Article
Environmental Sciences
Bin Shi, Medhavi Patel, Dian Yu, Jihui Yan, Zhengyu Li, David Petriw, Thomas Pruyn, Kelsey Smyth, Elodie Passeport, R. J. Dwayne Miller, Jane Y. Howe
Summary: This paper presents a study on the quantification and classification of microplastics using scanning electron microscopy and deep learning methods. The use of deep learning models allows for fast and accurate segmentation and classification of microplastics, which is cheaper and more efficient compared to traditional methods. This research is important for monitoring and evaluating microplastic pollution and investigating potential health risks.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Computer Science, Artificial Intelligence
Anusha Aswath, Ahmad Alsahaf, Ben N. G. Giepmans, George Azzopardi
Summary: This review summarizes the progress of deep learning-based segmentation techniques in large-scale cellular electron microscopy (EM) over the past six years. It discusses the application of deep learning in EM segmentation, including supervised, unsupervised, and self-supervised learning methods, and examines their adaptability in segmenting cellular and sub-cellular structures. Evaluation measures for benchmarking EM datasets in various segmentation tasks are also provided. Finally, the current trends and future prospects of EM segmentation with large-scale models and unlabeled images are discussed.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Computer Science, Artificial Intelligence
Pushpak Pati, Guillaume Jaume, Zeineb Ayadi, Kevin Thandiackal, Behzad Bozorgtabar, Maria Gabrani, Orcun Goksel
Summary: This study proposes a weakly-supervised method called WholeSIGHT, which can simultaneously segment and classify WSIs of arbitrary shapes and sizes. It achieves state-of-the-art weakly-supervised segmentation performance on three public prostate cancer WSI datasets.
MEDICAL IMAGE ANALYSIS
(2023)
Review
Materials Science, Multidisciplinary
Luther W. McDonald IV, Kari Sentz, Alex Hagen, Brandon W. Chung, Cody A. Nizinski, Ian J. Schwerdt, Alexa Hanson, Scott Donald, Richard Clark, Glenn Sjoden, Reid Porter, Matthew T. Athon, Tolga Tasdizen, Vincent Noel, Samuel M. Webb, Arjen Van Veelen, Sarah M. Hickam, Cuong Ly
Summary: This article introduces a method for identifying the processing history of unknown nuclear materials in nuclear forensics using particle morphology. By measuring the morphology of solid materials using scanning electron microscopes and combining robust image analysis and classification methods, morphology analysis can be conducted quickly and accurately. This method can be applied to intercepted nuclear materials and the detection of trace amounts of nuclear materials.
JOURNAL OF NUCLEAR MATERIALS
(2024)
Article
Microscopy
Cameron G. Bell, Kevin P. Treder, Judy S. Kim, Manfred E. Schuster, Angus Kirkland, Thomas J. A. Slater
Summary: This study presents a trainable segmentation method for accurately segmenting inorganic nanoparticles from transmission electron microscope images. The method achieves a balance between accuracy and training time, outperforming global and local thresholding methods and neural networks. The study also quantitatively investigates the effectiveness of the components of the trainable segmentation method, namely filter kernels and classifiers, and identifies the most accurate classifiers for different data types in ParticleSpy.
JOURNAL OF MICROSCOPY
(2022)
Article
Computer Science, Artificial Intelligence
Krishna Chaitanya, Ertunc Erdil, Neerav Karani, Ender Konukoglu
Summary: Supervised deep learning methods require large labeled datasets for accurate medical image segmentation. This paper proposes a local contrastive loss-based approach that utilizes pseudo-labels of unlabeled images and limited annotated images to learn pixel-level features for segmentation. Experimental results on three public medical datasets demonstrate the substantial improvement achieved by the proposed method.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Multidisciplinary Sciences
Rama Krishnan Vasudevan, Sai Mani Valleti, Maxim Ziatdinov, Gerd Duscher, Suhas Somnath
Summary: Major advancements in various fields have relied on microscopy techniques, but there are still significant challenges in processing and analyzing the acquired datasets. The pycroscopy ecosystem introduces a common data model and leverages Python-based packages to accelerate analysis and visualization, enabling the creation of reproducible workflows for microscopy data.
