Search

Your search keyword '"Fayad, Zahi"' showing total 260 results
Start Over Author "Fayad, Zahi" Publication Year Range Last 3 years
260 results on '"Fayad, Zahi"'

1. Polymersomes with splenic avidity target red pulp myeloid cells for cancer immunotherapy

Author

Wauters, Annelies C., Scheerstra, Jari F., van Leent, Mandy M. T., Teunissen, Abraham J. P., Priem, Bram, Beldman, Thijs J., Rother, Nils, Duivenvoorden, Raphaël, Prévot, Geoffrey, Munitz, Jazz, Toner, Yohana C., Deckers, Jeroen, van Elsas, Yuri, Mora-Raimundo, Patricia, Chen, Gal, Nauta, Sheqouia A., Verschuur, Anna Vera D., Griffioen, Arjan W., Schrijver, David P., Anbergen, Tom, Li, Yudong, Wu, Hanglong, Mason, Alexander F., van Stevendaal, Marleen H. M. E., Kluza, Ewelina, Post, Richard A. J., Joosten, Leo A. B., Netea, Mihai G., Calcagno, Claudia, Fayad, Zahi A., van der Meel, Roy, Schroeder, Avi, Abdelmohsen, Loai K. E. A., Mulder, Willem J. M., and van Hest, Jan C. M.

Published
2024
Full Text
View/download PDF

2. VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and Classification

Author

Liu, Zelong, Tieu, Andrew, Patel, Nikhil, Soultanidis, George, Deyer, Louisa, Wang, Ying, Huver, Sean, Zhou, Alexander, Mei, Yunhao, Fayad, Zahi A., Deyer, Timothy, Mei, Xueyan, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Xu, Xuanang, editor, Cui, Zhiming, editor, Rekik, Islem, editor, Ouyang, Xi, editor, and Sun, Kaicong, editor

Published
2025
Full Text
View/download PDF

3. MRAnnotator: A Multi-Anatomy Deep Learning Model for MRI Segmentation

Author

Zhou, Alexander, Liu, Zelong, Tieu, Andrew, Patel, Nikhil, Sun, Sean, Yang, Anthony, Choi, Peter, Fauveau, Valentin, Soultanidis, George, Huang, Mingqian, Doshi, Amish, Fayad, Zahi A., Deyer, Timothy, and Mei, Xueyan

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Purpose To develop a deep learning model for multi-anatomy and many-class segmentation of diverse anatomic structures on MRI imaging. Materials and Methods In this retrospective study, two datasets were curated and annotated for model development and evaluation. An internal dataset of 1022 MRI sequences from various clinical sites within a health system and an external dataset of 264 MRI sequences from an independent imaging center were collected. In both datasets, 49 anatomic structures were annotated as the ground truth. The internal dataset was divided into training, validation, and test sets and used to train and evaluate an nnU-Net model. The external dataset was used to evaluate nnU-Net model generalizability and performance in all classes on independent imaging data. Dice scores were calculated to evaluate model segmentation performance. Results The model achieved an average Dice score of 0.801 on the internal test set, and an average score of 0.814 on the complete external dataset across 49 classes. Conclusion The developed model achieves robust and generalizable segmentation of 49 anatomic structures on MRI imaging. A future direction is focused on the incorporation of additional anatomic regions and structures into the datasets and model.

Published
2024

5. RadImageGAN -- A Multi-modal Dataset-Scale Generative AI for Medical Imaging

Author

Liu, Zelong, Zhou, Alexander, Yang, Arnold, Yilmaz, Alara, Yoo, Maxwell, Sullivan, Mikey, Zhang, Catherine, Grant, James, Li, Daiqing, Fayad, Zahi A., Huver, Sean, Deyer, Timothy, and Mei, Xueyan

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Deep learning in medical imaging often requires large-scale, high-quality data or initiation with suitably pre-trained weights. However, medical datasets are limited by data availability, domain-specific knowledge, and privacy concerns, and the creation of large and diverse radiologic databases like RadImageNet is highly resource-intensive. To address these limitations, we introduce RadImageGAN, the first multi-modal radiologic data generator, which was developed by training StyleGAN-XL on the real RadImageNet dataset of 102,774 patients. RadImageGAN can generate high-resolution synthetic medical imaging datasets across 12 anatomical regions and 130 pathological classes in 3 modalities. Furthermore, we demonstrate that RadImageGAN generators can be utilized with BigDatasetGAN to generate multi-class pixel-wise annotated paired synthetic images and masks for diverse downstream segmentation tasks with minimal manual annotation. We showed that using synthetic auto-labeled data from RadImageGAN can significantly improve performance on four diverse downstream segmentation datasets by augmenting real training data and/or developing pre-trained weights for fine-tuning. This shows that RadImageGAN combined with BigDatasetGAN can improve model performance and address data scarcity while reducing the resources needed for annotations for segmentation tasks.

