Article
Agriculture, Dairy & Animal Science
M. Martin, M. D. Kleinhenz, K. S. Schwartzkopf-Genswein, D. Melendez, S. Marti, E. A. Pajor, E. D. Janzen, J. Coetzee
Summary: This study used ROC analysis to evaluate the predictive value of pain biomarkers in livestock. It found that plasma cortisol, hair cortisol, and IRT had higher AUC values, while salivary cortisol, MNT, substance P, kinematic gait analysis, and a visual analog scale for pain had lower AUC values.
JOURNAL OF DAIRY SCIENCE
(2022)
Article
Geochemistry & Geophysics
Chein-I Chang
Summary: This article explores fundamental and conceptual issues in the application of the 2D ROC curve for hyperspectral anomaly detection, providing solutions and insights. By deriving a mathematical theory and conducting comprehensive analysis, it reveals the principles of plotting the 2D ROC curve and evaluating background suppression. The article also highlights that many detectors claiming good performance in AD actually perform poorly in BS.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Gastroenterology & Hepatology
Sergei Vosko, Neal Shahidi, Mayenaaz Sidhu, W. Arnout van Hattem, Iddo Bar-Yishay, Scott Schoeman, David J. Tate, Luke F. Hourigan, Rajvinder Singh, Alan Moss, Karen Byth, Eric Y. T. Lee, Nicholas G. Burgess, Michael J. Bourke
Summary: This study found significant differences in optical evaluation performance between flat and nodular large nonpedunculated colorectal polyps. Flat lesions can be presumed benign and managed accordingly, while nodular lesions are more likely to be missed for submucosal invasive cancer.
CLINICAL GASTROENTEROLOGY AND HEPATOLOGY
(2021)
Article
Medicine, General & Internal
Kei Nakazawa, Sadaharu Nouda, Kazuki Kakimoto, Naohiko Kinoshita, Yasuyoshi Tanaka, Hideki Tawa, Ryoji Koshiba, Yutaka Naka, Yuki Hirata, Kazuhiro Ota, Ken Kawakami, Toshihisa Takeuchi, Takuya Inoue, Takako Miyazaki, Makoto Sanomura, Shiro Nakamura, Yutaka Saito, Kazuhide Higuchi
Summary: In this study, we aimed to differentiate between adenomatous polyps (APs) and hyperplastic polyps (HPs) using colon capsule endoscopy (CCE) with the CIELAB color space method. The results showed that the FICE Delta E' was significantly higher for APs compared to HPs, indicating the potential of this method to reduce unnecessary colonoscopy procedures.
Article
Medicine, General & Internal
Pere Gilabert, Jordi Vitria, Pablo Laiz, Carolina Malagelada, Angus Watson, Hagen Wenzek, Santi Segui
Summary: Colon Capsule Endoscopy (CCE) is a minimally invasive procedure used as an alternative to conventional colonoscopy. We developed AI-Tool, a web application that uses artificial intelligence to assist CCE reviewers in detecting polyps. The new software significantly reduces reviewing time and improves polyp detection sensitivity compared to the traditional method.
FRONTIERS IN MEDICINE
(2022)
Article
Health Care Sciences & Services
Ka Luen Thomas Lui, Sze Hang Kevin Liu, Kathy Leung, Joseph T. Wu, Ann G. Zauber, Wai Keung Leung
Summary: The widespread adoption of computer-aided detection (CADe) in detecting colorectal polyps would result in shorter surveillance intervals for patients, particularly according to the US Multi-Society Task Force on Colorectal Cancer (USMSTF) guideline. Based on simulation, CADe application would lead to approximately 19.1% and 1.9% of patients requiring shorter surveillance intervals, as recommended by the USMSTF and European Society of Gastrointestinal Endoscopy (ESGE) guidelines, respectively. Specifically, all or 2.7% of patients initially scheduled for 3-5 years of surveillance would have their intervals shortened to 3 years, according to the USMSTF guideline.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2023)
Article
Gastroenterology & Hepatology
Mayenaaz Sidhu, Neal Shahidi, Sunil Gupta, Lobke Desomer, Sergei Vosko, W. Arnout van Hattem, Luke F. Hourigan, Eric Y. T. Lee, Alan Moss, Spiro Raftopoulos, Steven J. Heitman, Stephen J. Williams, Simon Zanati, David J. Tate, Nicholas Burgess, Michael J. Bourke
Summary: Thermal ablation of the defect margin after endoscopic mucosal resection (EMR-T) has been shown to significantly reduce residual or recurrent adenoma (RRA) at first surveillance colonoscopy. In an international multi-center prospective trial, EMR-T was found to be a simple, inexpensive, and highly effective auxiliary technique for managing large nonpedunculated colorectal polyps.
