scholarly journals Decision Tree With Only Two Musculoskeletal Sites to Diagnose Polymyalgia Rheumatica Using [18F]FDG PET-CT

2021 ◽  
Vol 8 ◽  
Author(s):  
Anthime Flaus ◽  
Julie Amat ◽  
Nathalie Prevot ◽  
Louis Olagne ◽  
Lucie Descamps ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Tree ◽  
Polymyalgia Rheumatica ◽  
Fdg Pet ◽  
Validation Cohort ◽  
Learning Algorithm ◽  
Final Diagnosis ◽  
Machine Learning Algorithm ◽  
Pet Ct ◽  
Fdg Pet Ct

Introduction: The aim of this study was to find the best ordered combination of two FDG positive musculoskeletal sites with a machine learning algorithm to diagnose polymyalgia rheumatica (PMR) vs. other rheumatisms in a cohort of patients with inflammatory rheumatisms.Methods: This retrospective study included 140 patients who underwent [18F]FDG PET-CT and whose final diagnosis was inflammatory rheumatism. The cohort was randomized, stratified on the final diagnosis into a training and a validation cohort. FDG uptake of 17 musculoskeletal sites was evaluated visually and set positive if uptake was at least equal to that of the liver. A decision tree classifier was trained and validated to find the best combination of two positives sites to diagnose PMR. Diagnosis performances were measured first, for each musculoskeletal site, secondly for combination of two positive sites and thirdly using the decision tree created with machine learning.Results: 55 patients with PMR and 85 patients with other inflammatory rheumatisms were included. Musculoskeletal sites, used either individually or in combination of two, were highly imbalanced to diagnose PMR with a high specificity and a low sensitivity. The machine learning algorithm identified an optimal ordered combination of two sites to diagnose PMR. This required a positive interspinous bursa or, if negative, a positive trochanteric bursa. Following the decision tree, sensitivity and specificity to diagnose PMR were respectively 73.2 and 87.5% in the training cohort and 78.6 and 80.1% in the validation cohort.Conclusion: Ordered combination of two visually positive sites leads to PMR diagnosis with an accurate sensitivity and specificity vs. other rheumatisms in a large cohort of patients with inflammatory rheumatisms.

Abstract WP406: Training and Validation of Deepmedic Machine Learning Tool for Automated Hematoma Segmentation and Volume Analysis on CT Using Multicenter Data

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Sean Nurmsoo ◽  
Alessandro Guida ◽  
Alex Wong ◽  
Richard I Aviv ◽  
Andrew Demchuk ◽  
...  
Keyword(s):  
Machine Learning ◽  
Validation Cohort ◽  
Learning Algorithm ◽  
Intraclass Correlation ◽  
Ct Scans ◽  
Dice Similarity Coefficient ◽  
Machine Learning Algorithm ◽  
Manual Segmentation ◽  
Training Cohort ◽  
Volume Calculation

Introduction: We sought to train and validate an automated machine learning algorithm for ICH segmentation and volume calculation using multicenter data. Methods: An open-source 3D deep machine learning algorithm “DeepMedic” was trained using manually segmented ICH from 208 CT scans (129 patients) from the multicenter PREDICT study. The algorithm was then validated with 125 manually segmented CT scans (48 patients) from the SPOTLIGHT study. Manual segmentation was performed with Quantomo semi-automated software. ABC/2 was measured for all studies by two neuroradiologists. Accuracy of DeepMedic segmentation was assessed using the Dice similarity coefficient. Analysis was stratified by presence of IVH. Intraclass correlation (ICC) with 95% confidence intervals (CI) assessed agreement between manual vs. DeepMedic segmentation volume; and manual segmentation and ABC/2 volume. Bland-Altman charts were analyzed for ABC/2 and DeepMedic vs. manual segmentation volumes. Results: DeepMedic demonstrated high segmentation accuracy in the training cohort (median Dice 0.96; IQR 0.95 - 0.97) and in the validation cohort (median Dice 0.91; IQR 0.86 - 0.94). Dice coefficients were not significantly different between patients with IVH in the training cohort; however was significantly worse in the validation cohort in patients with IVH (Wilcoxon p<0.001). Agreement was significantly better between DeepMedic and manual segmentation (PREDICT: ICC 0.99 [95%CI 0.99 -1.00]; SPOTLIGHT: ICC 0.98 [95%CI 0.97 - 0.99]) than between ABC/2 and manual segmentation (PREDICT: ICC 0.92 [95%CI 0.89 - 0.95]; SPOTLIGHT: ICC 0.95 [95%CI 0.93-0.97]). Improved accuracy of DeepMedic was demonstrated in Bland-Altman charts (Fig 1). Conclusion: ICH machine learning segmentation with DeepMedic is feasible and accurate; and demonstrates greater agreement with manual segmentation compared to ABC/2 volumes. Accuracy of the machine learning algorithm however is limited in patients with IVH.

