Article
Computer Science, Artificial Intelligence
Feng Li, Shengfei Shi, Hongzhi Wang
Summary: Partial Multi-Label Learning (PML) is a learning approach that aims to build a robust multi-label classifier by considering label correlations and extracting label-specific features. The proposed method, named Partial multi-lAbel learning via Specific lAbel Disambiguation (PASAD), utilizes the Hilbert-Schmidt Independence Criterion (HSIC) to identify projection matrices for each label and map instances into label-specific feature spaces. The method also incorporates label propagation and considers interactions between different label spaces. Experimental results demonstrate the effectiveness and superiority of the proposed method.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Information Systems
Garima Singh
Summary: IoMT has gained popularity in the healthcare industry and is expected to expand beyond clinics and hospitals in the future. However, security remains a major concern as cybercriminals constantly target healthcare facilities. This research proposes a secure authentication and key agreement protocol to enhance IoMT security.
INTERNET OF THINGS
(2023)
Article
Engineering, Electrical & Electronic
Duo Shan, Changming Cheng, Lingjian Li, Zhike Peng, Qingbo He
Summary: Fault diagnosis of gearboxes is crucial for the safe operation of industrial systems. This article proposes a novel semisupervised method for gearboxes using weighted label propagation and virtual adversarial training to overcome the shortage of labeled data in practical industrial applications. The proposed method leverages unlabeled data for pseudo label inference and introduces sample weights to reduce the negative effect of noisy labels. Experimental results demonstrate the effectiveness of the proposed semisupervised approach in leveraging unlabeled data to solve the labeled data shortage.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Information Systems
Kamal Berahmand, Sogol Haghani, Mehrdad Rostami, Yuefeng Li
Summary: The diffusion method is a major approach for community detection in complex networks. The LPA algorithm, which mimics epidemic contagion, is efficient but has some issues. This paper proposes a new version of the LPA algorithm for attributed graphs that solves problems related to instability and low quality, and improves node selection and updating mechanisms. Experimental results show that the proposed method outperforms other state-of-the-art attributed graph clustering methods in terms of efficiency and accuracy.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Environmental Sciences
Gang Xu, Min Deng, Geng Sun, Ya Guo, Jie Chen
Summary: This paper proposes a knowledge distillation-based building extraction method to reduce the impact of noise on the model and improve the performance. The method utilizes the generalizable knowledge from large-scale noisy samples and accurate supervision from small-scale clean samples to train a teacher and student network. Experimental results show that the student network can alleviate the influence of noise labels and achieve accurate building extraction.
Article
Engineering, Biomedical
Takaaki Sugino, Yutaro Suzuki, Taichi Kin, Nobuhito Saito, Shinya Onogi, Toshihiro Kawase, Kensaku Mori, Yoshikazu Nakajima
Summary: This study evaluates the performance of FCNs in label cleaning and propagation, showing that both 2D and 3D FCNs can provide improved segmentation results from incomplete training data, especially when using three orthogonal annotation images for network training.
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
(2021)
Article
Computer Science, Artificial Intelligence
Jia Zhang, Hanrui Wu, Min Jiang, Jinghua Liu, Shaozi Li, Yong Tang, Jinyi Long
Summary: In many real-world application domains, objects often belong to multiple class labels, which leads to the multi-label learning problem. The quality of available features greatly affects the performance of multi-label learning, but the data usually contain many irrelevant, redundant, or noisy features. As a result, feature selection methods have been extensively studied to select meaningful features for multi-label learning. However, existing methods often fail to consider label-specific features and are inefficient in utilizing labeling information. In this paper, we propose a new group-preserving label-specific feature selection framework to address these issues, and extensive experiments demonstrate its advantages.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Biomedical
Yong Peng, Honggang Liu, Junhua Li, Jun Huang, Bao-Liang Lu, Wanzeng Kong
Summary: This paper proposes a Joint label-Common and label-Specific Features Exploration (JCSFE) model for semi-supervised cross-session EEG emotion recognition. The experimental results demonstrate that JCSFE achieves superior emotion recognition performance and provides a quantitative method to identify the label-common and label-specific EEG features in emotion recognition.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Yangning Li, Yinghui Li, Xi Chen, Hai-Tao Zheng, Ying Shen