Published
2023

6. Artificial intelligence applied to coronary artery calcium scans (AI-CAC) significantly improves cardiovascular events prediction

Author

Naghavi, Morteza, Reeves, Anthony P., Atlas, Kyle, Zhang, Chenyu, Atlas, Thomas, Henschke, Claudia I., Yankelevitz, David F., Budoff, Matthew J., Li, Dong, Roy, Sion K., Nasir, Khurram, Molloi, Sabee, Fayad, Zahi, McConnell, Michael V., Kakadiaris, Ioannis, Maron, David J., Narula, Jagat, Williams, Kim, Shah, Prediman K., Levy, Daniel, and Wong, Nathan D.

Published
2024
Full Text
View/download PDF

7. Macrophage PET imaging in mouse models of cardiovascular disease and cancer with an apolipoprotein-inspired radiotracer

Author

Toner, Yohana C., Prévot, Geoffrey, van Leent, Mandy M. T., Munitz, Jazz, Oosterwijk, Roderick, Verschuur, Anna Vera D., van Elsas, Yuri, Peric, Vedran, Maas, Rianne J. F., Ranzenigo, Anna, Morla-Folch, Judit, Wang, William, Umali, Martin, de Dreu, Anne, Fernandes, Jessica Chimene, Sullivan, Nathaniel A. T., Maier, Alexander, Mason, Christian, Reiner, Thomas, Fayad, Zahi A., Mulder, Willem J. M., Teunissen, Abraham J. P., and Pérez-Medina, Carlos

Published
2024
Full Text
View/download PDF

8. Abstract 4144108: Incorporating AI-enabled Left Atrial Volume Measurement from Coronary Artery Calcium Scans (AI-CAC) to CHA2DS2s-VASc Risk Score Improves Stroke Prediction in the Asymptomatic Population: The Multi-Ethnic Study of Atherosclerosis

Author

Naghavi, Morteza, Reeves, Anthony, Atlas, Kyle, Zhang, Chenyu, Atlas, Thomas, Henschke, Claudia, Yankelevitz, David, Budoff, Matthew, FAN, WENJUN, Yu, Ruilin, Branch, Andrea, Ma, Ning, Roy, Sion, Nasir, Khurram, Molloi, Sabee, Fayad, Zahi, McConnell, Michael, Kakadiaris, Ioannis, Zulueta, Javier, Maron, David, Shah, Prediman, Williams, Kim, Abela, george, Levy, Daniel, and Wong, Nathan

Published
2024
Full Text
View/download PDF

9. Abstract 4144083: AI-CVD: Artificial Intelligence-Enabled Opportunistic Screening of Coronary Artery Calcium Computed Tomography Scans for Predicting CVD Events and All-Cause Mortality: The Multi-Ethnic Study of Atherosclerosis (MESA)

Author

Naghavi, Morteza, Reeves, Anthony, Atlas, Kyle, Zhang, Chenyu, Atlas, Thomas, Henschke, Claudia, Yankelevitz, David, Budoff, Matthew, FAN, WENJUN, Yu, Ruilin, Branch, Andrea, Ma, Ning, Roy, Sion, Nasir, Khurram, Molloi, Sabee, Fayad, Zahi, McConnell, Michael, Kakadiaris, Ioannis, Zulueta, Javier, Maron, David, Shah, Prediman, Williams, Kim, Abela, george, Levy, Daniel, and Wong, Nathan

Published
2024
Full Text
View/download PDF

10. Abstract 4144067: AI-enabled Cardiac Chambers Volumetry in Coronary Artery Calcium Scans (AI-CAC) vs. ASCVD Pooled Cohorts Equation and PREVENT Risk Scores: The Multi-Ethnic Study of Atherosclerosis

