Article
Biology
Esteban Andres Sanchez-Jaramillo, Luz Elena Gasca-Lozano, Jose Maria Vera-Cruz, Luis Daniel Hernandez-Ortega, Adriana Maria Salazar-Montes
Summary: The article introduces a method of using computer-assisted fast automated analysis to evaluate the degree of kidney fibrosis in animal models. This method is faster and easier than traditional image-by-image analysis, helping researchers to conduct studies more efficiently and discover new treatments.
Article
Multidisciplinary Sciences
Weijia Fan, Yudi Sang, Hanyue Zhou, Jiayu Xiao, Zhaoyang Fan, Dan Ruan
Summary: Analysis of vessel morphology is crucial in evaluating intracranial atherosclerosis disease (ICAD), and magnetic resonance vessel wall imaging (VWI) has been introduced to image ICAD and characterize atherosclerotic lesions. This study aims to investigate the feasibility of inferring vessel location directly from VWI by combining an atlas-based method with a deep learning network. The proposed pipeline shows clinically feasible performance in localizing intracranial vessels, demonstrating the potential of VWI in vessel morphology analysis.
SCIENTIFIC REPORTS
(2022)
Article
Neurosciences
Wenjing Xu, Xiong Yang, Yikang Li, Guihua Jiang, Sen Jia, Zhenhuan Gong, Yufei Mao, Shuheng Zhang, Yanqun Teng, Jiayu Zhu, Qiang He, Liwen Wan, Dong Liang, Ye Li, Zhanli Hu, Hairong Zheng, Xin Liu, Na Zhang
Summary: A deep learning-based automatic segmentation method for arterial vessel walls and plaques was developed and evaluated in this study. The method, using the VWISegNet model, achieved good segmentation results and outperformed traditional methods. The application of this method facilitates the quantification of arterial morphology.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Computer Science, Interdisciplinary Applications
Maikel M. Ronnau, Tatiana W. Lepper, Luara N. Amaral, Pantelis Rados, Manuel M. Oliveira
Summary: By training a CNN on AgNOR-stained cell images of oral mucosa, our method successfully segments and counts nuclei and AgNORs, achieving performance levels similar to human experts.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Medicine, General & Internal
Sricharan S. Veeturi, Nandor K. Pinter, Andre Monteiro, Ammad A. Baig, Hamid H. Rai, Muhammad Waqas, Adnan H. Siddiqui, Hamidreza Rajabzadeh-Oghaz, Vincent M. Tutino
Summary: The study developed and validated a tool for visualization and objective identification of VWE regions in contrast-enhanced magnetic resonance imaging, aiming to improve the reliability and consistency of IA evaluation.
Article
Radiology, Nuclear Medicine & Medical Imaging
Na Zhang, Xinfeng Liu, Jiayu Xiao, Shlee S. Song, Zhaoyang Fan
Summary: The study aimed to evaluate the reliability of 3D whole-brain VWI in quantifying plaque morphology in patients with ICAD, and found that whole-brain VWI showed excellent interobserver/intraobserver agreement, interscan repeatability, and agreement with 2D TSE in all morphologic measurements.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2021)
Article
Computer Science, Artificial Intelligence
Fiona Milano, Anik Chevrier, Gregory De Crescenzo, Marc Lavertu
Summary: This study proposes a definition of homogeneity and an algorithm called MASQH for its quantification, which is simple, robust, and easy to use. The performance and reliability of the method are demonstrated through three case studies. By quantifying homogeneity, the MASQH method may help compare different studies and demonstrate the impact of homogeneity in various fields.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Hanyue Zhou, Jiayu Xiao, Siddarth Ganesh, Alexander Lerner, Dan Ruan, Zhaoyang Fan
Summary: An automated processing pipeline for quantitative plaque assessment based on 3D magnetic resonance vessel wall imaging (VWI) has been developed and evaluated. The VWI-APP was found to be an accurate and efficient approach for intracranial atherosclerotic plaque quantification.