ADVANCED THEORY AND SIMULATIONS
(2023)
Article
Chemistry, Analytical
Elena M. Hoppener, M. Sadegh Shahmohammadi, Luke A. Parker, Sieger Henke, Jan Harm Urbanus
Summary: Microplastics are a growing environmental and toxicological concern, and their scale of the problem is not fully known. This study demonstrated the utility of SEM paired with CL in identifying and characterizing different types of microplastics with detailed spatial and chemical resolution.
Article
Computer Science, Artificial Intelligence
Krishna Chaitanya, Neerav Karani, Christian F. Baumgartner, Ertunc Erdil, Anton Becker, Olivio Donati, Ender Konukoglu
Summary: Supervised learning-based segmentation methods typically require a large number of annotated training data, which is challenging in medical applications. This work presents a novel task-driven data augmentation method that significantly outperforms other approaches in limited annotation settings.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Artificial Intelligence
Yu Hua, Xin Shu, Zizhou Wang, Lei Zhang
Summary: This paper proposes a semi-supervised method that narrows the gap between semi-supervised and fully supervised models by utilizing unlabeled data and establishing contrastive relationships between feature representation vectors through supervised contrastive learning. It overcomes data misuse and underutilization in semi-supervised frameworks, enhancing performance.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2022)
Article
Biology
Arnaud Deleruyelle, Cristian Versari, John Klein
Summary: This study introduces a neural pipeline for micro-capsule image segmentation, which utilizes synthetic or indirect supervision to improve model generalization. Experimental results demonstrate significant accuracy improvement, indicating the potential of replacing human annotations.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Interdisciplinary Applications
Zhu Meng, Zhicheng Zhao, Bingyang Li, Fei Su, Limei Guo
Summary: This study introduces a new cervical histopathology image dataset for automated precancerous diagnosis and demonstrates the feasibility of computer aided diagnosis through extensive experiments and methods. The proposed weakly supervised ensemble algorithm shows effectiveness in improving performance.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Computer Science, Artificial Intelligence
Guoyu Lin, Zhentai Zhang, Kaixing Long, Yiwen Zhang, Yanmeng Lu, Jian Geng, Zhitao Zhou, Qianjin Feng, Lijun Lu, Lei Cao
Summary: Our proposed GCLR method achieves state-of-the-art results in the segmentation of GFB in glomerular TEM images through self-supervised representation learning and outperforms other self-supervised pre-training methods.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Ming Yan, Yewang Chen, Yi Chen, Guoyao Zeng, Xiaoliang Hu, Jixiang Du
Summary: This paper proposes a weakly supervised image segmentation algorithm based on Density Peaks (DPeaks) clustering algorithm. By training decision curves on a few sample images, the algorithm is able to effectively identify sparse regions in imbalanced images and recognize relatively small objects. Experimental results demonstrate the good performance of the proposed algorithm on imbalanced image datasets.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Feng Gao, Minhao Hu, Min-Er Zhong, Shixiang Feng, Xuwei Tian, Xiaochun Meng, Ma-yi-di-li Ni-jia-ti, Zeping Huang, Minyi Lv, Tao Song, Xiaofan Zhang, Xiaoguang Zou, Xiaojian Wu
Summary: This paper proposes a novel weakly- and semi-supervised framework named SOUSA, which aims to learn from a small set of sparse annotated data and a large amount of unlabeled data. Extensive experiments demonstrate the robustness and generalization ability of the proposed method on multiple datasets.
MEDICAL IMAGE ANALYSIS
(2022)
Article
Computer Science, Interdisciplinary Applications
A. Meilan-Vila, M. Francisco-Fernandez, R. M. Crujeiras
Summary: This work proposes testing procedures for assessing a parametric regression model with a circular response and an R-d-valued covariate. The test statistics are based on comparing a parametric circular regression estimator and a nonparametric one using circular distance. Two bootstrap procedures for calibrating the tests in practice are also presented. The finite sample performance of the tests in different scenarios is analyzed by simulations and illustrated with real data examples.