Author

Naghavi, Morteza, Reeves, Anthony, Atlas, Kyle, Zhang, Chenyu, Atlas, Thomas, Henschke, Claudia, Yankelevitz, David, Budoff, Matthew, FAN, WENJUN, Yu, Ruilin, Branch, Andrea, Ma, Ning, Roy, Sion, Nasir, Khurram, Molloi, Sabee, Fayad, Zahi, McConnell, Michael, Kakadiaris, Ioannis, Zulueta, Javier, Maron, David, Narula, Jagat, Shah, Prediman, Williams, Kim, Abela, george, Levy, Daniel, and Wong, Nathan

Published
2024
Full Text
View/download PDF

11. Interstitial lung disease diagnosis and prognosis using an AI system integrating longitudinal data

Author

Mei, Xueyan, Liu, Zelong, Singh, Ayushi, Lange, Marcia, Boddu, Priyanka, Gong, Jingqi QX, Lee, Justine, DeMarco, Cody, Cao, Chendi, Platt, Samantha, Sivakumar, Ganesh, Gross, Benjamin, Huang, Mingqian, Masseaux, Joy, Dua, Sakshi, Bernheim, Adam, Chung, Michael, Deyer, Timothy, Jacobi, Adam, Padilla, Maria, Fayad, Zahi A, and Yang, Yang

Subjects
Biomedical and Clinical Sciences, Clinical Sciences, Rare Diseases, Biomedical Imaging, Clinical Research, Lung, 7.3 Management and decision making, 4.1 Discovery and preclinical testing of markers and technologies, Management of diseases and conditions, 4.2 Evaluation of markers and technologies, Detection, screening and diagnosis, Respiratory, Humans, Lung Diseases, Interstitial, Disease Progression, Thorax, Tomography, X-Ray Computed, Retrospective Studies
Abstract

For accurate diagnosis of interstitial lung disease (ILD), a consensus of radiologic, pathological, and clinical findings is vital. Management of ILD also requires thorough follow-up with computed tomography (CT) studies and lung function tests to assess disease progression, severity, and response to treatment. However, accurate classification of ILD subtypes can be challenging, especially for those not accustomed to reading chest CTs regularly. Dynamic models to predict patient survival rates based on longitudinal data are challenging to create due to disease complexity, variation, and irregular visit intervals. Here, we utilize RadImageNet pretrained models to diagnose five types of ILD with multimodal data and a transformer model to determine a patient's 3-year survival rate. When clinical history and associated CT scans are available, the proposed deep learning system can help clinicians diagnose and classify ILD patients and, importantly, dynamically predict disease progression and prognosis.

Published
2023

12. Trained immunity suppression determines kidney allograft survival

Author

Jonkman, Inge, Jacobs, Maaike M.E., Negishi, Yutaka, Yanginlar, Cansu, Martens, Joost H.A., Baltissen, Marijke, Vermeulen, Michiel, van den Hoogen, Martijn W.F., Baas, Marije, van der Vlag, Johan, Fayad, Zahi A., Teunissen, Abraham J.P., Madsen, Joren C., Ochando, Jordi, Joosten, Leo A.B., Netea, Mihai G., Mulder, Willem J.M., Mhlanga, Musa M., Hilbrands, Luuk B., Rother, Nils, and Duivenvoorden, Raphaël

Published
2024
Full Text
View/download PDF

13. Author Correction: Clonally expanded CD8 T cells characterize amyotrophic lateral sclerosis-4

Author

Campisi, Laura, Chizari, Shahab, Ho, Jessica SY, Gromova, Anastasia, Arnold, Frederick J, Mosca, Lorena, Mei, Xueyan, Fstkchyan, Yesai, Torre, Denis, Beharry, Cindy, Garcia-Forn, Marta, Jiménez-Alcázar, Miguel, Korobeynikov, Vladislav A, Prazich, Jack, Fayad, Zahi A, Seldin, Marcus M, De Rubeis, Silvia, Bennett, Craig L, Ostrow, Lyle W, Lunetta, Christian, Squatrito, Massimo, Byun, Minji, Shneider, Neil A, Jiang, Ning, La Spada, Albert R, and Marazzi, Ivan

