Article
Computer Science, Artificial Intelligence
Aron Henriksson, Yash Pawar, Pontus Hedberg, Pontus Naucler
Summary: This study demonstrates the development of multimodal models for predicting COVID-19 outcomes, effectively utilizing both structured and unstructured data. The models are trained and evaluated on a multicenter cohort, outperforming unimodal models in predicting various outcomes.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Paolo Soda, Natascha Claudia D'Amico, Jacopo Tessadori, Giovanni Valbusa, Valerio Guarrasi, Chandra Bortolotto, Muhammad Usman Akbar, Rosa Sicilia, Ermanno Cordelli, Deborah Fazzini, Michaela Cellina, Giancarlo Oliva, Giovanni Callea, Silvia Panella, Maurizio Cariati, Diletta Cozzi, Vittorio Miele, Elvira Stellato, Gianpaolo Carrafiello, Giulia Castorani, Annalisa Simeone, Lorenzo Preda, Giulio Iannello, Alessio Del Bue, Fabio Tedoldi, Marco Ali, Diego Sona, Sergio Papa
Summary: This study investigates the use of artificial intelligence with chest X-ray scans and clinical data for the early identification of COVID-19 patients at risk, showing promising performance and potential for providing useful information in patient and hospital resource management.
MEDICAL IMAGE ANALYSIS
(2021)
Review
Computer Science, Artificial Intelligence
Sadaf Naz, Khoa T. Phan, Yi-Ping Phoebe Chen
Summary: This paper reviews the importance of applying artificial intelligence and machine learning techniques in COVID-19 detection, with a focus on the federated learning approach for protecting data privacy. Case studies of using FL for COVID-19 detection in health systems and applications of FL in COVID-19 research are discussed, along with challenges in implementing FL in the healthcare domain.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Information Systems
Weishan Zhang, Tao Zhou, Qinghua Lu, Xiao Wang, Chunsheng Zhu, Haoyun Sun, Zhipeng Wang, Sin Kit Lo, Fei-Yue Wang
Summary: This study introduces a dynamic fusion-based federated learning approach for medical diagnostic image analysis to detect COVID-19 infections. By dynamically selecting participating clients and scheduling model fusion, communication efficiency and model performance are improved.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Chemistry, Multidisciplinary
Evandro Carvalho de Andrade, Placido Rogerio Pinheiro, Ana Luiza Bessa de Paula Barros, Luciano Comin Nunes, Luana Ibiapina C. C. Pinheiro, Pedro Gabriel Caliope Dantas Pinheiro, Raimir Holanda Filho
Summary: This research evaluates the performance of classification algorithms applied to COVID-19 patient data using comparative analysis and benchmarking techniques, and finds that the Multilayer Perceptron algorithm performs well in the clinical evolution classification process.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Dharwada Sesha Sriram, Aseem Ranjan, Vedant Ghuge, Naveen Rathore, Raghav Agarwal, Tausif Diwan, Jitendra V. Tembhurne
Summary: Federated learning is important for COVID-19 detection as it allows collaborative analysis of dispersed medical data while preserving privacy. This research introduces Personalized Federated Averaging (PerFedAvg) as an improvement over the standard FedAvg technique, resulting in better model performance in settings with high data heterogeneity.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Public, Environmental & Occupational Health
Mahalakshmi Kumaran, Truong-Minh Pham, Kaiming Wang, Hussain Usman, Colleen M. Norris, Judy MacDonald, Gavin Y. Oudit, Vineet Saini, Khokan C. Sikdar
Summary: This study used decision tree modeling to identify key factors associated with severe outcomes in COVID-19 patients. Age and breathing difficulties were the most important predictors, while neurological conditions, diabetes, cardiovascular disease, hypertension, and renal disease were significant comorbidities.