scholarly journals Evaluation of FDG-PET/CT Use in Children with Suspected Infection or Inflammation

Diagnostics ◽  
2020 ◽  
Vol 10 (9) ◽  
pp. 715
Author(s):  
Fabienne G. Ropers ◽  
Robin M. P. van Mossevelde ◽  
Chantal P. Bleeker-Rovers ◽  
Floris H. P. van Velden ◽  
Danielle M. E. van Assema ◽  
...  
Keyword(s):  
Fdg Pet ◽  
Final Diagnosis ◽  
Management Decisions ◽  
Multicenter Cohort Study ◽  
Disease Manifestation ◽  
Suspected Infection ◽  
Pet Ct ◽  
Fdg Pet Ct ◽  
The Impact

[18F]-FDG-PET/CT ([18F]-fluoro-deoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT)) is increasingly used as a diagnostic tool in suspected infectious or inflammatory conditions. Studies on the value of FDG-PET/CT in children are scarce. This study assesses the role of FDG-PET/CT in suspected infection or inflammation in children. In this multicenter cohort study, 64 scans in 59 children with suspected infection or inflammation were selected from 452 pediatric FDG-PET/CT scans, performed in five hospitals between January 2016 and August 2017. Main outcomes were diagnostic information provided by FDG-PET/CT for diagnostic scans and impact on clinical management for follow-up scans. Of these 64 scans, 50 were performed for primary diagnosis and 14 to monitor disease activity. Of the positive diagnostic scans, 23/27 (85%) contributed to establishing a diagnosis. Of the negative diagnostic scans, 8/21 (38%) contributed to the final diagnosis by narrowing the differential or by providing information on the disease manifestation. In all follow-up scans, FDG-PET/CT results guided management decisions. CRP was significantly higher in positive scans than in negative scans (p = 0.004). In 6% of diagnostic scans, relevant incidental findings were identified. In conclusion, FDG-PET/CT performed in children with suspected infection or inflammation resulted in information that contributed to the final diagnosis or helped to guide management decisions in the majority of cases. Prospective studies assessing the impact of FDG-PET/CT results on diagnosis and patient management using a structured diagnostic protocol are feasible and necessary.

scholarly journals Predicting Bank Operational Efficiency Using Machine Learning Algorithm: Comparative Study of Decision Tree, Random Forest, and Neural Networks

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Peter Appiahene ◽  
Yaw Marfo Missah ◽  
Ussiph Najim
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Decision Tree ◽  
Banking Sector ◽  
Banking Industry ◽  
Predictive Accuracy ◽  
Learning Algorithm ◽  
Machine Learning Algorithms ◽  
Machine Learning Algorithm ◽  
And Performance