Subjects
General Science & Technology
Published
2022

14. Clonally expanded CD8 T cells characterize amyotrophic lateral sclerosis-4

Author

Campisi, Laura, Chizari, Shahab, Ho, Jessica SY, Gromova, Anastasia, Arnold, Frederick J, Mosca, Lorena, Mei, Xueyan, Fstkchyan, Yesai, Torre, Denis, Beharry, Cindy, Garcia-Forn, Marta, Jiménez-Alcázar, Miguel, Korobeynikov, Vladislav A, Prazich, Jack, Fayad, Zahi A, Seldin, Marcus M, De Rubeis, Silvia, Bennett, Craig L, Ostrow, Lyle W, Lunetta, Christian, Squatrito, Massimo, Byun, Minji, Shneider, Neil A, Jiang, Ning, La Spada, Albert R, and Marazzi, Ivan

Subjects
Biomedical and Clinical Sciences, Immunology, ALS, Neurodegenerative, Brain Disorders, Neurosciences, Rare Diseases, Genetics, 2.1 Biological and endogenous factors, Neurological, Inflammatory and immune system, Animals, Mice, Amyotrophic Lateral Sclerosis, CD8-Positive T-Lymphocytes, Clone Cells, DNA Helicases, Gene Knock-In Techniques, Motor Neurons, Multifunctional Enzymes, Mutation, RNA Helicases, Humans, General Science & Technology
Abstract

Amyotrophic lateral sclerosis (ALS) is a heterogenous neurodegenerative disorder that affects motor neurons and voluntary muscle control1. ALS heterogeneity includes the age of manifestation, the rate of progression and the anatomical sites of symptom onset. Disease-causing mutations in specific genes have been identified and define different subtypes of ALS1. Although several ALS-associated genes have been shown to affect immune functions2, whether specific immune features account for ALS heterogeneity is poorly understood. Amyotrophic lateral sclerosis-4 (ALS4) is characterized by juvenile onset and slow progression3. Patients with ALS4 show motor difficulties by the time that they are in their thirties, and most of them require devices to assist with walking by their fifties. ALS4 is caused by mutations in the senataxin gene (SETX). Here, using Setx knock-in mice that carry the ALS4-causative L389S mutation, we describe an immunological signature that consists of clonally expanded, terminally differentiated effector memory (TEMRA) CD8 T cells in the central nervous system and the blood of knock-in mice. Increased frequencies of antigen-specific CD8 T cells in knock-in mice mirror the progression of motor neuron disease and correlate with anti-glioma immunity. Furthermore, bone marrow transplantation experiments indicate that the immune system has a key role in ALS4 neurodegeneration. In patients with ALS4, clonally expanded TEMRA CD8 T cells circulate in the peripheral blood. Our results provide evidence of an antigen-specific CD8 T cell response in ALS4, which could be used to unravel disease mechanisms and as a potential biomarker of disease state.

Published
2022

15. Resolving sepsis-induced immunoparalysis via trained immunity by targeting interleukin-4 to myeloid cells

Author

Schrijver, David P., Röring, Rutger J., Deckers, Jeroen, de Dreu, Anne, Toner, Yohana C., Prevot, Geoffrey, Priem, Bram, Munitz, Jazz, Nugraha, Eveline G., van Elsas, Yuri, Azzun, Anthony, Anbergen, Tom, Groh, Laszlo A., Becker, Anouk M. D., Pérez-Medina, Carlos, Oosterwijk, Roderick S., Novakovic, Boris, Moorlag, Simone J. C. F. M., Jansen, Aron, Pickkers, Peter, Kox, Matthijs, Beldman, Thijs J., Kluza, Ewelina, van Leent, Mandy M. T., Teunissen, Abraham J. P., van der Meel, Roy, Fayad, Zahi A., Joosten, Leo A. B., Fisher, Edward A., Merkx, Maarten, Netea, Mihai G., and Mulder, Willem J. M.

Published
2023
Full Text
View/download PDF

17. U-Net Based Segmentation and Characterization of Gliomas

Author

Kihira, Shingo, Mei, Xueyan, Mahmoudi, Keon, Liu, Zelong, Dogra, Siddhant, Belani, Puneet, Tsankova, Nadejda, Hormigo, Adilia, Fayad, Zahi A, Doshi, Amish, and Nael, Kambiz

Subjects
Biomedical and Clinical Sciences, Oncology and Carcinogenesis, Brain Disorders, Brain Cancer, Cancer, Rare Diseases, Neurosciences, deep learning, glioma, tumor segmentation, radiogenomic, isocitrate dehydrogenase 1, magnetic resonance imaging, Oncology and carcinogenesis
Abstract

