Dataset Information

Object detection networks and augmented reality for cellular detection in fluorescence microscopy.

ABSTRACT: Object detection networks are high-performance algorithms famously applied to the task of identifying and localizing objects in photography images. We demonstrate their application for the classification and localization of cells in fluorescence microscopy by benchmarking four leading object detection algorithms across multiple challenging 2D microscopy datasets. Furthermore we develop and demonstrate an algorithm that can localize and image cells in 3D, in close to real time, at the microscope using widely available and inexpensive hardware. Furthermore, we exploit the fast processing of these networks and develop a simple and effective augmented reality (AR) system for fluorescence microscopy systems using a display screen and back-projection onto the eyepiece. We show that it is possible to achieve very high classification accuracy using datasets with as few as 26 images present. Using our approach, it is possible for relatively nonskilled users to automate detection of cell classes with a variety of appearances and enable new avenues for automation of fluorescence microscopy acquisition pipelines.

SUBMITTER: Waithe D

PROVIDER: S-EPMC7659718 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Object detection networks and augmented reality for cellular detection in fluorescence microscopy.

Waithe Dominic D Brown Jill M JM Reglinski Katharina K Diez-Sevilla Isabel I Roberts David D Eggeling Christian C

The Journal of cell biology 20201001 10

Object detection networks are high-performance algorithms famously applied to the task of identifying and localizing objects in photography images. We demonstrate their application for the classification and localization of cells in fluorescence microscopy by benchmarking four leading object detection algorithms across multiple challenging 2D microscopy datasets. Furthermore we develop and demonstrate an algorithm that can localize and image cells in 3D, in close to real time, at the microscope ...[more]

PMID: 32854116

Similar Datasets

Project description:Background: Educators often face difficulties in explaining abstract concepts such as vectors. During the ongoing coronavirus disease 2019 (COVID-19) pandemic, fully online classes have also caused additional challenges to using conventional teaching methods. To explain a vector concept of more than 2 dimensions, visualization becomes a problem. Although Microsoft PowerPoint can integrate animation, the illustration is still in 2-dimensions. Augmented reality (AR) technology is recommended to aid educators and students in teaching-learning vectors, namely via a vector personal computer augmented reality system (VPCAR), to fulfil the demand for tools to support the learning and teaching of vectors. Methods: A PC learning module for vectors was developed in a 3-dimensional coordinate system by using AR technology. Purposive sampling was applied to get feedback from educators and students in Malaysia through an online survey. The supportiveness of using VPCAR based on six items (attractiveness, easiness, visualization, conceptual understanding, inspiration and helpfulness) was recorded on 5-points Likert-type scales. Findings are presented descriptively and graphically. Results: Surprisingly, both students and educators adapted to the new technology easily and provided significant positive feedback that showed a left-skewed and J-shaped distribution for each measurement item, respectively. The distributions were proven significantly different among the students and educators, where supportive level result of educators was higher than students. This study introduced a PC learning module other than mobile apps as students mostly use laptops to attend online class and educators also engage other IT tools in their teaching. Conclusions: Based on these findings, VPCAR provides a good prospect in supporting educators and students during their online teaching-learning process. However, the findings may not be generalizable to all students and educators in Malaysia as purposive sampling was applied. Further studies may focus on government-funded schools using the newly developed VPCAR system, which is the novelty of this study.

Dataset Information

Object detection networks and augmented reality for cellular detection in fluorescence microscopy.

Publications

Object detection networks and augmented reality for cellular detection in fluorescence microscopy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets