Article
Computer Science, Information Systems
Meng Shen, Aijing Gu, Jiawen Kang, Xiangyun Tang, Xiaodong Lin, Liehuang Zhu, Dusit Niyato
Summary: With the rapid advances in information and communication technologies, the Internet of Things has become large and complex. Leveraging artificial intelligence technologies, IoT can achieve superior information extraction and decision making, resulting in the revolutionized AIoT. Despite the promising features, AIoT systems still face challenges including efficiency, security, privacy, trust, and incentive. Blockchain can be a promising technology for addressing these challenges.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Review
Radiology, Nuclear Medicine & Medical Imaging
Liping Si, Jingyu Zhong, Jiayu Huo, Kai Xuan, Zixu Zhuang, Yangfan Hu, Qian Wang, Huan Zhang, Weiwu Yao
Summary: The study systematically reviewed 36 articles on the application of deep learning in knee joint imaging, revealing the insufficient scientific quality of the studies. Improvements in study design, validation, and open science are needed to demonstrate the generalizability of findings and achieve clinical applications. Despite this, deep learning remains a promising technology for diagnostic or predictive purposes.
EUROPEAN RADIOLOGY
(2022)
Article
Rheumatology
Lukas Folle, Sara Bayat, Arnd Kleyer, Filippo Fagni, Lorenz A. Kapsner, Maja Schlereth, Timo Meinderink, Katharina Breininger, Koray Tacilar, Gerhard Kroenke, Michael Uder, Michael Sticherling, Sebastian Bickelhaupt, Georg Schett, Andreas Maier, Frank Roemer, David Simon
Summary: This study evaluated whether neural networks could differentiate seropositive rheumatoid arthritis (RA), seronegative RA, and psoriatic arthritis (PsA) based on inflammatory patterns from hand MRIs. The results showed that neural networks could successfully classify these types of inflammation based on MRI data.
Article
Neurosciences
Heath R. Pardoe, Arun Raj Antony, Hoby Hetherington, Anto I. Bagic, Timothy M. Shepherd, Daniel Friedman, Orrin Devinsky, Jullie Pan
Summary: The study utilized 3D deep CNN to label hippocampus and amygdala on 7T MRI, with successful labeling and highly correlated volume estimates compared to manual labels. The performance of CNN labeling was consistent between healthy controls and epilepsy cases, suggesting potential for development of morphometric analysis techniques in high field strength, high spatial resolution brain MRI.
HUMAN BRAIN MAPPING
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Anushri Parakh, Jinjin Cao, Theodore T. Pierce, Michael A. Blake, Cristy A. Savage, Avinash R. Kambadakone
Summary: The sinogram-based deep learning image reconstructions were both subjectively and objectively preferred over iterative reconstruction due to improved image quality and lower noise, even in large patients. DLIR-H had the best objective scores, indicating potential for clinical use and radiation dose reduction.
EUROPEAN RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Alexia Tran, Louis Lassalle, Pascal Zille, Raphael Guillin, Etienne Pluot, Chloe Adam, Martin Charachon, Hugues Brat, Maxence Wallaert, Gaspard D'Assignies, Benoit Rizk
Summary: This study developed a deep learning algorithm for the detection of anterior cruciate ligament (ACL) tears and compared its accuracy using two external datasets. The algorithm showed high performance and generalizability across different manufacturers and populations.
EUROPEAN RADIOLOGY
(2022)
Review
Radiology, Nuclear Medicine & Medical Imaging
Nikita Sushentsev, Nadia Moreira Da Silva, Michael Yeung, Tristan Barrett, Evis Sala, Michael Roberts, Leonardo Rundo
Summary: This study systematically reviewed the current literature to evaluate the ability of fully-automated deep learning (DL) and semi-automated traditional machine learning (TML) MRI-based artificial intelligence (AI) methods in differentiating clinically significant prostate cancer from indolent prostate cancer and benign conditions. The study found comparable performance of the two classes of AI methods and identified common methodological limitations and biases.