Article
Radiology, Nuclear Medicine & Medical Imaging
Arndt Lukas Bodenberger, Philip Konietzke, Oliver Weinheimer, Willi Linus Wagner, Wolfram Stiller, Tim Frederik Weber, Claus Peter Heussel, Hans-Ulrich Kauczor, Mark Oliver Wielpuetz
Summary: This study aimed to quantify lung parenchyma and airway wall enhancement using a single contrast-enhanced spectral detector CT. The results showed that lung density was higher at 40 keV compared to 100 keV, and wall thickness and enhancement were higher at 40 keV for arterial phases. Spectral CT can quantify lung parenchyma and airway wall enhancement, and further studies are needed to analyze inflammatory airway diseases.
EUROPEAN RADIOLOGY
(2023)
Article
Engineering, Chemical
Seshu K. Damarla, Xi Sun, Fangwei Xu, Ashish Shah, Biao Huang
Summary: Control valve, affected by stiction, causes oscillations in closed-loop signals, leading to reduced product quality, plant throughput, and increased environmental impact. Therefore, it is crucial to detect and quantify stiction in control valves. In this study, four noninvasive and practical methods are developed using statistical tests such as F-test, t-test, modified Hotelling T2-test, and reverse arrangement test. These methods are applied to benchmark control loops from various industries and compared with existing methods. The results show that the proposed methods perform equally well or better than existing methods, with the t-test-based method and the modified Hotelling T2-test-based method being particularly effective. The proposed methods not only detect stiction but also quantify its severity, providing timely notifications to operators and assisting maintenance engineers in scheduling plant shutdowns. These methods are applicable to all control loops except for level loops.
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH
(2023)
Article
Oncology
Ying Zhang, Shijie Chen, Yuling Wang, Jingjing Li, Kai Xu, Jyhcheng Chen, Jie Zhao
Summary: This study proposes a deep-learning approach to predict the microsatellite status of endometrial cancer directly from H&E-stained WSIs. The proposed architecture can capture valuable features for classification and provide a more convenient screening tool for rapid automated testing.
JOURNAL OF CANCER RESEARCH AND CLINICAL ONCOLOGY
(2023)
Article
Clinical Neurology
Jorge A. Roa, Mario Zanaty, Carlos Osorno-Cruz, Daizo Ishii, Girish Bathla, Santiago Ortega-Gutierrez, David M. Hasan, Edgar A. Samaniego
Summary: This study compared different methods for quantifying wall enhancement of UIAs and determined the sensitivity and specificity of each method as a surrogate of aneurysm instability. The study found that CRstalk using maximal SI values was the most reliable objective method to quantify enhancement of UIAs on HR-VWI. There was a good correlation between different manufacturers and scans obtained using magnets of different strengths.
JOURNAL OF NEUROSURGERY
(2021)
Article
Engineering, Industrial
Jee Yun Kim, David Garcia, Yunhui Zhu, David M. Higdon, Hang Z. Yu
Summary: This paper presents an interdisciplinary framework that combines experimentation, mechanical modeling, and statistical learning to address the challenges of multi-material design in additive manufacturing. By using advanced Bayesian learning and inference, this framework enables parameter calibration, fast and accurate prediction of physical response, and uncertainty quantification.
JOURNAL OF MATERIALS PROCESSING TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Yousef Ibrahim Daradkeh, Volodymyr Gorokhovatskyi, Iryna Tvoroshenko, Svitlana Gadetska, Mujahed Al-Dhaifallah
Summary: This article addresses the issue of image recognition in computer vision systems, presenting the development of a method for image classification based on a structural approach. Two options for constructing the classifier are proposed, with the experiment showing the significant advantage of the object descriptor - etalon method over the integrated approach. Both methods classified the set of etalons without error, showing the effectiveness of the developed classifiers.
Article
Chemistry, Analytical
Tim Lauschke, Georg Dierkes, Thomas A. Ternes
Summary: This study focuses on the effects of inorganic sample matrix on the pyrolysis of PET and discusses various approaches to tackle these issues. Inorganic matrix constituents caused changes in the distribution of pyrolysis products, reactions with the analytes, or losses of intensity due to decomposition of the specific markers used for identification and quantification of PET. Therefore, a fast, reliable thermoanalytical method for precise quantification of PET in complex environmental matrices cannot be recommended currently, and extensive, time-consuming sample clean-up protocols seem to be unavoidable.
