scholarly journals Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl

2019 ◽  
Vol 16 (12) ◽  
pp. 1247-1253 ◽  
Author(s):  
Juan C. Caicedo ◽  
Allen Goodman ◽  
Kyle W. Karhohs ◽  
Beth A. Cimini ◽  
Jeanelle Ackerman ◽  
...  
Keyword(s):  
Biomedical Applications ◽  
Data Science ◽  
Human Interaction ◽  
Imaging Data ◽  
Cell Nuclei ◽  
Experimental Conditions ◽  
Microscopy Image ◽  
Bioimage Analysis ◽  
Microscopy Images ◽  
Nucleus Segmentation

Abstract Segmenting the nuclei of cells in microscopy images is often the first step in the quantitative analysis of imaging data for biological and biomedical applications. Many bioimage analysis tools can segment nuclei in images but need to be selected and configured for every experiment. The 2018 Data Science Bowl attracted 3,891 teams worldwide to make the first attempt to build a segmentation method that could be applied to any two-dimensional light microscopy image of stained nuclei across experiments, with no human interaction. Top participants in the challenge succeeded in this task, developing deep-learning-based models that identified cell nuclei across many image types and experimental conditions without the need to manually adjust segmentation parameters. This represents an important step toward configuration-free bioimage analysis software tools.

scholarly journals Microscopy cell nuclei segmentation with enhanced U-Net

2020 ◽  
Vol 21 (1) ◽  
Author(s):  
Feixiao Long
Keyword(s):  
Data Science ◽  
State Of The Art ◽  
Cell Nuclei ◽  
Nuclei Segmentation ◽  
Microscopy Image ◽  
Segmentation Algorithms ◽  
Bright Field Microscopy ◽  
The Cost ◽  
Advanced Computing ◽  
Microscopy Image Analysis

Abstract Background Cell nuclei segmentation is a fundamental task in microscopy image analysis, based on which multiple biological related analysis can be performed. Although deep learning (DL) based techniques have achieved state-of-the-art performances in image segmentation tasks, these methods are usually complex and require support of powerful computing resources. In addition, it is impractical to allocate advanced computing resources to each dark- or bright-field microscopy, which is widely employed in vast clinical institutions, considering the cost of medical exams. Thus, it is essential to develop accurate DL based segmentation algorithms working with resources-constraint computing. Results An enhanced, light-weighted U-Net (called U-Net+) with modified encoded branch is proposed to potentially work with low-resources computing. Through strictly controlled experiments, the average IOU and precision of U-Net+ predictions are confirmed to outperform other prevalent competing methods with 1.0% to 3.0% gain on the first stage test set of 2018 Kaggle Data Science Bowl cell nuclei segmentation contest with shorter inference time. Conclusions Our results preliminarily demonstrate the potential of proposed U-Net+ in correctly spotting microscopy cell nuclei with resources-constraint computing.

scholarly journals A Learning-Based Formulation of Parametric Curve Fitting for Bioimage Analysis

2020 ◽  
Author(s):  
Soham Mandal ◽  
Virginie Uhlmann
Keyword(s):  
Data Science ◽  
Image Data ◽  
Parametric Representation ◽  
Cell Nuclei ◽  
Parametric Curve ◽  
Biological Objects ◽  
Domain Expertise ◽  
Bioimage Analysis ◽  
User Friendly ◽  
Parametric Curve Fitting

AbstractParametric curve models are convenient to describe and quantitatively characterize the contour of objects in bioimages. Unfortunately, designing algorithms to fit smoothly such models onto image data classically requires significant domain expertise. Here, we propose a convolutional neural network-based approach to predict a continuous parametric representation of the outline of biological objects. We successfully apply our method on the Kaggle 2018 Data Science Bowl dataset composed of a varied collection of images of cell nuclei. This work is a first step towards user-friendly bioimage analysis tools that extract continuously-defined representations of objects.