(1) Background: Gliomas are the most common primary brain neoplasms accounting for roughly 40−50% of all malignant primary central nervous system tumors. We aim to develop a deep learning-based framework for automated segmentation and prediction of biomarkers and prognosis in patients with gliomas. (2) Methods: In this retrospective two center study, patients were included if they (1) had a diagnosis of glioma with known surgical histopathology and (2) had preoperative MRI with FLAIR sequence. The entire tumor volume including FLAIR hyperintense infiltrative component and necrotic and cystic components was segmented. Deep learning-based U-Net framework was developed based on symmetric architecture from the 512 × 512 segmented maps from FLAIR as the ground truth mask. (3) Results: The final cohort consisted of 208 patients with mean ± standard deviation of age (years) of 56 ± 15 with M/F of 130/78. DSC of the generated mask was 0.93. Prediction for IDH-1 and MGMT status had a performance of AUC 0.88 and 0.62, respectively. Survival prediction of

Published
2022

18. Hybrid Magnetic Resonance Positron Emission Tomography Is Associated With Cardiac-Related Outcomes in Cardiac Sarcoidosis

Author

Trivieri, Maria Giovanna, Robson, Philip M., Vergani, Vittoria, LaRocca, Gina, Romero-Daza, Angelica M., Abgral, Ronan, Devesa, Ana, Azoulay, Levi-Dan, Karakatsanis, Nicolas A., Parikh, Aditya, Panagiota, Christia, Palmisano, Anna, DePalo, Louis, Chang, Helena L., Rothstein, Joseph H., Fayad, Rima A., Miller, Marc A., Fuster, Valentin, Narula, Jagat, Dweck, Marc R., Morgenthau, Adam, Jacobi, Adam, Padilla, Maria, Kovacic, Jason C., and Fayad, Zahi A.

Published
2024
Full Text
View/download PDF

19. 18F-FDG PET/CT in left ventricular assist device infections: In-depth characterization and clinical implications

Author

Devesa, Ana, Rashed, Eman, Moss, Noah, Robson, Philip M., Pyzik, Renata, Roldan, Julie, Taimur, Sarah, Rana, Meenakshi M., Ashley, Kimberly, Young, Anna, Patel, Gopi, Mahmood, Kiran, Mitter, Sumeet S., Lala, Anuradha, Barghash, Maya, Fox, Arieh, Correa, Ashish, Pirlamarla, Preethi, Contreras, Johanna, Parikh, Aditya, Mancini, Donna, Jacobi, Adam, Ghesani, Nasrin, Gavane, Somali C., Ghesani, Munir, Itagaki, Shinobu, Anyanwu, Anelechi, Fayad, Zahi A., and Trivieri, Maria Giovanna

Published
2024
Full Text
View/download PDF

21. Systems immunology-based drug repurposing framework to target inflammation in atherosclerosis

Author

Amadori, Letizia, Calcagno, Claudia, Fernandez, Dawn M., Koplev, Simon, Fernandez, Nicolas, Kaur, Ravneet, Mury, Pauline, Khan, Nayaab S, Sajja, Swathy, Shamailova, Roza, Cyr, Yannick, Jeon, Minji, Hill, Christopher A., Chong, Peik Sean, Naidu, Sonum, Sakurai, Ken, Ghotbi, Adam Ali, Soler, Raphael, Eberhardt, Natalia, Rahman, Adeeb, Faries, Peter, Moore, Kathryn J., Fayad, Zahi A., Ma’ayan, Avi, and Giannarelli, Chiara

Published
2023
Full Text
View/download PDF

23. Acid ceramidase regulates innate immune memory

Author

Rother, Nils, Yanginlar, Cansu, Prévot, Geoffrey, Jonkman, Inge, Jacobs, Maaike, van Leent, Mandy M.T., van Heck, Julia, Matzaraki, Vasiliki, Azzun, Anthony, Morla-Folch, Judit, Ranzenigo, Anna, Wang, William, van der Meel, Roy, Fayad, Zahi A., Riksen, Niels P., Hilbrands, Luuk B., Lindeboom, Rik G.H., Martens, Joost H.A., Vermeulen, Michiel, Joosten, Leo A.B., Netea, Mihai G., Mulder, Willem J.M., van der Vlag, Johan, Teunissen, Abraham J.P., and Duivenvoorden, Raphaël