Summary: This article addresses two major problems in Open Relation Extraction (OpenRE): insufficient capacity to discriminate between known and novel relations, and the inability to label human-readable and meaningful types for novel relations. To solve these issues, the Active Relation Discovery (ARD) framework, which includes relational outlier detection and active learning, is proposed. Extensive experiments demonstrate the superior performance of ARD in both conventional and general OpenRE settings.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Tingting Hang, Jun Feng, Le Yan, Yunfeng Wang, Jiamin Lu
Summary: This article presents a joint extraction model for entities and relations called MLRA-LSTM-CRF, which uses multi-label tagging and relational alignment to solve the identification problem of entities and relations. Experimental results show that this model significantly outperforms other methods.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Runqing Jiang, Yan Yan, Jing-Hao Xue, Si Chen, Nannan Wang, Hanzi Wang
Summary: This article explores the issue of knowledge distillation (KD) with noisy labels and proposes a novel method called ambiguity-guided mutual label refinery KD (AML-KD) to train the student model in the presence of noisy labels. The AML-KD method introduces a label refinery framework and an ambiguity-aware weight estimation module to refine labels gradually and address the problem of ambiguous samples, achieving a high-accuracy and low-cost student model with label noise.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Naiyao Liang, Zuyuan Yang, Zhenni Li, Shengli Xie, Weijun Sun
Summary: This study introduces a novel semi-supervised multi-view learning approach called Label Propagation based Non-negative Matrix Factorization (LPNMF) to address the problem of sparse labeled data. By constructing the intrinsic manifold structure of data and utilizing label propagation, the limited labeled data can be fully utilized. Experimental results demonstrate the advantages of this method over existing methods.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Engineering, Biomedical
Zeynab Barzegar, Mansour Jamzad
Summary: The study introduces a semi-supervised learning framework that combines atlas-based segmentation and machine learning methods, achieving accurate segmentation results in identifying glioma. Experimental results show that the framework outperforms state-of-the-art methods in tumor segmentation.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Joseph Nathaniel Stember, Hrithwik Shalu
Summary: Image classification is a fundamental task in radiology AI. Researchers employed automated label extraction and reinforced learning classification to reduce data acquisition and labeling burden, showing the potential application of these methods in radiology AI.
JOURNAL OF DIGITAL IMAGING
(2022)
Article
Computer Science, Theory & Methods
Jia Hou Chin, Kuru Ratnavelu
Summary: This paper introduces an improved community detection algorithm, SSCLPA, which enhances stability by incorporating various constraints while maintaining accuracy and time efficiency. After testing across multiple benchmarks and real-world networks, the algorithm demonstrates a well-balanced approach towards stability, quality, and time efficiency in detection.
Article
Clinical Neurology
Stavros Tsagkaris, Eric K. C. Yau, Verity McClelland, Apostolos Papandreou, Ata Siddiqui, Daniel E. Lumsden, Margaret Kaminska, Eric Guedj, Alexander Hammers, Jean-Pierre Lin
Summary: Tsagkaris et al. found that patients with paediatric dystonia have different patterns of brain glucose metabolism observed through FDG-PET scans. These patterns can be linked to specific clinical signs and may serve as useful biomarkers for differential diagnosis and personalized management. The study sheds light on the pathophysiology of dystonia and supports the network theory for its development.
Letter
Clinical Neurology
Siti N. Yaakub, Tristan A. White, Eric Kerfoot, Lennart Verhagen, Alexander Hammers, Elsa F. Fouragnan
Article
Neurosciences
Sunniva Fenn-Moltu, Sean P. Fitzgibbon, Judit Ciarrusta, Michael Eyre, Lucilio Cordero-Grande, Andrew Chew, Shona Falconer, Oliver Gale-Grant, Nicholas Harper, Ralica Dimitrova, Katy Vecchiato, Daphna Fenchel, Ayesha Javed, Megan Earl, Anthony N. Price, Emer Hughes, Eugene P. Duff, Jonathan O'Muircheartaigh, Chiara Nosarti, Tomoki Arichi, Daniel Rueckert, Serena Counsell, Joseph Hajnal, A. David Edwards, Grainne McAlonan, Dafnis Batalle
Summary: The formation of the functional connectome in early life is crucial for future learning and behavior. However, our understanding of how the functional organization of brain regions matures during the early postnatal period, especially in response to adverse neurodevelopmental outcomes like preterm birth, is limited. In this study involving 366 neonates, we found that functional centrality (weighted degree) increased with age in visual regions and decreased in motor and auditory regions in term-born infants. Preterm-born infants scanned at term equivalent age showed higher functional centrality in visual regions and lower measures in motor regions. Functional centrality did not predict neurodevelopmental outcomes at 18 months old.