scholarly journals A Hierarchical Feature-Based Methodology to Perform Cervical Cancer Classification

2021 ◽  
Vol 11 (9) ◽  
pp. 4091
Author(s):  
Débora N. Diniz ◽  
Mariana T. Rezende ◽  
Andrea G. C. Bianchi ◽  
Claudia M. Carneiro ◽  
Daniela M. Ushizima ◽  
...  
Keyword(s):  
Cervical Cancer ◽  
Pap Smear ◽  
Hierarchical Classification ◽  
Cell Nuclei ◽  
Test Analysis ◽  
Pap Smear Test ◽  
Microscopy Image ◽  
Feature Based ◽  
Cervical Cells ◽  
Number Of Classes

Prevention of cervical cancer could be performed using Pap smear image analysis. This test screens pre-neoplastic changes in the cervical epithelial cells; accurate screening can reduce deaths caused by the disease. Pap smear test analysis is exhaustive and repetitive work performed visually by a cytopathologist. This article proposes a workload-reducing algorithm for cervical cancer detection based on analysis of cell nuclei features within Pap smear images. We investigate eight traditional machine learning methods to perform a hierarchical classification. We propose a hierarchical classification methodology for computer-aided screening of cell lesions, which can recommend fields of view from the microscopy image based on the nuclei detection of cervical cells. We evaluate the performance of several algorithms against the Herlev and CRIC databases, using a varying number of classes during image classification. Results indicate that the hierarchical classification performed best when using Random Forest as the key classifier, particularly when compared with decision trees, k-NN, and the Ridge methods.

scholarly journals Towards pixel-to-pixel deep nucleus detection in microscopy images

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Fuyong Xing ◽  
Yuanpu Xie ◽  
Xiaoshuang Shi ◽  
Pingjun Chen ◽  
Zizhao Zhang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Large Scale ◽  
Deep Neural Networks ◽  
Image Data ◽  
Fine Tuning ◽  
Cell Detection ◽  
Imaging Protocol ◽  
Microscopy Image ◽  
Microscopy Images ◽  
Target Data

Abstract Background Nucleus or cell detection is a fundamental task in microscopy image analysis and supports many other quantitative studies such as object counting, segmentation, tracking, etc. Deep neural networks are emerging as a powerful tool for biomedical image computing; in particular, convolutional neural networks have been widely applied to nucleus/cell detection in microscopy images. However, almost all models are tailored for specific datasets and their applicability to other microscopy image data remains unknown. Some existing studies casually learn and evaluate deep neural networks on multiple microscopy datasets, but there are still several critical, open questions to be addressed. Results We analyze the applicability of deep models specifically for nucleus detection across a wide variety of microscopy image data. More specifically, we present a fully convolutional network-based regression model and extensively evaluate it on large-scale digital pathology and microscopy image datasets, which consist of 23 organs (or cancer diseases) and come from multiple institutions. We demonstrate that for a specific target dataset, training with images from the same types of organs might be usually necessary for nucleus detection. Although the images can be visually similar due to the same staining technique and imaging protocol, deep models learned with images from different organs might not deliver desirable results and would require model fine-tuning to be on a par with those trained with target data. We also observe that training with a mixture of target and other/non-target data does not always mean a higher accuracy of nucleus detection, and it might require proper data manipulation during model training to achieve good performance. Conclusions We conduct a systematic case study on deep models for nucleus detection in a wide variety of microscopy images, aiming to address several important but previously understudied questions. We present and extensively evaluate an end-to-end, pixel-to-pixel fully convolutional regression network and report a few significant findings, some of which might have not been reported in previous studies. The model performance analysis and observations would be helpful to nucleus detection in microscopy images.

scholarly journals Nuclear incorporation of iron during the eukaryotic cell cycle

