moving features without computing dense velocity fields (i.e. optical flow). In this paper we propose a novel motion detection algorithm based on the flux tensor combined with multi-feature level set-based segmentation, using an efficient additive operator splitting (AOS) numerical implementation, that robustly handles deformable motion of non-homogeneous objects. The flux tensor level set framework effectively handles biological video segmentation in the presence of complex biological processes, background noise and clutter.

Segmentation and Classification of Cell Cycle Phases in Fluorescence Imaging

Current chemical biology methods for studying spatiotemporal correlation between biochemical networks and cell cycle phase progression in live-cells typically use fluorescence-based imaging of fusion proteins. Stable cell lines expressing fluorescently tagged protein GFP-PCNA produce rich, dynamically varying sub-cellular foci patterns characterizing the cell cycle phases, including the progress during the S-phase. Variable fluorescence patterns, drastic changes in SNR, shape and position changes and abundance of touching cells require sophisticated algorithms for reliable automatic segmentation and cell cycle classification. We extend the recently proposed graph partitioning active contours (GPAC) for fluorescence-based nucleus segmentation using regional density functions and dramatically improve its efficiency, making it scalable for high content microscopy imaging. We utilize surface shape properties of GFP-PCNA intensity field to obtain descriptors of foci patterns and perform automated cell cycle phase classification, and give quantitative performance by comparing our results to manually labeled data.

Vasoactive agonists exert dynamic and coordinated effects on vascular smooth muscle cell elasticity, cytoskeletal remodelling and adhesion

This study demonstrates rapid and dynamic changes in adhesion and cell elasticity following agonist stimulation that culminate in a remodelled cytoskeleton in vascular smooth muscle. Evidence is presented that the changes in adhesion and elasticity are coordinated and that these variables demonstrate temporal oscillation consisting of three major oscillation components. Eigen‐decomposition spectrum analysis revealed that these components of oscillation in cell elasticity and adhesion may be linked by shared signalling pathways. Evidence is provided that the agonists angiotensin II and adenosine produce remodelling of actin cytoskeleton that may alter the properties of the observed oscillations in elasticity and adhesion. It is concluded that angiotensin II and adenosine may regulate extracellular matrix adhesion and elasticity in vascular smooth muscle cells as a form of adaptation to more efficiently support contractile behaviour.

Multi-feature contour evolution for automatic live cell segmentation in time lapse imagery

Cell boundary segmentation in live cell image sequences is the first step towards quantitative analysis of cell motion and behavior. The time lapse microscopy imaging produces large volumes of image sequence collections which requires fast and robust automatic segmentation of cell boundaries to utilize further automated tools such as cell tracking to quantify and classify cell behavior. This paper presents a methodology that is based on utilizing the temporal context of the cell image sequences to accurately delineate the boundaries of non-homogeneous cells. A novel flux tensor-based detection of moving cells provides initial localization that is further refined by a multi-feature level set-based method using an efficient additive operator splitting scheme. The segmentation result is processed by a watershed-based algorithm to avoid merging boundaries of neighboring cells. By utilizing robust features, the level-set algorithm produces accurate segmentation for non-homogeneous cells with concave shapes and varying intensities.

Performance evaluation of block-based motion estimation algorithms and distortion measures

Motion estimation is an important component in video compression schemes, which impacts the encoder performance and the quality of the reconstructed video sequence. Block-based techniques are the most popular among the several motion estimation techniques used in practice due to their simplicity allowing efficient hardware implementations. The quality of motion predicted frame and the speed of motion vector computation are the primary measures of performance of motion estimation schemes. The video compression standards only specify the syntax of the bitstream and not any specifics of the motion estimation techniques. Thus, the knowledge of the workings and performance of commonly used motion estimation schemes would facilitate development of better schemes or choosing a particular one for a given application. We present the results of performance evaluation of combinations of several commonly used block-based motion estimation algorithms and distortion measures.

Cell Spreading Analysis with Directed Edge Profile-Guided Level Set Active Contours

Cell adhesion and spreading within the extracellular matrix (ECM) plays an important role in cell motility, cell growth and tissue organization. Measuring cell spreading dynamics enables the investigation of cell mechanosensitivity to external mechanical stimuli, such as substrate rigidity. A common approach to measure cell spreading dynamics is to take time lapse images and quantify cell size and perimeter as a function of time. In our experiments, differences in cell characteristics between different treatments are subtle and require accurate measurements of cell parameters across a large population of cells to ensure an adequate sample size for statistical hypothesis testing. This paper presents a new approach to estimate accurate cell boundaries with complex shapes by applying a modified geodesic active contour level set method that directly utilizes the halo effect typically seen in phase contrast microscopy. Contour evolution is guided by edge profiles in a perpendicular direction to ensure convergence to the correct cell boundary. The proposed approach is tested on bovine aortic endothelial cell images under different treatments, and demonstrates accurate segmentation for a wide range of cell sizes and shapes compared to manual ground truth.

CNN-based image analysis for malaria diagnosis

Malaria is a major global health threat. The standard way of diagnosing malaria is by visually examining blood smears for parasite-infected red blood cells under the microscope by qualified technicians. This method is inefficient and the diagnosis depends on the experience and the knowledge of the person doing the examination. Automatic image recognition technologies based on machine learning have been applied to malaria blood smears for diagnosis before. However, the practical performance has not been sufficient so far. This study proposes a new and robust machine learning model based on a convolutional neural network (CNN) to automatically classify single cells in thin blood smears on standard microscope slides as either infected or uninfected. In a ten-fold cross-validation based on 27,578 single cell images, the average accuracy of our new 16-layer CNN model is 97.37%. A transfer learning model only achieves 91.99% on the same images. The CNN model shows superiority over the transfer learning model in all performance indicators such as sensitivity (96.99% vs 89.00%), specificity (97.75% vs 94.98%), precision (97.73% vs 95.12%), F1 score (97.36% vs 90.24%), and Matthews correlation coefficient (94.75% vs 85.25%).

Peroxiredoxin 6 (Prdx6) supports NADPH oxidase1 (Nox1)-based superoxide generation and cell migration.

Nox1 is an abundant source of reactive oxygen species (ROS) in colon epithelium recently shown to function in wound healing and epithelial homeostasis. We identified Peroxiredoxin 6 (Prdx6) as a novel binding partner of Nox activator 1 (Noxa1) in yeast two-hybrid screening experiments using the Noxa1 SH3 domain as bait. Prdx6 is a unique member of the Prdx antioxidant enzyme family exhibiting both glutathione peroxidase and phospholipase A2 activities. We confirmed this interaction in cells overexpressing both proteins, showing Prdx6 binds to and stabilizes wild type Noxa1, but not the SH3 domain mutant form, Noxa1 W436R. We demonstrated in several cell models that Prdx6 knockdown suppresses Nox1 activity, whereas enhanced Prdx6 expression supports higher Nox1-derived superoxide production. Both peroxidase- and lipase-deficient mutant forms of Prdx6 (Prdx6 C47S and S32A, respectively) failed to bind to or stabilize Nox1 components or support Nox1-mediated superoxide generation. Furthermore, the transition-state substrate analogue inhibitor of Prdx6 phospholipase A2 activity (MJ-33) was shown to suppress Nox1 activity, suggesting Nox1 activity is regulated by the phospholipase activity of Prdx6. Finally, wild type Prdx6, but not lipase or peroxidase mutant forms, supports Nox1-mediated cell migration in the HCT-116 colon epithelial cell model of wound closure. These findings highlight a novel pathway in which this antioxidant enzyme positively regulates an oxidant-generating system to support cell migration and wound healing.