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
(2022)
Article
Environmental Sciences
Juan A. Vallejo, Noelia Trigo-Tasende, Soraya Rumbo-Feal, Kelly Conde-Perez, Angel Lopez-Oriona, Ines Barbeito, Manuel Vaamonde, Javier Tarrio-Saavedra, Ruben Reif, Susana Ladra, Bruno K. Rodino-Janeiro, Mohammed Nasser-Ali, Angeles Cid, Maria Veiga, Anton Acevedo, Carlos Lamora, German Bou, Ricardo Cao, Margarita Poza
Summary: The quantification of SARS-CoV-2 RNA load in wastewater has emerged as a useful tool to monitor COVID-19 outbreaks in communities. This approach was implemented in the metropolitan area of A Coruna, where wastewater analysis helped track the epidemic dynamics. Regression models allowed estimation of the number of infected individuals and served as an effective early warning tool for predicting outbreaks in the municipality.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Environmental Sciences
Luis Carral, M. Isabel Lamas-Galdo, Jose Luis Mier Buenhombre, Juan Jose Cartelle Barros, Salvador Naya, Javier Tarrio-Saavedra
Summary: This study suggests an innovative approach to convert waste from bivalve mollusc production into artificial reefs, creating marine ecosystems in a sustainable way. The physical and chemical characteristics of the waste were analyzed, and specific concrete mixtures with bivalve shells were proposed.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Mathematics
Jorge R. Sosa Donoso, Miguel Flores, Salvador Naya, Javier Tarrio-Saavedra
Summary: This work presents a methodology for detecting outliers in functional data that considers both their shape and magnitude. The Local Correlation Integral (LOCI) method, a multivariate anomaly detection technique, has been extended and adapted for functional data using distance calculations in Hilbert spaces. The methodology has been validated through simulation studies and application to real data, showing good performance in scenarios with inter-curve dependence, particularly when outliers are due to curve magnitudes. Results are further supported by the successful application of the methodology to a meteorological database, outperforming other competitive methods.
Article
Multidisciplinary Sciences
Francisco J. Rodriguez-Dopico, R. J. C. Carbas, Catarina S. P. Borges, J. Tarrio-Saavedra, L. F. M. da Silva, A. Alvarez Garcia
Summary: Adhesive technology in the shipbuilding industry is not as advanced as in other industries due to the lack of specific knowledge that guarantees durability of bonded joints in optimal conditions throughout a ship's life cycle. This study simulates a marine-like environment in the laboratory to characterize seawater absorption behavior and its impact on the mechanical, thermal, and chemical properties of the adhesive. Gravimetric tests are used to determine seawater ingress and Fick's Law is applied to study the absorption process. Additionally, differential scanning calorimetry (DSC) and Fourier transform infrared spectroscopy (FTIR) are used to analyze thermal behavior and chemical degradation, respectively.
Article
Multidisciplinary Sciences
Antonio Meneses, Salvador Naya, Mario Francisco-Fernandez, Jorge Lopez-Beceiro, Carlos Gracia-Fernandez, Javier Tarrio-Saavedra
Summary: The TTS package, developed in R software, applies the Time Temperature Superposition (TTS) principle to predict the mechanical properties of viscoelastic materials at different observation times/frequencies. It utilizes the concept of shifting data curves obtained at different temperatures to estimate properties beyond the experimental range. The TTS package provides free computational tools to obtain master curves and implements a method to obtain shift factors and master curves using a non-parametric approach.
Article
Multidisciplinary Sciences
Luis Carral, Javier Tarrio-Saavedra, Juan Jose Cartelle Barros, Carolina Camba Fabal, Alberto Ramil, Carlos Alvarez-Feal
Summary: The installation of artificial reefs enhances marine ecosystems but also modifies them. The sustainability of the ecosystem requires not only the manufacture and installation of artificial reefs but also the analysis of their impact on the ecosystem and the potential return to its initial state. This paper presents a design for artificial reefs with limited functional life, achieved by treating the base material, concrete, to limit its useful life to one generation.