Published
2023
Full Text
View/download PDF

27. Inhibition of thrombin-activatable fibrinolysis inhibitor via DS-1040 to accelerate clot lysis in patients with acute pulmonary embolism: a randomized phase 1b study

Author

Huisman, Menno, Tapson, Victor, Grosso, Michael, Segers, Annelise, Ageno, Walter, Brodmann, Marianne, Jimenez, David, Meyer, Guy, Middeldorp, Saskia, Rosovsky, Rachel, Schellong, Sebastian, Verhamme, Peter, Büller, Harry, Bossuyt, Patrick, van Es, Nick, Vanassche, Thomas, Rosovsky, Rachel P., Moustafa, Fares, Büller, Harry R., Patel, Indu, Shi, Minggao, Miyoshi, Naoki, Mani, Venkatesh, Fayad, Zahi, Stephan, Dominique, Schmidt, Jeannot, Grosso, Michael A., Tapson, Victor F., and Huisman, Menno V.

Published
2023
Full Text
View/download PDF

29. Multiparametric Immunoimaging Maps Inflammatory Signatures in Murine Myocardial Infarction Models

Author

Maier, Alexander, Toner, Yohana C., Munitz, Jazz, Sullivan, Nathaniel A.T., Sakurai, Ken, Meerwaldt, Anu E., Brechbühl, Eliane E.S., Prévot, Geoffrey, van Elsas, Yuri, Maas, Rianne J.F., Ranzenigo, Anna, Soultanidis, Georgios, Rashidian, Mohammad, Pérez-Medina, Carlos, Heo, Gyu Seong, Gropler, Robert J., Liu, Yongjian, Reiner, Thomas, Nahrendorf, Matthias, Swirski, Filip K., Strijkers, Gustav J., Teunissen, Abraham J.P., Calcagno, Claudia, Fayad, Zahi A., Mulder, Willem J.M., and van Leent, Mandy M.T.

Published
2023
Full Text
View/download PDF

32. Somatostatin Receptor PET/MR Imaging of Inflammation in Patients With Large Vessel Vasculitis and Atherosclerosis

Author

Ćorović, Andrej, Wall, Christopher, Nus, Meritxell, Gopalan, Deepa, Huang, Yuan, Imaz, Maria, Zulcinski, Michal, Peverelli, Marta, Uryga, Anna, Lambert, Jordi, Bressan, Dario, Maughan, Robert T., Pericleous, Charis, Dubash, Suraiya, Jordan, Natasha, Jayne, David R., Hoole, Stephen P., Calvert, Patrick A., Dean, Andrew F., Rassl, Doris, Barwick, Tara, Iles, Mark, Frontini, Mattia, Hannon, Greg, Manavaki, Roido, Fryer, Tim D., Aloj, Luigi, Graves, Martin J., Gilbert, Fiona J., Dweck, Marc R., Newby, David E., Fayad, Zahi A., Reynolds, Gary, Morgan, Ann W., Aboagye, Eric O., Davenport, Anthony P., Jørgensen, Helle F., Mallat, Ziad, Bennett, Martin R., Peters, James E., Rudd, James H.F., Mason, Justin C., and Tarkin, Jason M.

Published
2023
Full Text
View/download PDF

37. Publisher Correction: Systems immunology-based drug repurposing framework to target inflammation in atherosclerosis

Author

Amadori, Letizia, Calcagno, Claudia, Fernandez, Dawn M., Koplev, Simon, Fernandez, Nicolas, Kaur, Ravneet, Mury, Pauline, Khan, Nayaab S, Sajja, Swathy, Shamailova, Roza, Cyr, Yannick, Jeon, Minji, Hill, Christopher A., Chong, Peik Sean, Naidu, Sonum, Sakurai, Ken, Ghotbi, Adam Ali, Soler, Raphael, Eberhardt, Natalia, Rahman, Adeeb, Faries, Peter, Moore, Kathryn J., Fayad, Zahi A., Ma’ayan, Avi, and Giannarelli, Chiara

Published
2023
Full Text
View/download PDF

39. Systematically evaluating DOTATATE and FDG as PET immuno-imaging tracers of cardiovascular inflammation

Author

Toner, Yohana C., Ghotbi, Adam A., Naidu, Sonum, Sakurai, Ken, van Leent, Mandy M. T., Jordan, Stefan, Ordikhani, Farideh, Amadori, Letizia, Sofias, Alexandros Marios, Fisher, Elizabeth L., Maier, Alexander, Sullivan, Nathaniel, Munitz, Jazz, Senders, Max L., Mason, Christian, Reiner, Thomas, Soultanidis, Georgios, Tarkin, Jason M., Rudd, James H. F., Giannarelli, Chiara, Ochando, Jordi, Pérez-Medina, Carlos, Kjaer, Andreas, Mulder, Willem J. M., Fayad, Zahi A., and Calcagno, Claudia