FRONTIERS IN PUBLIC HEALTH
(2022)
Article
Computer Science, Artificial Intelligence
Ines Feki, Sourour Ammar, Yousri Kessentini, Khan Muhammad
Summary: The COVID-19 pandemic has led to a need for efficient diagnosis methods, with deep learning proving to be valuable in analyzing chest X-ray images. This study introduces a collaborative federated learning framework for medical institutions to screen COVID-19 without sharing patient data, showing competitive results compared to traditional data-sharing models. By addressing privacy concerns and utilizing private data, this framework allows for the rapid development of powerful models for COVID-19 screening.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Information Systems
Guanjin Wang, Stephen Wai Hang Kwok, Mohammed Yousufuddin, Ferdous Sohel
Summary: The study proposes a novel imbalanced learning approach, ImAUC-PSVM, based on classical PSVM to predict the composite outcomes of hospitalized COVID-19 patients. Experimental results demonstrate that ImAUC-PSVM outperforms other methods in most cases, showcasing its potential to assist clinicians in triaging COVID-19 patients at an early stage and in other prediction applications.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Information Systems
Dasaradharami Reddy Kandati, Thippa Reddy Gadekallu
Summary: Coronavirus (COVID-19) has caused a global disaster. Early detection of COVID-19 symptoms is important and artificial intelligence (AI) can play a vital role in this process. However, AI requires access to sensitive patient personal records, posing privacy concerns. Federated Learning (FL) is a promising solution that can detect COVID-19 cases without compromising patient privacy.
Letter
Medicine, General & Internal
Marion Renaud, Claire Thibault, Floriane Le Normand, Emily G. Mcdonald, Benoit Gallix, Christian Debry, Aina Venkatasamy
Summary: This cohort study examines the clinical course and prognosis of patients with COVID-19-related anosmia for 1 year after diagnosis.
Article
Oncology
Haris Hatic, Kristine R. R. Hearld, Devika Das, Jessy Deshane
Summary: Patients with cancer who contract COVID-19 while receiving chemotherapy or immune checkpoint inhibitors (ICIs) are at higher risk of complications and mortality. This retrospective study found that COVID-19-related ICI mortality was higher compared to patients receiving chemotherapy. However, patients with better functional status and COVID-19 vaccination had reduced mortality.
Article
Computer Science, Artificial Intelligence
Deepraj Chowdhury, Soham Banerjee, Madhushree Sannigrahi, Arka Chakraborty, Anik Das, Ajoy Dey, Ashutosh Dhar Dwivedi
Summary: The researchers developed a CNN model based on deep and federated learning, which can quickly detect COVID-19 by uploading a single chest X-ray image. The model has achieved high accuracy and emphasizes user data security.
Article
Medicine, General & Internal
Mikyoung Park, Mina Hur, Hanah Kim, Chae Hoon Lee, Jong Ho Lee, Hyung Woo Kim, Minjeong Nam, Seungho Lee
Summary: This study demonstrated that sST2 could be a useful biomarker to predict ICU admission, ventilator use, ECMO use, and 30-day mortality in hospitalized COVID-19 patients. sST2 may be implemented as a prognostic COVID-19 biomarker in clinical practice.
Article
Virology
Sandhya R. Nagarakanti, Alexis K. Okoh, Sagy Grinberg, Eliahu Bishburg
Summary: A retrospective study was conducted at Newark Beth Israel Medical Center to compare the clinical outcomes of HIV patients hospitalized for COVID-19 with a matched control group. The study found that HIV patients had similar in-hospital mortality, ICU admission rate, and need for mechanical ventilation compared to COVID-19 patients without HIV.
JOURNAL OF MEDICAL VIROLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Po -Ting Chen, Tinghui Wu, Pochuan Wang, Dawei Chang, Kao-Lang Liu, Ming-Shiang Wu, Holger R. Roth, Po-Chang Lee, Wei-Chih Liao, Weichung Wang
Summary: A deep learning-based tool was developed to accurately detect pancreatic cancer on CT scans, with high sensitivity for tumors smaller than 2 cm.
Biographical-Item
Radiology, Nuclear Medicine & Medical Imaging
Gordon D. Waiter, Fiona J. Gilbert, Alison Murray, Beverly MacLennan
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2023)
Article
Cardiac & Cardiovascular Systems
Andrej Corovic, Christopher Wall, Meritxell Nus, Deepa Gopalan, Yuan Huang, Maria Imaz, Michal Zulcinski, Marta Peverelli, Anna Uryga, Jordi Lambert, Dario Bressan, Robert T. Maughan, Charis Pericleous, Suraiya Dubash, Natasha Jordan, David R. Jayne, Stephen P. Hoole, Patrick A. Calvert, Andrew F. Dean, Doris Rassl, Tara Barwick, Mark Iles, Mattia Frontini, Greg Hannon, Roido Manavaki, Tim D. Fryer, Luigi Aloj, Martin J. Graves, Fiona J. Gilbert, Marc R. Dweck, David E. Newby, Zahi A. Fayad, Gary Reynolds, Ann W. Morgan, Eric O. Aboagye, Anthony P. Davenport, Helle F. Jorgensen, Ziad Mallat, Martin R. Bennett, James E. Peters, James H. F. Rudd, Justin C. Mason, Jason M. Tarkin
Summary: This study investigates the feasibility of using somatostatin receptor 2 (SST2) as a molecular imaging target for inflammation in large vessel vasculitis (LVV), and provides evidence for its potential in the diagnosis and therapeutic monitoring of LVV.
JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Syed M. S. Reza, Winston T. Chu, Fatemeh Homayounieh, Maxim Blain, Fatemeh D. Firouzabadi, Pouria Y. Anari, Ji Hyun Lee, Gabriella Worwa, Courtney L. Finch, Jens H. Kuhn, Ashkan Malayeri, Ian Crozier, Bradford J. Wood, Irwin M. Feuerstein, Jeffrey Solomon
Summary: This study employs deep-learning techniques to quantitatively analyze the CT scans of nonhuman primates exposed to SARS-CoV-2, specifically focusing on whole-lung and lung-lesion segmentation. Through the use of a novel multi-model ensemble technique, the automated segmentation of lung lesions is improved, demonstrating superior performance compared to other methods. The application of automated segmentation methods provides a standardized and automated approach for disease detection and quantification.
ACADEMIC RADIOLOGY
(2023)
Article
Multidisciplinary Sciences
Lavender Yao Jiang, Xujin Chris Liu, Nima Pour Nejatian, Mustafa Nasir-Moin, Duo Wang, Anas Abidin, Kevin Eaton, Howard Antony Riina, Ilya Laufer, Paawan Punjabi, Madeline Miceli, Nora C. Kim, Cordelia Orillac, Zane Schnurman, Christopher Livia, Hannah Weiss, David Kurland, Sean Neifert, Yosef Dastagirzada, Douglas Kondziolka, Alexander T. M. Cheung, Grace Yang, Ming Cao, Mona Flores, Anthony B. Costa, Yindalon Aphinyanaphongs, Kyunghyun Cho, Eric Karl Oermann
Summary: Clinical language models trained on unstructured clinical notes can be used as all-purpose clinical predictive engines, providing guidance and improving prediction accuracy compared to traditional models. The models can be easily developed and deployed, with potential for generalizability to different healthcare systems.
Review
Radiology, Nuclear Medicine & Medical Imaging
Jung Hyun Yoon, Fredrik Strand, Pascal A. T. Baltzer, Emily F. Conant, Fiona J. Gilbert, Constance D. Lehman, Elizabeth A. Morris, Lisa A. Mullen, Robert M. Nishikawa, Nisha Sharma, Ilse Vejborg, Linda Moy, Ritse M. Mann
Summary: This study evaluated the performance of artificial intelligence (AI) in the interpretation of digital mammography and digital breast tomosynthesis (DBT). The results showed that standalone AI performed as well as or better than radiologists in digital mammography, but there were insufficient studies to assess its performance in DBT interpretation.
Editorial Material
Computer Science, Interdisciplinary Applications
Holger R. Roth, Nicola Rieke, Shadi Albarqouni, Quanzheng Li
Summary: Federated Learning (FL) alleviates privacy concerns in medical imaging by enabling collaborative training without sharing raw data. This Special Issue explores various FL-related topics and their implications in healthcare and medical imaging. The articles cover a wide range of federated scenarios and applications, emphasizing the importance of unbiased, privacy-preserving, and generalizable AI models in clinical practice. The research presented in this Special Issue significantly advances the field.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Editorial Material
Biochemistry & Molecular Biology
Fiona Gilbert
Summary: Combining artificial intelligence with human expertise can be the best approach to enhance diagnostic accuracy in clinical imaging while ensuring safety.
Article
Acoustics
Hisham Assi, Rui Cao, Madhura Castelino, Ben Cox, Fiona J. Gilbert, Janek Gro, Kurinchi Gurusamy, Lina Hacker, Aoife M. Ivory, James Joseph, Ferdinand Knieling, Martin J. Leahy, Ledia Lilaj, Srirang Manohar, Igor Meglinski, Carmel Moran, Andrea Murray, Alexander A. Oraevsky, Mark D. Pagel, Manojit Pramanik, Jason Raymond, Mithun Kuniyil Ajith Singh, William C. Vogt, Lihong Wang, Shufan Yang, Sarah E. Bohndiek
Summary: Photoacoustic imaging has a promising potential in clinical trials, but its adoption in healthcare systems for clinical decision making faces barriers such as education, training, and data interpretation. The International Photoacoustic Standardisation Consortium identified these barriers and developed plans to address them.