The financial crisis that hit Ghana from 2015 to 2018 has raised various issues with respect to the efficiency of banks and the safety of depositors’ in the banking industry. As part of measures to improve the banking sector and also restore customers’ confidence, efficiency and performance analysis in the banking industry has become a hot issue. This is because stakeholders have to detect the underlying causes of inefficiencies within the banking industry. Nonparametric methods such as Data Envelopment Analysis (DEA) have been suggested in the literature as a good measure of banks’ efficiency and performance. Machine learning algorithms have also been viewed as a good tool to estimate various nonparametric and nonlinear problems. This paper presents a combined DEA with three machine learning approaches in evaluating bank efficiency and performance using 444 Ghanaian bank branches, Decision Making Units (DMUs). The results were compared with the corresponding efficiency ratings obtained from the DEA. Finally, the prediction accuracies of the three machine learning algorithm models were compared. The results suggested that the decision tree (DT) and its C5.0 algorithm provided the best predictive model. It had 100% accuracy in predicting the 134 holdout sample dataset (30% banks) and a P value of 0.00. The DT was followed closely by random forest algorithm with a predictive accuracy of 98.5% and a P value of 0.00 and finally the neural network (86.6% accuracy) with a P value 0.66. The study concluded that banks in Ghana can use the result of this study to predict their respective efficiencies. All experiments were performed within a simulation environment and conducted in R studio using R codes.

scholarly journals Diagnostic Value of 18F-FDG-PET/CT in Patients with FUO

2020 ◽  
Vol 9 (7) ◽  
pp. 2112
Author(s):  
Stamata Georga ◽  
Paraskevi Exadaktylou ◽  
Ioannis Petrou ◽  
Dimitrios Katsampoukas ◽  
Vasilios Mpalaris ◽  
...  
Keyword(s):  
Predictive Value ◽  
Fdg Pet ◽  
Final Diagnosis ◽  
Diagnostic Value ◽  
Whole Body ◽  
Considerable Proportion ◽  
Clinical Criteria ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

Conventional diagnostic imaging is often ineffective in revealing the underlying cause in a considerable proportion of patients with fever of unknown origin (FUO). The aim of this study was to assess the diagnostic value of fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG-PET/CT) in patients with FUO. We retrospectively reviewed 18F-FDG-PET/CT scans performed on 50 consecutive adult patients referred to our department for further investigation of classic FUO. Final diagnosis was based on histopathological and microbiological findings, clinical criteria, or clinical follow-up. Final diagnosis was established in 39/50 (78%) of the patients. The cause of FUO was infection in 20/50 (40%), noninfectious inflammatory diseases in 11/50 (22%), and malignancy in 8/50 (16%) patients. Fever remained unexplained in 11/50 (22%) patients. 18F-FDG-PET/CT scan substantially contributed to the diagnosis in 70% of the patients, either by identifying the underlying cause of FUO or by directing to the most appropriate site for biopsy. Sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) of 18F-FDG-PET/CT for active disease detection in patients with FUO were 94.7%, 50.0%, 84.0%, 85.7%, and 75.0%, respectively. In conclusion, whole-body 18F-FDG-PET/CT is a highly sensitive method for detection of the underlining cause of FUO or for correctly targeting suspicious lesions for further evaluation.

scholarly journals F-18 Fluorodeoxyglucose PET/CT as a Diagnostic Tool in Orbital Inflammatory Disorders

2021 ◽  
Author(s):  
Ghassan Elourimi ◽  
Michael Soussan ◽  
Matthieu Groh ◽  
Antoine Martin ◽  
Françoise Héran ◽  
...  
Keyword(s):  
Autoimmune Diseases ◽  
Diagnostic Tool ◽  
Fdg Pet ◽  
Final Diagnosis ◽  
Diagnostic Workup ◽  
Routine Practice ◽  
Inflammatory Disorders ◽  
Tertiary Referral Center ◽  
Pet Ct ◽  
Fdg Pet Ct