Published
2022
Full Text
View/download PDF

43. An assessment of PET and CMR radiomic features for the detection of cardiac sarcoidosis.

Author

Mushari, Nouf A., Soultanidis, Georgios, Duff, Lisa, Trivieri, Maria G., Fayad, Zahi A., Robson, Philip, and Tsoumpas, Charalampos

Subjects
LEFT heart ventricle, RANDOM forest algorithms, POISSON distribution, STATISTICAL correlation, CARDIOMYOPATHIES, RADIOPHARMACEUTICALS, DIAGNOSTIC imaging, RESEARCH funding, RECEIVER operating characteristic curves, DATA analysis, RADIOMICS, DEOXY sugars, LOGISTIC regression analysis, SARCOIDOSIS, POSITRON emission tomography, MAGNETIC resonance imaging, DESCRIPTIVE statistics, SEVERITY of illness index, RETROSPECTIVE studies, MANN Whitney U Test, SUPPORT vector machines, MEDICAL records, ACQUISITION of data, STATISTICS, RESEARCH, INFLAMMATION, MACHINE learning, AUTOMATION, DATA analysis software, CONFIDENCE intervals, COVID-19, SENSITIVITY & specificity (Statistics)
Abstract

Background: Visual interpretation of PET and CMR may fail to identify cardiac sarcoidosis (CS) with high specificity. This study aimed to evaluate the role of [18F]FDG PET and late gadolinium enhancement (LGE)-CMR radiomic features in differentiating CS from another cause of myocardial inflammation, in this case patients with cardiac-related clinical symptoms following COVID-19. Methods: [18F]FDG PET and LGE-CMR were treated separately in this work. There were 35 post-COVID-19 (PC) and 40 CS datasets. Regions of interest were delineated manually around the entire left ventricle for the PET and LGE-CMR datasets. Radiomic features were then extracted. The ability of individual features to correctly identify image data as CS or PC was tested to predict the clinical classification of CS vs. PC using Mann--Whitney U-tests and logistic regression. Features were retained if the P-value was <0.00053, the AUC was >0.5, and the accuracy was >0.7. After applying the correlation test, uncorrelated features were used as a signature ( joint features) to train machine learning classifiers. For LGE-CMR analysis, to further improve the results, different classifiers were used for individual features besides logistic regression, and the results of individual features of each classifier were screened to create a signature that included all features that followed the previously mentioned criteria and used it them as input for machine learning classifiers. Results: The Mann--Whitney U-tests and logistic regression were trained on individual features to build a collection of features. For [18F]FDG PET analysis, the maximum target-to-background ratio (TBRmax) showed a high area under the curve (AUC) and accuracy with small P-values (<0.00053), but the signature performed better (AUC 0.98 and accuracy 0.91). For LGE-CMR analysis, the Gray Level Dependence Matrix (gldm)-Dependence Non-Uniformity showed good results with small error bars (accuracy 0.75 and AUC 0.87). However, by applying a Support Vector Machine classifier to individual LGE-CMR features and creating a signature, a Random Forest classifier displayed better AUC and accuracy (0.91 and 0.84, respectively). Conclusion: Using radiomic features may prove useful in identifying individuals with CS. Some features showed promising results in differentiating between PC and CS. By automating the analysis, the patient management process can be accelerated and improved. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

44. A review of self‐supervised, generative, and few‐shot deep learning methods for data‐limited magnetic resonance imaging segmentation.

