A5083291106- Cell Image Analysis Techniques
- Plant Molecular Biology Research
- Image Processing Techniques and Applications
- Smart Agriculture and AI
- Leaf Properties and Growth Measurement
- Digital Imaging for Blood Diseases
- Tree Root and Stability Studies
- Plant Reproductive Biology
- Single-cell and spatial transcriptomics
- Computational Geometry and Mesh Generation
- Emotion and Mood Recognition
- Face recognition and analysis
- Image Retrieval and Classification Techniques
- Face and Expression Recognition
- Computer Graphics and Visualization Techniques
- Advanced biosensing and bioanalysis techniques
- Remote Sensing and LiDAR Applications
- Molecular Biology Techniques and Applications
- Plant Gene Expression Analysis
- 3D Shape Modeling and Analysis
- Medical Image Segmentation Techniques
- Advanced Fluorescence Microscopy Techniques
- Advanced Numerical Analysis Techniques
- Morphological variations and asymmetry
- AI in cancer detection
California Institute of Technology
2010-2023
Advanced Imaging Research (United States)
2019
Research Institute for Advanced Computer Science
2010
Carnegie Mellon University
1997-2004
Highlighted Article: In situ hybridization chain reaction (HCR) v3.0 exploits automatic background suppression to enable multiplexed quantitative mRNA imaging and flow cytometry with dramatically enhanced performance ease of use.
How growth and proliferation are precisely controlled in organs during development how the regulation of cell division contributes to formation complex type patterns important questions developmental biology. Such a pattern diverse sizes is characteristic sepals, outermost floral organs, plant Arabidopsis thaliana. To determine size formed sepal epidermis, we iterate between generating predictions from computational model testing these through time-lapse imaging. We show that diversity due...
Abstract The Cell Tracking Challenge is an ongoing benchmarking initiative that has become a reference in cell segmentation and tracking algorithm development. Here, we present significant number of improvements introduced the challenge since our 2017 report. These include creation new segmentation-only benchmark, enrichment dataset repository with datasets increase its diversity complexity, silver standard corpus based on most competitive results, which will be particular interest for...
We present an efficient algorithm for nonlocal image filtering with applications in electron cryomicroscopy. Our denoising is a rewriting of the recently proposed mean filter. It builds on separable property neighborhood to offer fast parallel and vectorized implementation contemporary shared memory computer architectures while reducing theoretical computational complexity original In practice, our approach much faster than serial, non-vectorized it scales linearly size. demonstrate its...
The formation of cellular patterns during development requires the coordination cell division with identity specification. This is essential in patterning highly elongated giant cells, which are interspersed between small outer epidermis Arabidopsis thaliana sepal. Giant cells undergo endocycles, replicating their DNA without dividing, whereas divide mitotically. We show that distinct enhancers expressed and indicating these types have different identities as well sizes. find members...
We present a new end-to-end network architecture for facial expression recognition with an attention model. It focuses in the human face and uses Gaussian space representation recognition. devise this based on two fundamental complementary components: (1) image correction (2) classification. The first component encoder-decoder style convolutional feature extractor that are pixel-wise multiplied to obtain map. second is responsible obtaining embedded classification of expression. propose loss...
Significance Stem cells not only initiate organs, but may also contribute to organ patterning, at least in the shoot apex of flowering plants: classical microsurgical experiments imply that apical meristem promotes development leaf adaxial side, i.e., upper side. In this study, we show existence a transient low auxin zone side contributes development. We further find results from transport leaves apex. Thus, it is positive signal stem cells, departure signaling molecule primordia delivers...
ABSTRACT In situ hybridization based on the mechanism of chain reaction (HCR) has addressed multi-decade challenges to imaging mRNA expression in diverse organisms, offering a unique combination multiplexing, quantitation, sensitivity, resolution, and versatility. Here, with third-generation HCR, we augment these capabilities using probes amplifiers that combine provide automatic background suppression throughout protocol, ensuring even if reagents bind non-specifically within sample they...
