scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Semi-automated tracking of muscle satellite cells in brightfield microscopy video

TL;DR: A semi-automated approach for satellite cell tracking on myofibers consisting of registration with illumination correction, background subtraction and particle filtering is proposed and initial experimental results show the effectiveness of the approach.
Abstract: Muscle satellite cells, also known as myogenic precursor cells, are the dedicated stem cells responsible for postnatal skeletal muscle growth, repair, and hypertrophy. Biological studies aimed at describing satellite cell activity on their host myofiber using timelapse light microscopy enable qualitative study, but high-throughput automatic tracking of satellite cells translocating on myofibers is very difficult due to their complex motion across the three-dimensional surface of myofibers and the lack of discriminating cell features. Other complicating factors include inhomogeneous illumination, fixed focal plane, low contrast, and stage motion. We propose a semi-automated approach for satellite cell tracking on myofibers consisting of registration with illumination correction, background subtraction and particle filtering. Initial experimental results show the effectiveness of the approach.
Citations
More filters
Journal ArticleDOI
TL;DR: A fast and accurate approach for automatic mitosis detection from histopathological images is proposed by restricting the scales with the maximization of relative-entropy between the cells and the background to result in precise cell segmentation.
Abstract: Histopathological grading of cancer not only offers an insight to the patients’ prognosis but also helps in making individual treatment plans. Mitosis counts in histopathological slides play a crucial role for invasive breast cancer grading using the Nottingham grading system. Pathologists perform this grading by manual examinations of a few thousand images for each patient. Hence, finding the mitotic figures from these images is a tedious job and also prone to observer variability due to variations in the appearances of the mitotic cells. We propose a fast and accurate approach for automatic mitosis detection from histopathological images. We employ area morphological scale space for cell segmentation. The scale space is constructed in a novel manner by restricting the scales with the maximization of relative-entropy between the cells and the background. This results in precise cell segmentation. The segmented cells are classified in mitotic and non-mitotic category using the random forest classifier. Experiments show at least 12% improvement in $F_{1}$ score on more than 450 histopathological images at $40\times $ magnification.

62 citations


Additional excerpts

  • ...For background subtraction based cell detection, see [13]....

    [...]

Proceedings ArticleDOI
14 Dec 2014
TL;DR: This work proposes a fast and accurate approach for automatic mitosis detection from histopathological images using an enhanced random forest classifier with weighted random trees.
Abstract: Histopathological grading of cancer is a measure of the cell appearance in malignant neoplasms. Grading offers an insight to the growth of the cancer and helps in developing individual treatment plans. The Nottingham grading system [12], well known method for invasive breast cancer grading, primarily relies on the mitosis count in histopathological slides. Pathologists manually identify mitotic figures from a few thousand slide images for each patient to determine the grade of the cancer. Mitotic figures are hard to identify as the appearance of the mitotic cells change at different phases of mitosis. So, the manual cancer grading is not only a tedious job but also prone to observer variability. We propose a fast and accurate approach for automatic mitosis detection from histopathological images using an enhanced random forest classifier with weighted random trees. The random trees are assigned a tree penalty and a forest penalty depending on their classification performance at the training phase. The weight of a tree is calculated based on these penalties. The forest is trained through regeneration of population from weighted trees. The input data is classified based on weighted voting from the random trees after several populations. Experiments show at least 11 percent improvement in F1 score on more than 450 histopathological images at ×40 magnification.

7 citations


Additional excerpts

  • ...For background subtraction based cell detection, see [8]....

    [...]

Book ChapterDOI
TL;DR: Three protocols developed in the group for quantitatively analyzing satellite cell motility over time are described, which allow identification and longitudinal evaluation of individual cells over time and quantification of variations in motility due to intrinsic or extrinsic factors.
Abstract: Motility and/or chemotaxis of satellite cells has been suggested or observed in multiple in vitro and in vivo contexts. Satellite cell motility also affects the efficiency of muscle regeneration, particularly in the context of engrafted exogenous cells. Consequently, there is keen interest in determining what cell-autonomous and environmental factors influence satellite cell motility and chemotaxis in vitro and in vivo. In addition, the ability of activated satellite cells to relocate in vivo would suggest that they must be able to invade and transit through the extracellular matrix (ECM), which is supported by studies in which alteration or addition of matrix metalloprotease (MMP) activity enhanced the spread of engrafted satellite cells. However, despite its potential importance, analysis of satellite cell motility or invasion quantitatively even in an in vitro setting can be difficult; one of the most powerful techniques for overcoming these difficulties is timelapse microscopy. Identification and longitudinal evaluation of individual cells over time permits not only quantification of variations in motility due to intrinsic or extrinsic factors, it permits observation and analysis of other (frequently unsuspected) cellular activities as well. We describe here three protocols developed in our group for quantitatively analyzing satellite cell motility over time in two dimensions on purified ECM substrates, in three dimensions on a living myofiber, and in three dimensions through an artificial matrix.

1 citations

01 Jan 2014
TL;DR: This article surveys the recent literature in the area of computer vision based automated cell tracking and discusses the latest trends and successes in the development and introduction of automated celltracking techniques and systems.
Abstract: With the advent of highly advanced optics and imaging system, currently biological research has reached a stage where scientists can study biological entities and processes at molecular and cellular-level in real time. However, a single experiment consists of hundreds and thousands of parameters to be recorded and a large population of microscopic objects to be tracked. Thus, making manual inspection of such events practically impossible. This calls for an approach to computer-vision based automated tracking and monitoring of cells in biological experiments. This technology promises to revolutionize the research in cellular biology and medical science which includes discovery of diseases by tracking the process in cells, development of therapy and drugs and the study of microscopic biological elements. This article surveys the recent literature in the area of computer vision based automated cell tracking. It discusses the latest trends and successes in the development and introduction of automated cell tracking techniques and systems.