Use of radiomics based on 18F-FDG PET/CT and machine learning methods to aid clinical decision-making in the classification of solitary pulmonary lesions: an innovative approach

2021 ◽  
Author(s):  
Yi Zhou ◽  
Xue-lei Ma ◽  
Ting Zhang ◽  
Jian Wang ◽  
Tao Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Pulmonary Lesions ◽  
Machine Learning Methods ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

scholarly journals Cardiovascular Mechanisms In Covid-19: Methodology of A Prospective Observational Multimodality Imaging Study (COSMIC-19 study)

2020 ◽  
Author(s):  
Shirjel Alam ◽  
Anoop Shah ◽  
Kevin Onyinkwa ◽  
Edward Nganga ◽  
Samuel Gitau ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Fdg Pet ◽  
Clinical Decision Making ◽  
Multimodality Imaging ◽  
Cardiac Injury ◽  
Imaging Study ◽  
Clinical Decision ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

Abstract Background: 8-28% of patients infected with COVID-19 have evidence of cardiac injury, and this is associated with an adverse prognosis. The cardiovascular mechanisms of injury are poorly understood and speculative. We aim to use multimodality cardiac imaging including cardiac magnetic resonance (CMR) imaging, computed tomography coronary angiography (CTCA) and positron emission tomography with 2-deoxy-2-[fluorine-18]fluoro- D-glucose integrated with computed tomography (18F-FDG-PET/CT) to identify the cardiac pathophysiological mechanisms related to COVID-19 infections.Methods: This is a single-centre exploratory observational study aiming to recruit 50 patients with COVID-19 infection who will undergo cardiac biomarker sampling. Of these, 30 patients will undergo combined CTCA & 18F-FDG-PET/CT, followed by CMR. Prevalence of obstructive and non-obstructive atherosclerotic coronary disease will be assessed using CTCA. CMR will be used to identify and characterise myocardial disease including presence of cardiac dysfunction, myocardial fibrosis, myocardial oedema and myocardial infarction. 18F-FDG-PET/CT will identify vascular and cardiac inflammation. Primary endpoint will be the presence of cardiovascular pathology and the association with troponin levels.Discussion: The results of the study will identify the presence and modality of cardiac injury associated COVID-19 infection, and the utility of multi-modality imaging in diagnosing such injury. This will further inform clinical decision making during the pandemic.TRIAL REGISTRATION: This study has been retrospectively registered at the ISRCTN registry (ID ISRCTN12154994) on 14th August 2020. Accessible at www.isrctn.com/ISRCTN12154994

18F-FDG PET/CT and respiratory synchronization: effect in the detection and classification of pulmonary lesions

2009 ◽  
Vol 28 (4) ◽  
pp. 181-187
Author(s):  
A.M. García Vicente ◽  
A. Soriano Castrejón ◽  
P. Talavera Rubio ◽  
V.M. Poblete García ◽  
A. Palomar Muñoz ◽  
...  
Keyword(s):  
Fdg Pet ◽  
Pulmonary Lesions ◽  
Pet Ct ◽  
18F Fdg ◽  
Respiratory Synchronization ◽  
Synchronization Effect ◽  
Fdg Pet Ct

scholarly journals CardiOvaScular Mechanisms In Covid-19: methodology of a prospective observational multimodality imaging study (COSMIC-19 study)

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Shirjel R. Alam ◽  
Anoop S. V. Shah ◽  
Kevin O. Ombati ◽  
Edward Nganga ◽  
Samuel Gitau ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Fdg Pet ◽  
Clinical Decision Making ◽  
Multimodality Imaging ◽  
Cardiac Injury ◽  
Imaging Study ◽  
Clinical Decision ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