Article
Medicine, General & Internal
Serhiy Semenov, Conor Costigan, Mohd Syafiq Ismail, Deirdre McNamara
Summary: This study assessed the false negative rate of CCE and the breakdown of reader/technical errors. The results showed that CCE has a significant false negative rate, which should be taken into consideration in clinical decision making.
Article
Biology
Keli Hu, Liping Zhao, Sheng Feng, Shengdong Zhang, Qianwei Zhou, Xiaozhi Gao, Yanhui Guo
Summary: In this paper, a novel method called NeutSS-PLP is proposed for polyp region extraction in colonoscopy images using a short connected saliency detection network with neutrosophic enhancement. Experimental results on two public datasets demonstrate the effectiveness of the proposed method for polyp extraction.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Psychology, Multidisciplinary
Yueran Yang
Summary: This article discusses how to improve classification performance using ROC analysis and introduces a tool to visualize a classifier's expected utility. The analysis reveals that expected utility depends not only on the accuracy of a classifier but also on its operating point. Therefore, choosing the optimal operating point can maximize expected utility. The article also explores other methods beyond ROC analysis to increase expected utility.
PSYCHOLOGICAL METHODS
(2022)
Article
Computer Science, Hardware & Architecture
Ruhul Ali Khan
Summary: A new semiparametric model of the ROC curve is proposed, which is based on the resilience family or proportional reversed hazard family. The resulting ROC curve and its summary indices have simple analytic forms. The estimation methodologies of the resilience family and a simulation study to assess the performance of the estimators are discussed.
IEEE TRANSACTIONS ON RELIABILITY
(2023)
Review
Medicine, General & Internal
Sarah Moen, Fanny E. R. Vuik, Ernst J. Kuipers, Manon C. W. Spaander
Summary: This article provides an overview of the literature on the use of artificial intelligence for reviewing colonic mucosa by colon capsule endoscopy and discusses the necessary actions for its clinical application. The results indicate that artificial intelligence models have promising sensitivity for bowel cleansing and the detection of polyps and colorectal neoplasia.
Article
Mathematics, Interdisciplinary Applications
Evgeniya Gospodinova, Penio Lebamovski, Galya Georgieva-Tsaneva, Mariya Negreva
Summary: The dynamics of cardiac signals were studied using methods for nonlinear analysis of HRV. The article used various methods, such as Rescaled Range, Detrended Fluctuation Analysis, Multifractal Detrended Fluctuation Analysis, Poincare plot, Approximate Entropy and Sample Entropy, to investigate the characteristics of the intervals between heartbeats. The results showed that these methods could effectively distinguish between healthy and unhealthy subjects, providing new perspectives in the diagnosis of cardiovascular diseases.
FRACTAL AND FRACTIONAL
(2023)
Article
Gastroenterology & Hepatology
E. Soons, T. Rath, Y. Hazewinkel, W. A. van Dop, D. Esposito, P. A. Testoni, P. D. Siersema
Summary: This study aimed to investigate the feasibility and safety of a novel CADe system during real-time colonoscopy in three European tertiary referral centers. The results showed that using this system for colonoscopy was feasible and safe, with relatively high adenoma and sessile serrated lesion detection rates compared to previous studies.
INTERNATIONAL JOURNAL OF COLORECTAL DISEASE
(2022)
Article
Mathematics, Applied
Alexej Gossmann, Aria Pezeshk, Yu-Ping Wang, Berkman Sahiner
Summary: The performance evaluation of constantly evolving machine learning algorithms, especially in high-risk fields such as medicine, faces new challenges. Reusing the same test dataset can lead to overfitting and overly optimistic conclusions about algorithm performance. A modified holdout mechanism shows potential in reducing overfitting issues.
SIAM JOURNAL ON MATHEMATICS OF DATA SCIENCE
(2021)
Article
Mathematics, Applied
L. Borcea, V Druskin, A. Mamonov, S. Moskow, M. Zaslavsky
Article
Computer Science, Information Systems
Abhinav Patel, Kumi Rani, Sunil Kumar, Isabel N. Figueiredo, Pedro N. Figueiredo
Summary: This study proposes a novel sparse coded features method for detecting bleeding in WCE images, achieving a classification accuracy of 98.18%. Experimental results demonstrate the reliability of this method for bleeding detection in WCE images.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Gastroenterology & Hepatology
Catarina Correia, Raquel Teixeira, Nuno Miguel Peres de Almeida, Sofia Morais, Pedro Figueiredo
Summary: The study aimed to assess the occurrence of burnout in Portuguese gastroenterologists and found a higher prevalence of burnout in young doctors, interns, doctors performing multiple techniques (upper gastrointestinal endoscopy and colonoscopy), those working on weekends or involved in legal-medical issues.
SCANDINAVIAN JOURNAL OF GASTROENTEROLOGY
(2021)
Article
Gastroenterology & Hepatology
Helena Cortez-Pinto, Rodrigo Liberal, Susana Lopes, Mariana Machado, Joana Carvalho, Teresa Dias, Arsenio Santos, Claudia Agostinho, Pedro Figueiredo, Rafaela Loureiro, Alexandra Martins, Goncalo Alexandrino, Isabel Cotrim, Carina Leal, Jose Presa, Monica Mesquita, Joana Nunes, Catarina Gouveia, Ana Horta E. Vale, Ana Luisa Alves, Mariana Coelho, Luis Maia, Isabel Pedroto, Antonio Banhudo, Joao Sebastiao Pinto, Marta Vargas Gomes, Joana Oliveira, Valeska Andreozzi, Filipe Calinas
Summary: This study found a considerable proportion of patients with primary biliary cholangitis showed incomplete biochemical response to ursodeoxycholic acid (UDCA) treatment. Patients with cirrhosis, elevated levels of gamma-glutamyl transferase (GGT) and alkaline phosphatase (ALP) at diagnosis were identified as being at higher risk for incomplete response. Early identification of patients at risk of incomplete response could improve treatment care and guide clinical decision-making.
UNITED EUROPEAN GASTROENTEROLOGY JOURNAL
(2021)
Article
Gastroenterology & Hepatology
Catarina Correia, Nuno Almeida, Pedro Figueiredo
Summary: This study aimed to understand the prevalence of asymptomatic COVID-19 infection among patients undergoing endoscopic procedures at a tertiary care hospital. Results showed a low proportion of asymptomatic carriers of SARS-CoV-2 among patients proposed for endoscopic intervention, with only 1 out of 833 patients tested positive, leading to a need for strict adherence to prevention measures.
GE PORTUGUESE JOURNAL OF GASTROENTEROLOGY
(2022)
Article
Gastroenterology & Hepatology
Carina Leal, Nuno Almeida, Maria Silva, Antonieta Santos, Helena Vasconcelos, Pedro Figueiredo
Summary: The study revealed a significant portion of endoscopies, particularly in private healthcare settings, were conducted without appropriate indications, impacting the diagnostic yield. Therefore, the use of adequate criteria is crucial for the rational utilization of an open-access system.
GE PORTUGUESE JOURNAL OF GASTROENTEROLOGY
(2022)
Article
Mathematics, Applied
Liliana Borcea, Josselin Garnier, Alexander Mamonov, Jorn Zimmerling
Summary: This paper introduces a novel and computationally inexpensive imaging method that utilizes an active array of sensors to probe an unknown medium and measure the resulting waves. The method is based on the principle of time reversal and employs a data-driven estimate to obtain the internal wave and achieve selective focusing of waves.