JOURNAL OF ANALYTICAL AND APPLIED PYROLYSIS
(2023)
Article
Computer Science, Artificial Intelligence
Elyoenai Guerra-Segura, Aysse Ortega-Perez, Carlos M. Travieso
Summary: The study introduces a novel in-air signature verification system utilizing Leap Motion controller, demonstrating its effectiveness through experiments. With a database of 100 users, the system shows robust performance against zero effort attacks and active impostors, with equal error rates of 0.25% and 1.20% respectively.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Biomedical
Rakesh Chandra Joshi, Saumya Yadav, Vinay Kumar Pathak, Hardeep Singh Malhotra, Harsh Vardhan Singh Khokhar, Anit Parihar, Neera Kohli, D. Himanshu, Ravindra K. Garg, Madan Lal Brahma Bhatt, Raj Kumar, Naresh Pal Singh, Vijay Sardana, Radim Burget, Cesare Alippi, Carlos M. Travieso-Gonzalez, Malay Kishore Dutta
Summary: A deep learning-based system is proposed for automatic detection and classification of COVID-19 using chest X-ray images, achieving a high accuracy rate in multi-class and binary classification. Infected patient's chest X-ray images reveal distinct opacities compared to healthy lungs, enabling a rapid and accurate diagnostic tool to assist healthcare professionals in managing the pandemic effectively.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2021)
Article
Chemistry, Analytical
Soumaya Dghim, Carlos M. Travieso-Gonzalez, Radim Burget
Summary: This paper introduces the detection of Nosema disease using image processing tools, machine learning, and deep learning approaches. Two main strategies are examined: one involves extracting valuable information and features from microscopic images dataset using image processing tools and applying machine learning methods, while the other explores deep learning and transfer learning.
Article
Chemistry, Multidisciplinary
Jesus B. Alonso-Hernandez, Maria Luisa Barragan-Pulido, Jose Manuel Gil-Bordon, Miguel Angel Ferrer-Ballester, Carlos M. Travieso-Gonzalez
Summary: This study aims to explore two different strategies for facilitating the generation of spontaneous speech for further analysis: using a human interviewer and using an automatic system. A database called Cross-Sectional Alzheimer Prognosis R2019 was established, consisting of speech samples recorded using both methodologies. The results show that both strategies have the ability to discriminate between speakers with AD and control subjects.
APPLIED SCIENCES-BASEL
(2021)
Article
Engineering, Biomedical
Manoj Kaushik, Neeraj Baghel, Radim Burget, Carlos M. Travieso, Malay Kishore Dutta
Summary: The article suggests an automatic deep learning model to assist in the early diagnosis of specific language impairment in children. By processing raw audio data and utilizing convolutional neural networks for classification, it can effectively aid in the automatic diagnosis of children's language development. This method has high accuracy and shows better diagnostic results compared to existing methods.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Artificial Intelligence
Jesus Bernardino Alonso Hernandez, Maria Luisa Barragan Pulido, Jose Manuel Gil Bordon, Miguel Angel Ferrer Ballester, Carlos Manuel Travieso Gonzalez
Summary: Recent studies focus on automatic analysis of speech recordings for Alzheimer's disease detection and evolutionary control, with results showing promising potential for automation in telemedicine and teleservice scenarios.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Mathematics, Applied
Amit Kumar Gupta, Pushpa Gothwal, Dinesh Goyal, Carlos M. Travieso-Gonzalez
Summary: The COVID-19 pandemic has had a global impact on public health, and efforts are being made to develop vaccination and maintain mental health. Sanitized environments are crucial to prevent the spread of infections, and many countries are facing challenges in increasing infection rates due to hygiene problems. This paper presents an IoT-powered Galvanized Pandemic Special E-Toilet that addresses the issue of hygiene by incorporating smart healthcare appliances. The proposed architecture includes occupancy checks, auto flush, and appliance control through a mobile application. The system utilizes a raspberry pi board, Arduino Uno, and various sensors and modules. The architecture has been successfully simulated and can be implemented in various settings such as education, industries, and healthcare facilities.