Article
Engineering, Electrical & Electronic
Xianqiang Bao, Shuangyi Wang, Lingling Zheng, Richard James Housden, Joseph V. Hajnal, Kawal Rhode
Summary: This article proposes an ultrasound robot that integrates force control, force/torque measurement, and online adjustment mechanisms to address the concerns in medical ultrasound. The robot can measure, adjust, and eliminate operating forces, and achieve various scanning depths based on clinical requirements. Simulations and experiments show that the robot performs well in detecting forces and torques, maintaining constant operating force, and achieving different scanning depths.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Acoustics
Laura Peralta, Daniele Mazierli, Alberto Gomez, Joseph Hajnal, Piero Tortoli, Alessandro Ramalli
Summary: Coherent multitransducer ultrasound (CoMTUS) utilizes the coherent combination of multiple arrays to create an extended effective aperture, resulting in improved resolution, field-of-view, and sensitivity in images. This study demonstrates the feasibility of implementing CoMTUS in 3-D imaging using a pair of 256-element 2-D sparse spiral arrays, which reduces channel count and data processing. The imaging performance of CoMTUS is investigated using simulations, phantom tests, and experimental free-hand operation, showing significant improvements in spatial resolution, contrast-to-noise ratio, and generalized CNR compared to a single dense array system.
IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ayse Sila Dokumaci, Fraser R. Aitken, Jan Sedlacik, Pip Bridgen, Raphael Tomi-Tricot, Ronald Mooiweer, Katy Vecchiato, Tom Wilkinson, Chiara Casella, Sharon Giles, Joseph Hajnal, Shaihan J. Malik, Jonathan O'Muircheartaigh, David W. Carmichael
Summary: In this study, an optimized MP2RAGE protocol at 7 Tesla was developed to provide T1-weighted uniform image and gray matter-dominant fluid and white matter suppression contrast images simultaneously in a clinically applicable acquisition time. The results showed that high-contrast images with excellent anatomical detail could be obtained using the optimized parameter set.
MAGNETIC RESONANCE IN MEDICINE
(2023)
Letter
Anesthesiology
Philippa Bridgen, Shaihan Malik, Thomas Wilkinson, John N. Cronin, Tahzeeb Bhagat, Nicholas Hart, Stuart Mc Corkell, Joanne Perkins, Shane Tibby, Sara Hanna, Richard Kirwan, Thomas Pauly, Arthur Weeks, Geoff Charles-Edwards, Francesco Padormo, David Stell, Kariem El-Boghdadly, Sebastien Ourselin, Sharon L. Giles, Anthony D. Edwards, Joseph V. Hajnal, Benjamin J. Blaise
BRITISH JOURNAL OF ANAESTHESIA
(2023)
Article
Neurosciences
Abi Fukami-Gartner, Ana A. Baburamani, Ralica Dimitrova, Prachi A. Patkee, Olatz Ojinaga-Alfageme, Alexandra F. Bonthrone, Daniel Cromb, Alena U. Uus, Serena J. Counsell, Joseph Hajnal, Jonathan O'Muircheartaigh, Mary A. Rutherford
Summary: Down syndrome (DS) is a common genetic cause of intellectual disability. In this study, researchers analyzed the brain volumes of neonates with DS using neuroimaging techniques. They found that the DS brain showed significant reductions in overall volume, cerebral white matter, and cerebellar volumes, as well as differences in relative lobar volumes. Furthermore, certain features such as enlarged deep gray matter volume and lateral ventricle enlargement were observed. Assessing phenotypic severity at the neonatal stage may help guide early interventions and improve neurodevelopmental outcomes in children with DS.
Article
Neurosciences
David Steinbart, Siti N. Yaakub, Mirja Steinbrenner, Lynn S. Guldin, Martin Holtkamp, Simon S. Keller, Bernd Weber, Theodor Rueber, Rolf Heckemann, Maria Ilyas-Feldmann, Alexander Hammers
Summary: This study proposes a manual segmentation protocol and an automatic segmentation method to investigate the relationship between the piriform cortex and memory as well as epilepsy. The results show differences in the volumes of the piriform cortex in healthy individuals, temporal lobe epilepsy patients, and Alzheimer's disease patients, providing a new biomarker for early diagnosis.