Abstract Background 8–28% of patients infected with COVID-19 have evidence of cardiac injury, and this is associated with an adverse prognosis. The cardiovascular mechanisms of injury are poorly understood and speculative. We aim to use multimodality cardiac imaging including cardiac magnetic resonance (CMR) imaging, computed tomography coronary angiography (CTCA) and positron emission tomography with 2-deoxy-2-[fluorine-18]fluoro-d-glucose integrated with computed tomography (18F-FDG-PET/CT) to identify the cardiac pathophysiological mechanisms related to COVID-19 infections. Methods This is a single-centre exploratory observational study aiming to recruit 50 patients with COVID-19 infection who will undergo cardiac biomarker sampling. Of these, 30 patients will undergo combined CTCA and 18F-FDG-PET/CT, followed by CMR. Prevalence of obstructive and non-obstructive atherosclerotic coronary disease will be assessed using CTCA. CMR will be used to identify and characterise myocardial disease including presence of cardiac dysfunction, myocardial fibrosis, myocardial oedema and myocardial infarction. 18F-FDG-PET/CT will identify vascular and cardiac inflammation. Primary endpoint will be the presence of cardiovascular pathology and the association with troponin levels. Discussion The results of the study will identify the presence and modality of cardiac injury associated COVID-19 infection, and the utility of multi-modality imaging in diagnosing such injury. This will further inform clinical decision making during the pandemic. Trial Registration: This study has been retrospectively registered at the ISRCTN registry (ID ISRCTN12154994) on 14th August 2020. Accessible at https://www.isrctn.com/ISRCTN12154994

scholarly journals Use of PET/CT to aid clinical decision-making in cases of solitary pulmonary nodule: a probabilistic approach

2020 ◽  
Vol 53 (1) ◽  
pp. 1-6 ◽  
Author(s):  
Felipe Alves Mourato ◽  
Ana Emília Teixeira Brito ◽  
Monique Sampaio Cruz Romão ◽  
Renata Guerra Galvão Santos ◽  
Cristiana Altino de Almeida ◽  
...  
Keyword(s):  
Pulmonary Nodule ◽  
Fdg Pet ◽  
Clinical Decision Making ◽  
Solitary Pulmonary Nodule ◽  
Probabilistic Approach ◽  
Solitary Pulmonary Nodules ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

Abstract Objective: To determine the frequency with which 18F-FDG-PET/CT findings change the probability of malignancy classification of solitary pulmonary nodules. Materials and Methods: This was a retrospective analysis of all 18F-FDG-PET/CT examinations performed for the investigation of a solitary pulmonary nodule between May 2016 and May 2017. We reviewed medical records and PET/CT images to collect the data necessary to calculate the pre-test probability of malignancy using the Swensen model and the Herder model. The probability of malignancy was classified as low if < 5%, intermediate if 5-65%, and high if > 65%. Cases classified as intermediate in the Swensen model were reclassified by the Herder model. Results: We reviewed the records for 33 patients, of whom 17 (51.5%) were male. The mean age was 68.63 ± 12.20 years. According to the Swensen model, the probability of malignancy was intermediate in 23 cases (69.7%). Among those, the application of the Herder model resulted in the probability of malignancy being reclassified as low in 6 (26.1%) and as high in 8 (34.8%). Conclusion: 18F-FDG-PET/CT was able to modify the probability of malignancy classification of a solitary pulmonary nodule in more than 50% of the cases evaluated.

scholarly journals Value of 4-Dimensional 18F-FDG PET/CT in the Classification of Pulmonary Lesions

2011 ◽  
Vol 39 (2) ◽  
pp. 91-99 ◽  
Author(s):  
A. M. Garcia Vicente ◽  
A. S. Castrejon ◽  
A. A. Leon Martin ◽  
B. G. Garcia ◽  
J. P. Pilkington Woll ◽  
...  
Keyword(s):  
Fdg Pet ◽  
Pulmonary Lesions ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

scholarly journals CardiOvaScular Mechanisms In Covid-19: Methodology of a prospective observational multimodality imaging study (COSMIC-19 study)