2016 ◽  
Vol 23 (6) ◽  
pp. 1490-1497 ◽  
Author(s):  
Ian Robinson ◽  
Yang Yang ◽  
Fucai Zhang ◽  
Christophe Lynch ◽  
Mohammed Yusuf ◽  
...  
Keyword(s):  
Cell Cycle ◽  
Fluorescence Microscopy ◽  
Phase Contrast ◽  
Eukaryotic Cell ◽  
Inhomogeneous Distribution ◽  
Cell Nuclei ◽  
X Ray ◽  
Microscopy Images ◽  
Different Levels

Scanning X-ray fluorescence microscopy has been used to probe the distribution of S, P and Fe within cell nuclei. Nuclei, which may have originated at different phases of the cell cycle, are found to show very different levels of Fe present with a strongly inhomogeneous distribution. P and S signals, presumably from DNA and associated nucleosomes, are high and relatively uniform across all the nuclei; these agree with X-ray phase contrast projection microscopy images of the same samples. Possible reasons for the Fe incorporation are discussed.

scholarly journals Topological Segmentation of Time-Varying Functional Connectivity Highlights the Role of Preferred Cortical Circuits

2020 ◽  
Author(s):  
Jacob Billings ◽  
Manish Saggar ◽  
Shella Keilholz ◽  
Giovanni Petri
Keyword(s):  
Functional Connectivity ◽  
Brain Function ◽  
Persistent Homology ◽  
Brain Regions ◽  
Topological Data Analysis ◽  
Time Varying ◽  
Imaging Data ◽  
Experimental Conditions ◽  
Common Time ◽  
Brain Imaging Data

Functional connectivity (FC) and its time-varying analogue (TVFC) leverage brain imaging data to interpret brain function as patterns of coordinating activity among brain regions. While many questions remain regarding the organizing principles through which brain function emerges from multi-regional interactions, advances in the mathematics of Topological Data Analysis (TDA) may provide new insights into the brain’s spontaneous self-organization. One tool from TDA, “persistent homology”, observes the occurrence and the persistence of n-dimensional holes presented in the metric space over a dataset. The occurrence of n-dimensional holes within the TVFC point cloud may denote conserved and preferred routes of information flow among brain regions. In the present study, we compare the use of persistence homology versus more traditional TVFC metrics at the task of segmenting brain states that differ across a common time-series of experimental conditions. We find that the structures identified by persistence homology more accurately segment the stimuli, more accurately segment volunteer performance during experimentally defined tasks, and generalize better across volunteers. Finally, we present empirical and theoretical observations that interpret brain function as a topological space defined by cyclic and interlinked motifs among distributed brain regions, especially, the attention networks.

scholarly journals Polarizer-Free AOTF-Based SWIR Hyperspectral Imaging for Biomedical Applications

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4439
Author(s):  
Vladislav Batshev ◽  
Alexander Machikhin ◽  
Grigoriy Martynov ◽  
Vitold Pozhar ◽  
Sergey Boritko ◽  
...  
Keyword(s):  
Hyperspectral Imaging ◽  
Biomedical Applications ◽  
Cost Effective ◽  
Short Wave ◽  
Tunable Filter ◽  
Quality Analysis ◽  
Imaging Data ◽  
Image Quality Analysis ◽  
Data Volume ◽  
Integrate Design

Optical biomedical imaging in short wave infrared (SWIR) range within 0.9–1.7 μm is a rapidly developing technique. For this reason, there is an increasing interest in cost-effective and robust hardware for hyperspectral imaging data acquisition in this range. Tunable-filter-based solutions are of particular interest as they provide image processing flexibility and effectiveness in terms of collected data volume. Acousto-optical tunable filters (AOTFs) provide a unique set of features necessary for high-quality SWIR hyperspectral imaging. In this paper, we discuss a polarizer-free configuration of an imaging AOTF that provides a compact and easy-to-integrate design of the whole imager. We have carried out image quality analysis of this system, assembled it and validated its efficiency through multiple experiments. The developed system can be helpful in many hyperspectral applications including biomedical analyses.

Sign in / Sign up

Export Citation Format

Share Document