Article
Mathematics, Applied
Vladimir Druskin, Alexander Mamonov, Mikhail Zaslavsky
Summary: This paper discusses the importance of Graph-Laplacians and spectral embeddings in machine learning, specifically in dimension reduction for spectral clustering. The authors propose two novel algorithms that focus on reducing computational cost and preserving important global distances between data nodes. The algorithms achieve this by developing a reduced-order model of the graph-Laplacian and working with a small target subset of data points. Numerical experiments demonstrate the effectiveness of these algorithms in clustering synthetic and real data.
JOURNAL OF SCIENTIFIC COMPUTING
(2022)
Article
Gastroenterology & Hepatology
Catarina Correia, Helder Moreira, Nuno Almeida, Marta Soares, Augusta Cipriano, Pedro Figueiredo
Summary: This case report presents a 30-year-old female patient with long-standing severe dysphagia and odynophagia. Despite anti-acid therapy, symptoms persisted, and endoscopy revealed a nontransposable stenosis in the proximal esophagus. An underlying autoimmune process was suspected, and topical immunosuppressants were tried, but the patient still experienced disabling dysphagia. A diagnosis of probable IgG4-related disease was made after esophageal biopsies, and treatment with topical corticosteroids did not lead to significant symptom improvement, possibly due to the chronic fibrotic nature of the disease.
GE PORTUGUESE JOURNAL OF GASTROENTEROLOGY
(2023)
Article
Engineering, Multidisciplinary
Alexander V. Mamonov, Maxim A. Olshanskii
Summary: This paper presents a reduced order model (ROM) for numerical integration of a dynamical system with multiple parameters. The ROM utilizes compressed tensor formats to find a low rank representation for high-fidelity snapshots of the system state. The computational cost of the online phase depends only on tensor compression ranks, making it efficient and accurate.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2022)
Article
Geochemistry & Geophysics
Liliana Borcea, Josselin Garnier, Alexander V. Mamonov, Jorn Zimmerling
Summary: We propose a novel approach to waveform inversion using a data-driven reduced order model (ROM). This method can be applied to acoustic, elastic, or electromagnetic waves. By minimizing the misfit between the ROM computed from recorded data and the ROM computed from modeled data, we solve the inverse problem of velocity estimation. We demonstrate the effectiveness of the ROM misfit objective function compared to the least-squares data fit objective function, which displays multiple local minima even with a poor initial guess.
Article
Computer Science, Artificial Intelligence
Liliana Borcea, Josselin Garnier, Alexander V. Mamonov, Jorn Zimmerling
Summary: This paper investigates an inverse problem for the wave equation, aiming to estimate the wave speed based on data collected from emitting probing signals and measuring resulting waves. The common approach of nonlinear least squares minimization faces two challenges: the nonlinearity of the mapping from wave speed to data and incomplete knowledge of the kinematics. To address this, the paper proposes using a data driven estimate of the internal wave field, which leads to improved inversion performance with a reasonable initial guess of the kinematics.
SIAM JOURNAL ON IMAGING SCIENCES
(2023)
Article
Gastroenterology & Hepatology
Mafalda Joao, Ines Cunha, Elisa Gravito-Soares, Marta Gravito-Soares, Pedro Amaro, Pedro Figueiredo
Summary: Colonic lipomas, while common, are usually asymptomatic. This case report demonstrates successful diagnosis and treatment of a colonic lipoma through a conservative approach and minimally invasive endoscopic procedure, averting the need for a major surgical intervention in a high-risk patient.
GE PORTUGUESE JOURNAL OF GASTROENTEROLOGY
(2022)
Article
Computer Science, Information Systems
Marina Oliveira, Helder Araujo, Isabel N. Figueiredo, Luis Pinto, Eva Curto, Luis Perdigoto
Summary: Wireless Capsule Endoscopy (WCE) is a non-invasive medical procedure designed for painless inspection of the gastrointestinal tract, especially the small intestine. The main challenge lies in accurately identifying the capsule's location and trajectory in the GI tract to detect tissue anomalies. Image registration between sequential frames is crucial for estimating the motion of the camera capsule.
Article
Computer Science, Artificial Intelligence
Liliana Borcea, Vladimir Druskin, Alexander Mamonov, Mikhail Zaslavsky, Joern Zimmerling
SIAM JOURNAL ON IMAGING SCIENCES
(2020)