Abstract Background: In the last decade, FDG-PET/CT has become routine practice in the management of lymphoma or autoimmune diseases. In the current study, we aimed to assess the usefulness of FDG-PET/CT as a potential diagnostic tool for detecting underlying systemic diseases (SD) in patients with orbital inflammatory disorders (OID).Methods: All consecutive patients managed for new-onset OID between 2011 and 2018 in a tertiary referral center for OID, who underwent FDG-PET/CT as part as the etiological diagnostic workup were enrolled. PET-FDG/CT scans were reviewed blindly and were considered as positive for SD detection if they showed lymphadenopathy and/or other visceral lesions with an uptake above blood pool background. We used the standard diagnostic workup (performed in all patients at presentation) as relevant comparator. To quantify the incremental value of FDG-PET/CT over the standard diagnostic workup, the Net Reclassification Index (NRI) and Integrated Discrimination Index (IDI) were used. The final diagnosis was based on international criteria for autoimmune diseases, or histological confirmation for lymphoma, xanthogranuloma, crystal storing histiocytosis (CSH), or idiopathic orbital inflammation syndrome (IOIS). Results: Among the 22 patients enrolled, 14 (63%) had underlying SD (granulomatosis with polyangiitis (GPA), n=1; IgG4-related disease (IgG4-RD), n=5; CSH, n=1; adult onset asthma and periocular xanthogranuloma (AAPOX), n=3; lymphoma, n=4) while the remaining 8 (37%) patients were diagnosed with IOIS. Eleven (50%) patients had a positive FDG-PET/CT. After clinicobiological evaluation, FDG-PET/CT correctly reclassified 29% of patients with SD (p=0.04) and 13% with IOIS (p=0.3), corresponding to an elevated NRI of 0.41±0.17 (p=0.03). The IDI test used to evaluate the improvement of FDG-PET/CT for SD detection was 0.38±0.08 (p<0.001). After FDG-PET/CT, probability changes for SD and IOIS were measured at 0.14 and -0.24, respectively (relative gain of 3.04 for IDI). FDG-PET/CT successfully detected asymptomatic lesions in all patients with a final diagnosis of lymphoma. Conclusion: FDG-PET/CT enabled accurate reclassification of more than one quarter of patients with SD, suggesting its potential value for detecting SD (especially extraorbital lymphoma).

scholarly journals Infectious endocarditis: Improving Diagnostic Performance in Native and Prosthetic Valve Infection with 18F-FDG PET/CT

2020 ◽  
Author(s):  
Ana Vera Marinho ◽  
José Paulo Almeida ◽  
Paula Soeiro ◽  
Rodolfo Silva ◽  
Francisco Gonçalves ◽  
...  
Keyword(s):  
Fdg Pet ◽  
Diagnostic Performance ◽  
Final Diagnosis ◽  
Prosthetic Material ◽  
Native Valve ◽  
Clinical Challenge ◽  
Duke Criteria ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

Abstract BackgroundThe diagnosis of infective endocarditis (IE) remains a clinical challenge. Diagnostic accuracy of the modified Duke criteria is suboptimal for native valve endocarditis (NVE) and even worse in the presence of prosthetic material-related infection (PVE). We aim to evaluate the diagnostic performance of 18F-FDG PET in patients with suspected IE referred to perform PET/CT.Methods: Consecutive patients with suspected IE, referred to perform PET/CT between May 2016 and June 2019 were included. Diagnostic performance of modified Duke criteria (mDC) and PET/ CT for IE for NVE and PVE was determined.Results: In total, 82 patients (mean age of 61 ± 19 years, 62% of male gender) were enrolled. There were 67 18F-FDG PET/CT concordant results with final diagnosis, corresponding to a 96% of agreement, k=0.91(p=0.04). A SUVmax cutoff value of ≥3.1 identified positive cases with 88.9% sensitivity and 70.0% specificity. In patients with NVE, the addition of PET/CT to the mDC resulted in a reduction of the number of possible IE cases (from 58% to 4.3%). In patients with PVE/intracardiac devices, PET/CT allowed reclassification of 67.4% of possible cases to 4.2%. An alternative diagnosis was provided in 55.6% of the negative IE cases.Conclusions: 18F-FDG PET/CT proved to be a useful diagnostic tool in patients with both suspected NVE and PVE with good sensitivity and specificity, resulting in a significant decrease of the number of possible endocarditis. Furthermore, it allowed the identification of the cause of clinical scenario in more than 50% of patients in which the diagnosis was excluded.

scholarly journals Clinical presentation and treatment response in patients with polymyalgia rheumatica and giant cell arteritis during a 40-week follow-up

2021 ◽  
Author(s):  
Amir Emamifar ◽  
Søren Hess ◽  
Torkell Ellingsen ◽  
Oke Gerke ◽  
Ziba Ahangarani Farahani ◽  
...  
Keyword(s):  
Giant Cell Arteritis ◽  
Treatment Response ◽  
Giant Cell ◽  
Clinical Features ◽  
Polymyalgia Rheumatica ◽  
Fdg Pet ◽  
Temporal Artery Biopsy ◽  
Pet Ct ◽  
Fdg Pet Ct