INSIGHTS INTO IMAGING
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Gabriel Keller, Arne Estler, Judith Herrmann, Saif Afat, Ahmed E. E. Othman, Dominik Nickel, Gregor Koerzdoerfer, Fabian Springer
Summary: This study evaluates the diagnostic performance of a deep learning-based accelerated TSE study protocol compared to a standard TSE study protocol in ankle MRI. The results show that DL TSE has high agreement with standard TSE in all analyzed structural pathologies and performs well in image quality. The total acquisition time of DL TSE is reduced by 48% compared to standard TSE.
Article
Computer Science, Information Systems
Ruhul Amin Hazarika, Debdatta Kandar, Arnab Kumar Maji
Summary: Classification of Alzheimer's disease is a challenging task for neurologists. A deep learning framework using brain images is proposed for more accurate results. The DenseNet-121 model achieves a convincing result with an average performance rate of 88.78%. To improve execution time, the convolution layers in the original architecture are replaced with depth-wise convolution layers, resulting in an average performance rate of 90.22%.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Medicine, General & Internal
J. Weston Hughes, Neal Yuan, Bryan He, Jiahong Ouyang, Joseph Ebinger, Patrick Botting, Jasper Lee, John Theurer, James E. Tooley, Koen Nieman, Matthew P. Lungren, David H. Liang, Ingela Schnittger, Jonathan H. Chen, Euan A. Ashley, Susan Cheng, David Ouyang, James Y. Zou
Summary: This study introduced EchoNet-Labs, a deep learning algorithm for interpreting echocardiogram videos to detect various blood biomarkers. The algorithm showed promising performance in detecting anemia, elevated BNP, troponin I, and BUN on both internal and external test datasets, demonstrating its potential for clinical application.
Article
Computer Science, Information Systems
Shivani Gaba, Ishan Budhiraja, Vimal Kumar, Sahil Garg, Georges Kaddoum, Mohammad Mehedi Hassan
Summary: This paper provides a detailed review of various deep learning architectures and models, with a focus on a specific convolutional neural network model. It discusses the working principles of convolutional neural networks and their components and presents various models from LeNet to AlexNet, GoogleNet, VGGNet, ResNet, DenseNet, Xception, PNAS/ENAS, and EfficientNet. The challenges associated with different network architectures are also summarized. The paper concludes with a discussion of the frameworks, datasets, applications, and accuracy of each model, serving as a future scope in the field.
COMPUTER COMMUNICATIONS
(2022)
Article
Medicine, General & Internal
Sebastian Breden, Florian Hinterwimmer, Sarah Consalvo, Jan Neumann, Carolin Knebel, Ruediger von Eisenhart-Rothe, Rainer H. Burgkart, Ulrich Lenze
Summary: Although rare, tumors in children are one of the leading causes of death among individuals under the age of 18. Detecting bone tumors, especially on X-rays, in underage patients is challenging due to their rarity and non-specific symptoms. However, early diagnosis is crucial for effective treatment and improved prognosis. A new approach utilizing artificial intelligence for evaluating X-ray images shows promise in facilitating the detection of suspicious lesions and expediting referrals to specialized centers.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Neurosciences
Leonie Henschel, David Kuegler, Martin Reuter
Summary: This study fills the gap in existing methods in the field of high-resolution MRI (HiRes) by proposing a Voxel-size Independent Neural Network (VINN) for resolution-independent image segmentation tasks. The FastSurferVINN method achieves whole brain segmentation within the resolution range of 0.7-1.0 mm and significantly outperforms existing methods at various resolutions. Additionally, this method addresses the data imbalance problem in HiRes datasets and has important application prospects.
Article
Radiology, Nuclear Medicine & Medical Imaging
MinWoo Kim, Sang-Min Lee, Chankue Park, Dongeon Lee, Kang Soo Kim, Hee Seok Jeong, Shinyoung Kim, Min-Hyeok Choi, Dominik Nickel
Summary: This study investigated different combinations of parallel imaging (PI) and simultaneous multislice (SMS) acceleration imaging using deep learning (DL)-enhanced and conventional reconstruction. It compared the diagnostic performance of these combinations in internal knee derangement and provided a quantitative evaluation of image sharpness and noise.