Article
Biology
Ruben Fernandez-Casal, Sergio Castillo-Paez, Mario Francisco-Fernandez
Summary: A nonparametric procedure is proposed in this article to estimate the conditional probability that a nonstationary geostatistical process exceeds a certain threshold value. The method combines conditional simulation techniques with nonparametric estimations of the trend and the variability, using a nonparametric local linear estimator with a bandwidth matrix selected using a method that takes spatial dependence into account to estimate the trend and modeling the variability by estimating the conditional variance and the variogram from corrected residuals to avoid biases. The proposed method allows for estimates of the conditional exceedance risk in non-observed spatial locations. The performance of the method is analyzed through simulations and illustrated with the application to a real data set of precipitations in the USA.
JOURNAL OF AGRICULTURAL BIOLOGICAL AND ENVIRONMENTAL STATISTICS
(2023)
Article
Multidisciplinary Sciences
Miguel Flores, Angel Llambo, Danilo Loza, Salvador Naya, Javier Tarrio-Saavedra
Summary: This study aims to predict the irrigation needs of corn crops in different regions of Ecuador, which is a fundamental food for the country's economy and other countries in the Andean area. Regression models based on Functional Data Analysis (FDA) are proposed to predict rainfall based on functional covariates such as temperature and wind speed. The models show high goodness of fit and practical utility. The study also demonstrates the application of FDA exploratory analysis and outlier detection techniques in rainfall prediction studies.
Article
Environmental Sciences
Noelia Trigo-Tasende, Juan A. Vallejo, Soraya Rumbo-Feal, Kelly Conde-Perez, Mohammed Nasser-Ali, Javier Tarrio-Saavedra, Ines Barbeito, Fernando Lamelo, Ricardo Cao, Susana Ladra, German Bou, Margarita Poza
Summary: Wastewater-based epidemiology (WBE) is an effective tool for monitoring COVID-19 and other infectious diseases. A study conducted in nursing homes showed that an increase in SARS-CoV-2 viral load in wastewater served as an early warning system for COVID-19 outbreaks, and demonstrated the effectiveness of vaccination campaigns. WBE is a cost-effective strategy that should be implemented in all cities.
Article
Environmental Sciences
Noelia Trigo-Tasende, Juan A. Vallejo, Soraya Rumbo-Feal, Kelly Conde-Perez, Manuel Vaamonde, Angel Lopez-Oriona, Ines Barbeito, Mohammed Nasser-Ali, Ruben Reif, Bruno K. Rodino-Janeiro, Elisa Fernandez-Alvarez, Iago Iglesias-Corras, Borja Freire, Javier Tarrio-Saavedra, Laura Tomas, Pilar Gallego-Garcia, David Posada, German Bou, Ignacio Lopez-de-Ullibarri, Ricardo Cao, Susana Ladra, Margarita Poza
Summary: The wastewater-based epidemiology program COVIDBENS in A Coruna, Spain, monitored viral load and detected SARS-CoV-2 mutations in wastewater using RT-qPCR and Illumina sequencing. It successfully predicted community outbreaks and identified new variants, providing early warning to local authorities and health managers.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Public, Environmental & Occupational Health
Paloma Noelia Trigo-Tasende, Manuel Vaamonde, Kelly Conde-Perez, Angel Lopez-Oriona, Elisa F. Alvarez, Borja Freire, Mohammed Nasser-Ali, Ines Barbeito, Soraya Rumbo-Feal, Ruben Reif, Bruno K. Rodinos, Jose Parama, Laura Tomas, Pili Gallego, German Bou, Javier Tarrio-Saavedra, Iago I. Corras, David Posada, Ignacio Lopez de Ulibarri, Juan A. Vallejo, Susana Ladra, Ricardo Cao, Margarita Poza
REVISTA DE SALUD AMBIENTAL
(2022)