The quantitative analysis of cellular membranes helps understanding developmental processes at the level. Particularly 3D microscopic image data offers valuable insights into cell dynamics, but error-free automatic segmentation remains challenging due to huge amount generated and strong variations in intensities. In this paper, we propose a new approach that combines discriminative power convolutional neural networks (CNNs) for preprocessing investigates performance three watershed-based...
We propose a new multiclass weighted loss function for instance segmentation of cluttered cells. are primarily motivated by the need developmental biologists to quantify and model behavior blood T-cells which might help us in understanding their regulation mechanisms ultimately researchers quest developing an effective immuno-therapy cancer treatment. Segmenting individual touching cells regions is challenging as feature distribution on shared borders cell foreground similar thus...
Recent advances in biological imaging have resulted an explosion the quality and quantity of images obtained a digital format. Developmental biologists are increasingly acquiring beautiful complex images, thus creating vast image datasets. In past, patterns data been detected by human eye. Larger datasets, however, necessitate high-throughput objective analysis tools to computationally extract quantitative information from images. These developed collaborations between biologists, computer...
Significance Membrane and cytoskeletal dynamics are critical to cell motility. Extensively studied in culture, their roles movement vivo less understood, especially higher vertebrates. We use dynamic imaging visualize membrane behavior migrating neural crest cells living tissue. found that forward of individual is accompanied by circular flow, from anterior-to-posterior apically posterior-to-anterior basally, coupled with internalization lipid vesicles via macropinocytosis the soma....
We propose a new loss formulation to further advance the multiclass segmentation of cluttered cells under weakly supervised conditions. When adding Youden's J statistic regularization term cross entropy we improve separation touching and immediate cells, obtaining sharp boundaries with high adequacy. This intrinsically supports class imbalance thus eliminating necessity explicitly using weights balance training. Simulations demonstrate this capability show how leads correct results by...
Automated segmentation approaches are crucial to quantitatively analyze large-scale 3D microscopy images. Particularly in deep tissue regions, automatic methods still fail provide error-free segmentations. To improve the quality throughout imaged samples, we present a new supervoxel-based approach that outperforms current and reduces manual correction effort. The algorithm consists of gentle preprocessing conservative super-voxel generation method followed by supervoxel agglomeration based...
The correct targeting and insertion of tail-anchored (TA) integral membrane proteins is critical for cellular homeostasis. TA are defined by a hydrophobic transmembrane domain (TMD) at their C-terminus targeted to either the ER or mitochondria. Derived from experimental measurements few proteins, there has been little examination TMD features that determine localization. As result, localization many misclassified simple heuristic overall hydrophobicity. Because ER-directed TMDs favor...
We present methods for segmenting the sepal and shoot apical meristem of Arabidopsis thaliana plant. propose a mathematical morphology pipeline modified numerical scheme active contours without edges algorithm to extract geometry topology plant cells imaged using confocal laser scanning microscopy. demonstrate our in typical images used studies cell endoreduplication hormone transport show that practice they produce highly accurate results requiring little human intervention cope with image...
We present a new framework for maintaining the quality of two dimensional triangular moving meshes. The use curved elements is key idea that allows us to avoid excessive refinement and still obtain good meshes consisting low number well shaped elements. B-splines curves model object boundaries, objects are meshed with second order Bézier triangles. As mesh evolves according non-uniform flow velocity field, we keep track boundaries and, if needed, carefully modify it by applying combination...
The quantitative analysis of 3D confocal microscopy images the shoot apical meristem helps understanding growth process some plants. Cell segmentation in these is crucial for computational plant and many automated methods have been proposed. However, variations signal intensity across image mitigate effectiveness those approaches with no easy way user correction. We propose a web-based collaborative application, SEGMENT3D, to leverage automatic results. divided into tiles that can be either...
Acetylcholine (ACh) promotes various cell migrations in vitro, but there are few investigations into this nonsynaptic role of ACh signaling vivo. Here we investigate the function a muscarinic receptor on an epithelial migration