JOURNAL OF DISCRETE MATHEMATICAL SCIENCES & CRYPTOGRAPHY
(2022)
Article
Anatomy & Morphology
Blanca Mompeo-Corredera, Pablo Hernandez-Morera, Irene Castano-Gonzalez, Maria del Pino Quintana-Montesdeoca, Natalia Mederos-Real
Summary: Detailed structural studies on the human renal artery using histocytochemistry, immunohistochemistry, and quantitative image analysis revealed distinct regional characteristics that may affect the occurrence and therapeutic response of related diseases.
ANATOMY & CELL BIOLOGY
(2022)
Article
Chemistry, Analytical
Jesus Galvan-Ruiz, Carlos M. Travieso-Gonzalez, Alejandro Pinan-Roescher, Jesus B. Alonso-Hernandez
Summary: According to WHO, a significant percentage of the global population faces difficulty in oral communication due to hearing disorders. This article discusses the importance of developing tools to aid in daily communication for these individuals. The research focuses on transcribing Spanish Sign Language (SSL) using a Leap Motion volumetric sensor capable of recognizing hand movements in 3D. By collaborating with a hearing-impaired subject and recording 176 dynamic words, the research achieves an accuracy of 95.17% in predicting input through the use of Dynamic Time Warping (DTW).
Article
Computer Science, Information Systems
Aayushi Chaudhari, Chintan Bhatt, Achyut Krishna, Carlos M. Travieso-Gonzalez
Summary: Emotion recognition is a challenging research field that involves various cognitive-emotional cues such as language, expressions, and speech. By using video input, a large amount of data can be obtained for analyzing human emotions. In this research, pretrained self-supervised learning models are used to extract features from text, audio, and visual data modalities. The fusion of these features and representations is the main challenge in multimodal emotion classification research. To address the high dimensionality of self-supervised learning characteristics, a unique fusion method based on Transformer and attention is proposed, achieving an accuracy of 86.40% for multimodal emotion classification.
Article
Mathematics
Sergio Celada-Bernal, Guillermo Perez-Acosta, Carlos M. Travieso-Gonzalez, Jose Blanco-Lopez, Luciano Santana-Cabrera
Summary: This paper aims to predict the medical test values of COVID-19 patients in the ICU, providing healthcare professionals with additional tools and information to combat COVID-19 by retrieving the missing medical test values.
Article
Computer Science, Artificial Intelligence
Shivangi Surati, Himani Trivedi, Bela Shrimali, Chintan Bhatt, Carlos M. Travieso-Gonzalez
Summary: This research aims to classify Monkeypox, Chickenpox, and Measles using trained standalone DL models and a SENet attention model, improving the accuracy of their diagnosis and classification. The proposed method achieves considerable success in accuracy, precision, recall, and F1-score, enhancing the overall performance of classification for Monkeypox.
MULTIMODAL TECHNOLOGIES AND INTERACTION
(2023)
Article
Multidisciplinary Sciences
Tobias Steinmetzer, Ingrid Bonninger, Carlos M. Travieso-Gonzalez
Summary: This paper proposes a new method for symmetry calculation in wearable devices. It addresses the issue of potential loss of information when using discrete features for calculation.
Article
Multidisciplinary Sciences
Rakesh Chandra Joshi, Saumya Yadav, Malay Kishore Dutta, Carlos M. Travieso-Gonzalez
Summary: Blood cell analysis is crucial for health and immunity assessment. Traditional methods are time-consuming and expensive, necessitating the need for automated methods. This study proposes a convolutional neural network-based framework that can accurately detect and count various types of blood cells.
Article
Computer Science, Information Systems
Anzhelika Mezina, Radim Burget, Carlos M. Travieso-Gonzalez
Summary: Anomaly detection in network traffic is crucial for ensuring security in future networks, requiring smart algorithms to adapt to changing network conditions and detect threats. Various approaches have been developed, but many are tested on outdated datasets, leading to overfitting and inaccuracies in real-world applications.