Author

Liu, Zelong, Kainth, Komal, Zhou, Alexander, Deyer, Timothy W., Fayad, Zahi A., Greenspan, Hayit, and Mei, Xueyan

Subjects
MAGNETIC resonance imaging, DEEP learning, IMAGE segmentation, SUPERVISED learning, DIAGNOSTIC imaging
Abstract

Magnetic resonance imaging (MRI) is a ubiquitous medical imaging technology with applications in disease diagnostics, intervention, and treatment planning. Accurate MRI segmentation is critical for diagnosing abnormalities, monitoring diseases, and deciding on a course of treatment. With the advent of advanced deep learning frameworks, fully automated and accurate MRI segmentation is advancing. Traditional supervised deep learning techniques have advanced tremendously, reaching clinical‐level accuracy in the field of segmentation. However, these algorithms still require a large amount of annotated data, which is oftentimes unavailable or impractical. One way to circumvent this issue is to utilize algorithms that exploit a limited amount of labeled data. This paper aims to review such state‐of‐the‐art algorithms that use a limited number of annotated samples. We explain the fundamental principles of self‐supervised learning, generative models, few‐shot learning, and semi‐supervised learning and summarize their applications in cardiac, abdomen, and brain MRI segmentation. Throughout this review, we highlight algorithms that can be employed based on the quantity of annotated data available. We also present a comprehensive list of notable publicly available MRI segmentation datasets. To conclude, we discuss possible future directions of the field—including emerging algorithms, such as contrastive language‐image pretraining, and potential combinations across the methods discussed—that can further increase the efficacy of image segmentation with limited labels. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

45. Remote Short Sessions of Heart Rate Variability Biofeedback Monitored With Wearable Technology: Open-Label Prospective Feasibility Study

Author

Hirten, Robert P, primary, Danieletto, Matteo, additional, Landell, Kyle, additional, Zweig, Micol, additional, Golden, Eddye, additional, Pyzik, Renata, additional, Kaur, Sparshdeep, additional, Chang, Helena, additional, Helmus, Drew, additional, Sands, Bruce E, additional, Charney, Dennis, additional, Nadkarni, Girish, additional, Bagiella, Emilia, additional, Keefer, Laurie, additional, and Fayad, Zahi A, additional

Published
2024
Full Text
View/download PDF

48. Effect of Stress-Related Neural Pathways on the Cardiovascular Benefit of Physical Activity

Author

Zureigat, Hadil, primary, Osborne, Michael T., additional, Abohashem, Shady, additional, Mezue, Kenechukwu, additional, Gharios, Charbel, additional, Grewal, Simran, additional, Cardeiro, Alex, additional, Naddaf, Nicki, additional, Civieri, Giovanni, additional, Abbasi, Taimur, additional, Radfar, Azar, additional, Aldosoky, Wesam, additional, Seligowski, Antonia V., additional, Wasfy, Meagan M., additional, Guseh, James Sawalla, additional, Churchill, Timothy W., additional, Rosovsky, Rachel P., additional, Fayad, Zahi, additional, Rosenzweig, Anthony, additional, Baggish, Aaron, additional, Pitman, Roger K., additional, Choi, Karmel W., additional, Smoller, Jordan, additional, Shin, Lisa M., additional, and Tawakol, Ahmed, additional

Published
2024
Full Text
View/download PDF

50. VISION-MAE: A Foundation Model for Medical Image Segmentation and Classification

Author

Liu, Zelong, Tieu, Andrew, Patel, Nikhil, Zhou, Alexander, Soultanidis, George, Fayad, Zahi A., Deyer, Timothy, Mei, Xueyan, Liu, Zelong, Tieu, Andrew, Patel, Nikhil, Zhou, Alexander, Soultanidis, George, Fayad, Zahi A., Deyer, Timothy, and Mei, Xueyan

Abstract

Artificial Intelligence (AI) has the potential to revolutionize diagnosis and segmentation in medical imaging. However, development and clinical implementation face multiple challenges including limited data availability, lack of generalizability, and the necessity to incorporate multi-modal data effectively. A foundation model, which is a large-scale pre-trained AI model, offers a versatile base that can be adapted to a variety of specific tasks and contexts. Here, we present a novel foundation model, VISION-MAE, specifically designed for medical imaging. Specifically, VISION-MAE is trained on a dataset of 2.5 million unlabeled images from various modalities (CT, MR, PET, X-rays, and ultrasound), using self-supervised learning techniques. It is then adapted to classification and segmentation tasks using explicit labels. VISION-MAE has high label efficiency, outperforming several benchmark models in both in-domain and out-of-domain applications, and achieves high performance even with reduced availability of labeled data. This model represents a significant advancement in medical imaging AI, offering a generalizable and robust solution for improving segmentation and classification tasks while reducing the data annotation workload.

Published
2024

Catalog

Books, media, physical & digital resources
See catalog results