INVESTIGATIVE RADIOLOGY
(2022)
Article
Multidisciplinary Sciences
Yonatan Elul, Aviv A. Rosenberg, Assaf Schuster, Alex M. Bronstein, Yael Yaniv
Summary: Artificial intelligence systems have not yet become widespread in medical practice due to unmet needs of healthcare practitioners, particularly in terms of providing explanations, handling unknown medical conditions, and transparently addressing system limitations. This study articulates these needs as machine-learning problems and uses cutting-edge techniques to tackle them, specifically focusing on ECG analysis to detect arrhythmias and identify underlying cardio-pathology. Validating the methods through population screening for arrhythmias, the system visualizes ECG segment importance, upholds statistical constraints, handles unknown rhythm types, and works with data from unseen patients. This work represents a significant step toward integrating AI into cardiology and medicine.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yanjie Zhu, Yuanyuan Liu, Leslie Ying, Xin Liu, Hairong Zheng, Dong Liang
MAGNETIC RESONANCE IN MEDICINE
(2020)
Editorial Material
Engineering, Electrical & Electronic
Mathews Jacob, Jong Chul Ye, Leslie Ying, Mariya Doneva
IEEE SIGNAL PROCESSING MAGAZINE
(2020)
Editorial Material
Engineering, Electrical & Electronic
Dong Liang, Jing Cheng, Ziwen Ke, Leslie Ying
IEEE SIGNAL PROCESSING MAGAZINE
(2020)
Article
Radiology, Nuclear Medicine & Medical Imaging
Sk HashemizadehKolowri, Rong-Rong Chen, Ganesh Adluru, Leslie Ying, Edward V. R. DiBella
MAGNETIC RESONANCE IMAGING
(2020)
Article
Radiology, Nuclear Medicine & Medical Imaging
Haifeng Wang, Dong Liang, Shi Su, Kevin F. King, Yuchou Chang, Xin Liu, Hairong Zheng, Leslie Ying
Article
Radiology, Nuclear Medicine & Medical Imaging
Shanshan Wang, Huitao Cheng, Leslie Ying, Taohui Xiao, Ziwen Ke, Hairong Zheng, Dong Liang
MAGNETIC RESONANCE IMAGING
(2020)
Article
Neurosciences
Chaoyi Zhang, Tanzil Mahmud Arefin, Ukash Nakarmi, Choong Heon Lee, Hongyu Li, Dong Liang, Jiangyang Zhang, Leslie Ying
Article
Biochemical Research Methods
Sunil Kumar Gaire, Yang Zhang, Hongyu Li, Ray Yu, Hao F. Zhang, Leslie Ying
BIOMEDICAL OPTICS EXPRESS
(2020)
Article
Engineering, Biomedical
Ziwen Ke, Jing Cheng, Leslie Ying, Hairong Zheng, Yanjie Zhu, Dong Liang
PHYSICS IN MEDICINE AND BIOLOGY
(2020)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yanjie Zhu, Yuanyuan Liu, Leslie Ying, Zhilang Qiu, Qiegen Liu, Sen Jia, Haifeng Wang, Xi Peng, Xin Liu, Hairong Zheng, Dong Liang
Summary: The MS-T-1 rho solution developed in this study allows for high-resolution whole-brain T-1 rho mapping within 4 minutes, showing good agreement with reference values in phantom and in vivo experiments. The results suggest that MS-T-1 rho may be a useful tool for investigating neural diseases, with accelerated T-1 rho measurements showing moderate to good agreement with fully sampled reference values.
MAGNETIC RESONANCE IN MEDICINE
(2021)
Article
Biochemical Research Methods
Sunil Kumar Gaire, Yanhua Wang, Hao F. Zhang, Dong Liang, Leslie Ying
Summary: The study aims to accelerate three-dimensional SMLM imaging by leveraging a computational approach to reconstruct high-density 3D images from low-density ones without compromising resolution, achieving superior reconstruction results and reducing the number of acquired frames.
JOURNAL OF BIOMEDICAL OPTICS
(2021)
Article
Engineering, Biomedical
Huijuan Zhang, Hongyu Li, Nikhila Nyayapathi, Depeng Wang, Alisa Le, Leslie Ying, Jun Xia
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS
(2020)