We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Improved detection and counting performance of microplastics in common carp whole blood by an attention-guided deep learning method
AI summary Read the abstract
Researchers developed an attention-guided deep learning method called Attention-YOLO to improve automated detection and counting of microplastic polystyrene particles in common carp whole blood samples imaged by bright-field microscopy. The system incorporated a channel attention mechanism into the feature extraction network and was trained on a custom dataset of particles in various colors, improving detection accuracy over standard YOLO approaches for high-throughput toxicity studies.
Microplastics are ubiquitous pollutants in the living environment and food chains. Microplastic particles were recently even discovered in human blood for the first time. For high-throughput biodistribution analysis in toxicity studies, we propose a new deep-learning-based method for the automatic identification of polystyrene particles in whole blood. Attention-YOLO helps the network improve detection accuracy by adding the channel attention mechanism to the feature extraction network. We use microscopy to collect a dataset consisting of bright-field images of particles in various colors to train and test a neural network model. Then we use the model to identify and count polystyrene particles in untrained carp blood. The experimental results show that the Attention-YOLO network, when compared to the standard YOLO network, can achieve a better detection performance of microplastics counting in carp blood without adding too many extra parameters, with improvements in the recognition accuracy of polystyrene microspheres (ps-Bs, ps-Rs, and psGs) of 0.2%, 1.1%, and 6%, respectively, and the mean Average Precision (mAP) of 2.4%.
More Papers Like This
Automated detection and identification of microplastics in biota using Nile red and machine learning: validation of an innovative, cost-effective approach.
AI summary Read the abstract
Researchers developed and validated an automated system combining Nile red fluorescent staining with machine learning image analysis to detect and identify microplastics in biological tissue samples. The approach offers a cost-effective and standardizable method for large-scale monitoring of microplastic ingestion across multiple marine species.
MicroDetect-Net (MDN): Leveraging Deep Learning to Detect Microplastics in Clam Blood, a Step Towards Human Blood Analysis
AI summary Read the abstract
Researchers developed MicroDetect-Net, a deep learning model trained to detect microplastics in clam blood, demonstrating a pathway toward automated detection in human blood samples as plastic production exceeds 368 million tons annually and microplastics are found across all environmental and biological matrices.
Detecting Microplastics in Aquatic Bodies Using Object Detection Model
AI summary Read the abstract
Microplastics—tiny plastic particles that pollute water and can work their way up the food chain into the fish and seafood we eat—are hard to track using traditional methods. This research shows that AI-powered image recognition tools (specifically YOLO models, a type of "smart camera" software) can automatically spot and count microplastics in water much faster than manual methods, with a newer version performing better than its predecessor. Faster, more accurate detection means scientists and regulators could monitor plastic pollution more effectively, which is an important step toward understanding and reducing our exposure to these contaminants.
Label-free identification of microplastics in human cells: dark-field microscopy and deep learning study
AI summary Read the abstract
Researchers developed a label-free method to identify microplastics inside living human cells using enhanced dark-field microscopy combined with deep learning, achieving high classification accuracy for polystyrene microparticles differing only in pigmentation.
A Machine Learning Approach To Microplastic Detection And Quantification In Aquatic Environments
AI summary Read the abstract
This study developed a machine learning approach for detecting and quantifying microplastics in aquatic environments, demonstrating that automated image analysis can improve throughput and accuracy compared to manual microscopic counting for environmental monitoring applications.
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.