We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Coherent lensless diffraction imaging via multicore fiber for label-efficient microplastics characteristic discrimination
AI summary Read the abstract
Researchers developed a lightweight lensless imaging method using multicore fiber bundles combined with self-supervised machine learning to rapidly discriminate damage states of microplastics, enabling in situ assessment of microplastic deformation status that is difficult to achieve with conventional benchtop microscopy.
The widespread exposure of microplastics (MPs) to environmental and biological systems makes the rapid identification of their damage status a critical task. This deformation influences how MPs migrate, degrade, and interact with organisms, thereby shaping their environmental fate and ecological risk. However, traditional bright-field microscopy suffers from degraded performance under defocused and low-contrast conditions, and benchtop systems are also difficult to deploy in situ in confined spaces. To address these challenges, we propose a lightweight method combining multicore fiber bundle-based coherent defocused imaging with self-supervised representation learning. When only an extremely small number of annotations are provided, semi-supervised constraints, including weighted updates and soft penalties are introduced to enhance cluster-class alignment. This scheme eliminates the need for holographic reconstruction and features a thin, flexible probe, making it suitable for in-situ and online detection in confined environments. The results demonstrate that combining physically enhanced coherent imaging with self-supervised features enables robust differentiation between damaged and undamaged MPs at low annotation cost, and provides a feasible path for on-site deployment.
More Papers Like This
Fast Mueller matrix digital holography with anisotropy-informed machine learning for automated non-destructive microplastic characterization
AI summary Read the abstract
Scientists developed a fast, light-based scanning method that can detect and identify different types of microplastics without damaging or altering the samples, using a smart camera system paired with machine learning. It correctly classified microplastics 96.4% of the time, which could lead to better tools for tracking these tiny pollutants in our water, food, and environment, an important step since microplastics are increasingly linked to health concerns.
Lensless shadow microscopy-based shortcut analysis strategy for fast quantification of microplastic fibers released to water
AI summary Read the abstract
Researchers developed a rapid analysis system for quantifying microplastic fibers in water using a high-resolution lensless shadow microscope combined with deep learning algorithms. The approach replaces the slow manual counting process with automated imaging on a chip, significantly increasing both speed and accuracy. The study offers a practical tool for routine monitoring of microplastic fiber pollution in water treatment and environmental settings.
Material analysis with polarization holography and machine learning
AI summary Read the abstract
Researchers developed a polarization holographic imaging system combined with machine learning to identify different materials, demonstrating the approach on microplastic identification. This novel optical method could become a fast, non-destructive tool for classifying microplastics in environmental samples.
Deep Learning for Microplastic Detection and Characterization Across Imaging, Spectroscopic, and Multimodal Platforms: Advances, Validation Gaps, and Deployment Challenges
AI summary Read the abstract
This review summarizes existing research on using computer programs called deep learning to detect and identify microplastics using imaging and light-based techniques. It finds these tools show progress but face challenges including limited data, inconsistent results across real-world samples, and difficulty working in portable field devices.
Smart polarization and spectroscopic holography for real-time microplastics identification
AI summary Read the abstract
Researchers developed a new optical imaging system called SPLASH that simultaneously captures polarization, holographic, and texture data from tiny particles — without needing a traditional spectrometer — and used machine learning to identify different types of microplastics with high accuracy. This approach could enable faster, more practical real-time monitoring of microplastic pollution in water.
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.