2021 ◽  
Author(s):  
Shirjel Alam ◽  
Anoop Shah ◽  
Kevin Onyinkwa ◽  
Edward Nganga ◽  
Samuel Gitau ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Fdg Pet ◽  
Clinical Decision Making ◽  
Multimodality Imaging ◽  
Cardiac Injury ◽  
Imaging Study ◽  
Clinical Decision ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

Abstract Background: 8-28% of patients infected with COVID-19 have evidence of cardiac injury, and this is associated with an adverse prognosis. The cardiovascular mechanisms of injury are poorly understood and speculative. We aim to use multimodality cardiac imaging including cardiac magnetic resonance (CMR) imaging, computed tomography coronary angiography (CTCA) and positron emission tomography with 2-deoxy-2-[fluorine-18]fluoro- D-glucose integrated with computed tomography (18F-FDG-PET/CT) to identify the cardiac pathophysiological mechanisms related to COVID-19 infections.Methods: This is a single-centre exploratory observational study aiming to recruit 50 patients with COVID-19 infection who will undergo cardiac biomarker sampling. Of these, 30 patients will undergo combined CTCA & 18F-FDG-PET/CT, followed by CMR. Prevalence of obstructive and non-obstructive atherosclerotic coronary disease will be assessed using CTCA. CMR will be used to identify and characterise myocardial disease including presence of cardiac dysfunction, myocardial fibrosis, myocardial oedema and myocardial infarction. 18F-FDG-PET/CT will identify vascular and cardiac inflammation. Primary endpoint will be the presence of cardiovascular pathology and the association with troponin levels. Discussion: The results of the study will identify the presence and modality of cardiac injury associated COVID-19 infection, and the utility of multi-modality imaging in diagnosing such injury. This will further inform clinical decision making during the pandemic. TRIAL REGISTRATION: This study has been retrospectively registered at the ISRCTN registry (ID ISRCTN12154994) on 14th August 2020. Accessible at www.isrctn.com/ISRCTN12154994

Machine learning in clinical decision making

Med ◽  
2021 ◽  
Author(s):  
Lorenz Adlung ◽  
Yotam Cohen ◽  
Uria Mor ◽  
Eran Elinav
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Decision

scholarly journals Machine-learning based prediction of Cushing’s syndrome in dogs attending UK primary-care veterinary practice

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Imogen Schofield ◽  
David C. Brodbelt ◽  
Noel Kennedy ◽  
Stijn J. M. Niessen ◽  
David B. Church ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cushing’S Syndrome ◽  
Clinical Decision Making ◽  
Predictive Performance ◽  
Clinical Decision ◽  
Cushing's Syndrome ◽  
Machine Learning Algorithms ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Clinical Records

AbstractCushing’s syndrome is an endocrine disease in dogs that negatively impacts upon the quality-of-life of affected animals. Cushing’s syndrome can be a challenging diagnosis to confirm, therefore new methods to aid diagnosis are warranted. Four machine-learning algorithms were applied to predict a future diagnosis of Cushing's syndrome, using structured clinical data from the VetCompass programme in the UK. Dogs suspected of having Cushing's syndrome were included in the analysis and classified based on their final reported diagnosis within their clinical records. Demographic and clinical features available at the point of first suspicion by the attending veterinarian were included within the models. The machine-learning methods were able to classify the recorded Cushing’s syndrome diagnoses, with good predictive performance. The LASSO penalised regression model indicated the best overall performance when applied to the test set with an AUROC = 0.85 (95% CI 0.80–0.89), sensitivity = 0.71, specificity = 0.82, PPV = 0.75 and NPV = 0.78. The findings of our study indicate that machine-learning methods could predict the future diagnosis of a practicing veterinarian. New approaches using these methods could support clinical decision-making and contribute to improved diagnosis of Cushing’s syndrome in dogs.

Sign in / Sign up

Export Citation Format

Share Document