Abstract Objectives To study the clinical features of polymyalgia rheumatica and/or giant cell arteritis (PMR/GCA) and clinical predictors of treatment response during a 40-week follow-up period. Method Clinical data on 77 patients with newly diagnosed PMR/GCA who were treated by oral glucocorticoids were gathered at baseline and during 40-week follow-up period. A unilateral temporal artery biopsy (TAB) and 18 F-FDG PET/CT were undertaken at diagnosis. In total, each patient was seen at 5 occasions i.e. baseline, weeks 4, 16, 28, and 40. Treatment response was assessed considering clinical evaluations and results of inflammatory markers. Results Of 77 patients (49(63.6%) female, mean age : 71.8 ± 8.0), 64(83.1%) patients had pure PMR, 10(13.0%) concomitant PMR and GCA, and 3(3.9%) pure GCA. The patients reported clinical symptoms except scalp pain and duration of morning stiffness improved significantly at week 4 and remained lower at week 40 compared with the relative frequencies at baseline. Besides, all components of physical examination showed significant improvement and remained lower at week 40 compared with the baseline. 68.7%, 62.9%, 44.1% and 33.3% of the patients had a complete response at weeks 4, 16, 28, and 40, respectively. Several clinical features including female gender, younger age, fewer relapse, and lower level of baseline ESR were significantly associated with a better treatment response. Treatment response during follow-up period was independent of TAB results and FDG uptakes on 18 F-FDG PET/CT at diagnosis. Conclusion Obtaining valid disease specific outcome measures for evaluating treatment efficacy in PMR and GCA, that can be applied universally is clearly an unmet clinical need. Trial registration ClinicalTrials.gov, https://clinicaltrials.gov, NCT02985424

scholarly journals Infectious endocarditis: Improving diagnostic performance in native and prosthetic valve infection with 18F-FDG PET/CT

2020 ◽  
Author(s):  
Ana Vera Marinho ◽  
José Paulo Almeida ◽  
Paula Soeiro ◽  
Rodolfo Silva ◽  
Francisco Gonçalves ◽  
...  
Keyword(s):  
Fdg Pet ◽  
Diagnostic Performance ◽  
Final Diagnosis ◽  
Prosthetic Material ◽  
Native Valve ◽  
Clinical Challenge ◽  
Duke Criteria ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

Abstract Background: The diagnosis of infective endocarditis (IE) remains a clinical challenge. Diagnostic accuracy of the modified Duke criteria is suboptimal for native valve endocarditis (NVE) and even worse in the presence of prosthetic material-related infection (PVE). We aim to evaluate the diagnostic performance of 18F-FDG PET in patients with suspected IE referred to perform PET/CT.Methods: Consecutive patients with suspected IE, referred to perform PET/CT between May 2016 and June 2019 were included. Diagnostic performance of modified Duke criteria (mDC) and PET/ CT for IE for NVE and PVE was determined.Results: In total, 82 patients (mean age of 61 ± 19 years, 62% of male gender) were enrolled. There were 67 18F-FDG PET/CT concordant results with final diagnosis, corresponding to a 96% of agreement, k=0.91(p=0.04). A SUV max cutoff value of ≥3.1 identified positive cases with 88.9% sensitivity and 70.0% specificity. In patients with NVE, the addition of PET/CT to the mDC resulted in a reduction of the number of possible IE cases (from 58% to 4.3%). In patients with PVE/intracardiac devices, PET/CT allowed reclassification of 67.4% of possible cases to 4.2%. An alternative diagnosis was provided in 55.6% of the negative IE cases.Conclusions: 18F-FDG PET/CT proved to be a useful diagnostic tool in patients with both suspected NVE and PVE with good sensitivity and specificity, resulting in a significant decrease of the number of possible endocarditis. Furthermore, it allowed the identification of the cause of clinical scenario in more than 50% of patients in which the diagnosis was excluded.

Sign in / Sign up

Export Citation Format

Share Document