We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Keeping a sharp Weka eye on tiny plastics – the usability and perspective of Fiji image analysis tool for microplastics identification in environmental samples
AI summary Read the abstract
Researchers tested the Trainable Weka Segmentation tool in the free image analysis software Fiji as an affordable method for detecting and classifying microplastics in environmental samples using machine learning. The approach shows promise as a lower-cost alternative to expensive spectroscopic identification for initial screening of microplastic samples.
The ubiquitous distribution of microplastics (MPs) in the environment is of rising scientific and civil concern. As a consequence, the number of studies on MPs has been growing rapidly in the last decades. One particularly important area of these research initiatives implies developing fast, relatively simple, and effective techniques for MPs detection as an alternative to costly and complex spectroscopic methods. One potential option based on image analysis is the Trainable Weka Segmentation (TWS). This Fiji software plugin uses machine learning algorithms to compute segmentation based on pixel classification. The primary advantage of TWS for MPs identification lies in the ability to divide the image into two or more groups by using the differences in pixel contrast, intensity, and texture of the selected regions of interest. Thereby, it is possible to detect specific shapes and structures (e.g., fibers, fragments) based on selected areas. TWS has been tested on images of zooplankton samples from regions potentially contaminated by MPs, and an image stack of biota samples spiked with MPs was used as a referential source for a model. Used primarily to compensate for inefficient digestion of organic material, TWS allowed removing regions of zooplankton remains from the image. Moreover, TWS aided in the identification and counting of potential MP particles. However, given the «automated» nature of such a tool, the applicability of TWS for large-scale MPs analysis should be repeatedly tested on artificial samples spiked with MPs. Complementary cross-checking using spectroscopic methods will further minimize the risk of false-positive results when applied on environmental samples. On the basis of further experiments, TWS has the potential to allow for quick and automated analysis of i) the presence of MPs in samples; ii) their numerical abundance; iii) MPs shapes and sizes. Also see: https://micro2022.sciencesconf.org/426388/document
More Papers Like This
Weka Model for automated microplastics segmentation in ImageJ
AI summary Read the abstract
This is a machine-learning model file (Weka segmentation for ImageJ) used to automate the identification of microplastic particles in microscope images — a software tool rather than a primary research article.
A new approach for routine and accelerated processing of microplastics using MPScanTool plugin for ImageJ
AI summary Read the abstract
Researchers developed a flatbed scanner-based system paired with open-source image analysis software to speed up the counting, measuring, and classification of microplastics in samples, reducing the time required compared to manual microscopy. The affordable system makes high-throughput microplastic analysis more accessible to laboratories with limited resources.
A Handy Open-Source Application Based on Computer Vision and Machine Learning Algorithms to Count and Classify Microplastics
AI summary Read the abstract
An open-source computer vision application was developed to automatically count and classify microplastics in microscopy images, achieving accuracy comparable to manual counting while processing samples orders of magnitude faster, offering the scientific community a free tool to reduce the bottleneck of tedious visual microplastic enumeration.
Detection of Microplastics Using Machine Learning
AI summary Read the abstract
Researchers reviewed and demonstrated machine learning approaches for detecting and classifying microplastics in environmental samples, finding that automated image analysis and spectral classification methods can improve the speed and accuracy of microplastic monitoring compared to manual methods.
Artificial intelligence in analysis of microplastic pollutants
AI summary Read the abstract
This Croatian thesis reviews artificial intelligence methods for analyzing and classifying microplastic pollutants. The author examines how machine learning and image analysis tools can improve the speed and accuracy of microplastic detection and characterization in environmental samples.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.