Based on a simple ratiometric intensity computation, dual-focus optics have enabled us to track the vesicle transport in a living cell directly from the fluorescence microscopy images. However, because the acquired dual images from this 3D microscopy can be suffered from optical distortion, the calculation result might not accurate enough for the nano-scale. In this paper, we suggest a linear transformation-based image processing method for the accurate detection and tracking of a vesicle in a living cell. In addition, we present a pipeline for reconstructing the 3D trajectory of the vesicle directly from the images.
Three-dimensional face pose estimation has been vastly researched in computer vision, as the face recognition techniques can be utilized in tremendous applications not only regarding human behavior monitoring but also about human-computer interaction. In this paper, we attempted to build a deep-learning model which classifies the pan angle of human head by directly applying convolutional neural network without preliminary image processing, for low-resolution face images. In comparison with the transfer learnings based on pre-trained model, customized simple model consisting of a few convolutional layers and dropout scheme showed an enhanced accuracy in face pan angle prediction.
The movement of vesicle in a living cell includes essential information for understanding the details of the intracellular transport. Although the vesicle tracking method has allowed us to understand precise movement of a single nanoparticle from the physical point of view, the whole cell-level transport has still not been clearly explained with the analysis of only a few representative vesicle movements. In this study, as an initial attempt to gain insight into cell-level vesicle transport, we adopted a computer vision technique to analyze the overall intracellular vesicle transport. In detail, we propose an algorithm to estimate and visualize the ow of the entire endocytic vesicles in terms of convergence and divergence with respect to the geometric cell center. In this algorithm, optical ow of the fluorescent nanoparticles in a living cell is computed using Lucas-Kanade method. Then, the direction of vesicle movement regarding the geometric center of the cell is calculated and mapped to visualize either converging or diverging movement, based on four-quadrant inverse tangent. With this suggested method, it is expected that we can gain insight into cell-level vesicle transport, which can help design and quantitatively evaluate various biomedical applications, including drug delivery.
Internalization of nanoparticles into intracellular area includes key information in biomedical field, such as cell signal pathway and drug delivery. Although the tracking of the individual nanoparticles in the cytoplasmic area has revealed the movement of the target in terms of single-particle level, the whole cell-level study is fundamental in order to efficiently acquire a large dataset of intracellular transport. In the present study, visualization and data analysis methods for understanding the entire cell-level intracellular transport in a living cell is suggested, by applying computer vision techniques to the cell images collected on the camera image sensor. Using the changes in the optical flow of the quantum dot-labeled vesicles for the entire intracellular area, our method showed the possibility of the time series analysis of vesicle movement related to the transport by two different types of molecular motors, dynein and kinesin.
To track volitional motion of a freely moving laboratory mouse, this paper suggests the angle gradient of the turning head as a quantitative criterion, based on markerless snout tracking using high-speed imaging system.
Here, we present a protocol for the identification of differentially expressed genes through RNA sequencing analysis. Starting with FASTQ files from public datasets, this protocol leverages RumBall within a self-contained Docker system. We describe the steps for software setup, obtaining data, read mapping, sample normalization, statistical modeling, and gene ontology enrichment. We then detail procedures for interpreting results with plots and tables. RumBall internally utilizes popular tools, ensuring a comprehensive understanding of the analysis process.
In this paper, a face pose tracking method using adaptive vision switching with a networked camera system is proposed and verified through simulation with a facial computer graphics model. The proposed method improves the pose estimation accuracy of the conventional techniques that use monocular camera. Additionally, adaptive vision switching provides a new pose tracking experience, pose lock-on, which has the potential for object recognition tasks including face recognition under dynamic conditions. Quantitative analysis and tracking demonstration with simulations of the proposed system are conducted and described.
To estimate the direction of vesicle movement near the cellular membrane, time series confocal image data of cells were collected and analyzed by image processing to calculate the active contour and the optical flow.
The shapes of metastatic cancer cells are considered to be relatively different from non-metastatic cancer cells, especially regarding the degree of development of lamellipodia or the pattern of internal organ arrangement. However, understanding the specific pattern of the metastatic cancer cell has just started to emerge. In this paper, based on the generative adversarial network approach, we attempted to generate metastatic cancer cell images using human breast cancer cells where the metastasis-promoting protein, PAR1, is expressed.
The metastatic profile of the cancer cell is considered to be one of the most problematic characteristics from the pathogenic point of view. Because the metastatic cancer cells often show higher mobility compared to the non-metastatic cancer cells, distinguishing the metastatic cancer cell by their images can contain a clue to understanding the molecular process of the cellular metastasis-associated behaviors. In this study, we suggest a deep-learning approach to classify the metastatic cancer cells and non-metastatic cancer cells by their single-cell images acquired by phase-contrast microscopy.