HUMAN BRAIN MAPPING
(2023)
Article
Computer Science, Interdisciplinary Applications
Lucilio Cordero-Grande, Juan Enrique Ortuno-Fisac, Alejandra Aguado del Hoyo, Alena Uus, Maria Deprez, Andres Santos, Joseph V. Hajnal, Maria J. Ledesma-Carbayo
Summary: In this paper, a deep generative prior and a diffeomorphic volume to slice registration method are proposed for robust volumetric reconstructions. Experiments on 72 fetal datasets show that our method outperforms existing techniques in improving image quality and accurately predicting gestational age.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Article
Psychology, Developmental
Lucy Vanes, Sunniva Fenn-Moltu, Laila Hadaya, Sean Fitzgibbon, Lucilio Cordero-Grande, Anthony Price, Andrew Chew, Shona Falconer, Tomoki Arichi, Serena J. Counsell, Joseph V. Hajnal, Dafnis Batalle, David Edwards, Chiara Nosarti
Summary: Preterm birth increases the risk of adverse behavioural outcomes in later life. Our study examines the longitudinal development of neonatal brain volume and functional connectivity after preterm birth and their relationship to psychomotor outcomes and psychopathology in toddlerhood. We found that better psychomotor functioning is associated with specific brain volume and connectivity changes in the neonatal period, while increased psychopathology is related to alterations in regional subcortical volume. Additionally, socio-economic deprivation and cognitively stimulating parenting play different roles in predicting psychopathology and psychomotor outcomes. Our findings highlight the importance of longitudinal imaging and environmental influences in understanding behavioural development in preterm infants.
DEVELOPMENTAL COGNITIVE NEUROSCIENCE
(2023)
Article
Biology
Sian Wilson, Maximilian Pietsch, Lucilio Cordero-Grande, Daan Christiaens, Alena Uus, Vyacheslav R. Karolis, Vanessa Kyriakopoulou, Kathleen Colford, Anthony N. Price, Jana Hutter, Mary A. Rutherford, Emer J. Hughes, Serena J. Counsell, Jacques-Donald Tournier, Joseph Hajnal, A. David Edwards, Jonathan O'Muicheartaigh, Tomoki Arichi, Finnegan J. Calabro
Summary: In this study, high-resolution in utero diffusion magnetic resonance imaging was used to examine the development of thalamocortical white matter in 140 fetuses. The researchers delineated the thalamocortical pathways and parcellated the fetal thalamus based on its cortical connectivity. They quantified microstructural tissue components along the tracts in fetal compartments and identified changes in diffusion metrics reflecting critical neurobiological transitions. These findings provide a normative reference for further studies on developmental disruptions and their contributions to pathophysiology.
Article
Automation & Control Systems
Xianqiang Bao, Shuangyi Wang, Lingling Zheng, Richard James Housden, Joseph Hajnal, Kawal Rhode
Summary: This article proposes a novel self-adaptive parallel manipulator (SAPM) for robotic ultrasonography. The SAPM can automatically adjust the ultrasound probe pose, provide approximate constant operating forces/torques, achieve mechanical measurement, and cushion undesired produced forces. Experimental results show that the SAPM can provide 3 DOFs motion, operating force/torque measurement, and automatically adjust the US probe pose to capture high-quality ultrasound images.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Infectious Diseases
Michela Antonelli, Rose S. Penfold, Liane Dos Santos Canas, Carole Sudre, Khaled Rjoob, Ben Murray, Erika Molteni, Eric Kerfoot, Nathan Cheetham, Juan Capdevila Pujol, Lorenzo Polidori, Anna May, Jonathan Wolf, Marc Modat, Tim Spector, Alexander Hammers, Sebastien Ourselin, Claire Steves
Summary: This study describes the characteristics of SARS-CoV-2 illness following a third vaccination and assesses the risk of progression to symptomatic disease in SARS-CoV-2 infected individuals with time since vaccination. The results suggest that a third dose of monovalent vaccine may reduce symptoms, severity, and duration of SARS-CoV-2 infection following vaccination.
JOURNAL OF INFECTION
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Sameer Omer Jin, Ines Merida, Ioannis Stavropoulos, Robert D. C. Elwes, Tanya Lam, Eric Guedj, Nadine Girard, Nicolas Costes, Alexander Hammers
Summary: This study compared two different databases of [F-18]FDG PET data and achieved a higher abnormality detection rate by adjusting spatial resolution and global values. The results demonstrate the importance of increasing database size and overcoming database differences, which can be applicable to traditional statistical analysis or machine learning, as well as clinical implementation.