Article
Radiology, Nuclear Medicine & Medical Imaging
Simone Schiaffino, Katja Pinker, Andrea Cozzi, Veronica Magni, Alexandra Athanasiou, Pascal A. T. Baltzer, Julia Camps Herrero, Paola Clauser, Eva M. Fallenberg, Gabor Forrai, Michael H. Fuchsjaeger, Fiona J. Gilbert, Thomas Helbich, Fleur Kilburn-Toppin, Christiane K. Kuhl, Mihai Lesaru, Ritse M. Mann, Pietro Panizza, Federica Pediconi, Francesco Sardanelli, Tamar Sella, Isabelle Thomassin-Naggara, Sophia Zackrisson, Ruud M. Pijnappel
Summary: New evidence has led to updates in recommendations by EUSOBI regarding breast imaging examinations after COVID-19 vaccination. For asymptomatic patients with unilateral lymphadenopathy and no suspicious breast findings, no further work-up is needed. Other recommendations issued in 2021 remain valid.
INSIGHTS INTO IMAGING
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Xinrui Song, Xuanang Xu, Sheng Xu, Baris Turkbey, Thomas Sanford, Bradford J. Wood, Pingkun Yan
MEDICAL IMAGING 2023
(2023)
Meeting Abstract
Urology & Nephrology
Anjali Pillai, Zoe Blake, Daniel R. Nemirovsky, Jacob J. Enders, Neil Mendhiratta, Alexander P. Kenigsberg, Michael B. Rothberg, Jibriel Noun, Daniel Nethala, Sandeep Gurram, Bradford J. Wood, Baris Turkbey, Peter A. Pinto
JOURNAL OF UROLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ana Jimenez-Pastor, Rafael Lopez-Gonzalez, Belen Fos-Guarinos, Fabio Garcia-Castro, Mark Wittenberg, Asuncion Torregrosa-Andres, Luis Marti-Bonmati, Margarita Garcia-Fontes, Pablo Duarte, Juan Pablo Gambini, Leonardo Kayat Bittencourt, Felipe Campos Kitamura, Vasantha Kumar Venugopal, Vidur Mahajan, Pablo Ros, Emilio Soria-Olivas, Angel Alberich-Bayarri
Summary: In this study, a U-Net based CNN model was developed to accurately segment the prostate using a heterogeneous database of 243 T2-weighted prostate studies from 7 countries and 10 machines of 3 different vendors, with manual delineations as ground truth. The model was trained and tested using deep supervision and a cyclical learning rate, and evaluated using dice similarity coefficient (DSC). The results showed that the proposed method achieved high accuracy in segmenting the prostate, central-transition zone, peripheral zone, and seminal vesicle, with no significant differences between manufacturers or continents.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Tim E. E. Phelps, Enis C. C. Yilmaz, Stephanie A. A. Harmon, Mason J. J. Belue, Joanna H. H. Shih, Charisse Garcia, Lindsey A. A. Hazen, Antoun Toubaji, Maria J. J. Merino, Sandeep Gurram, Peter L. L. Choyke, Bradford J. J. Wood, Peter A. A. Pinto, Baris Turkbey
Summary: This study evaluates the cancer detection rates of reduced-core biopsy schemes in patients with unilateral mpMRI-visible intraprostatic lesions and finds that the combined strategy of targeted biopsy and systematic biopsy maximizes the detection of clinically significant prostate cancer.
ABDOMINAL RADIOLOGY
(2023)
Article
Engineering, Biomedical
Neil Glossop, Reto Bale, Sheng Xu, William F. Pritchard, John W. Karanian, Bradford J. Wood
Summary: This study aimed to evaluate the feasibility of using personalized needle guidance grid templates for implementing in vivo ablation treatment plans with multiple needles. The personalized templates were fabricated using intraprocedural CT images, and multiple needle trajectories were planned. A numerical-controlled milling machine was used to drill the corresponding holes, and the needles were inserted to the calculated depth. The needle placement accuracy was high, and the procedure was performed rapidly.
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
(2023)