Evaluation of the Usefulness of CO-RADS for Chest CT in Patients Suspected of Having COVID-19

The purpose of this study was to use the Coronavirus Disease 2019 (COVID-19) Reporting and Data System (CO-RADS) to evaluate the chest computed tomography (CT) images of patients suspected of having COVID-19, and to investigate its diagnostic performance and interobserver agreement. The Dutch Radiological Society developed CO-RADS as a diagnostic indicator for assessing suspicion of lung involvement of COVID-19 on a scale of 1 (very low) to 5 (very high). We investigated retrospectively 154 adult patients with clinically suspected COVID-19, between April and June 2020, who underwent chest CT and reverse transcription-polymerase chain reaction (RT-PCR). The patients’ average age was 61.3 years (range, 21–93), 101 were male, and 76 were RT-PCR positive. Using CO-RADS, four radiologists evaluated the chest CT images. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. Interobserver agreement was calculated using the intraclass correlation coefficient (ICC) by comparing the individual reader’s score to the median of the remaining three radiologists. The average sensitivity was 87.8% (range, 80.2–93.4%), specificity was 66.4% (range, 51.3–84.5%), and AUC was 0.859 (range, 0.847–0.881); there was no significant difference between the readers (p > 0.200). In 325 (52.8%) of 616 observations, there was absolute agreement among observers. The average ICC of readers was 0.840 (range, 0.800–0.874; p < 0.001). CO-RADS is a categorical taxonomic evaluation scheme for COVID-19 pneumonia, using chest CT images, that provides outstanding performance and from substantial to almost perfect interobserver agreement for predicting COVID-19.

Download Full-text

Adaptation and Validation of the Mini-Addenbrooke’s Cognitive Examination in Dementia in Arabic Speakers in Egypt

Dementia and Geriatric Cognitive Disorders ◽

10.1159/000513411 ◽

2020 ◽

Vol 49 (6) ◽

pp. 611-616

Author(s):

Tarik Qassem ◽

Mohamed S. Khater ◽

Tamer Emara ◽

Doha Rasheedy ◽

Heba M. Tawfik ◽

...

Keyword(s):

Screening Tool ◽

Characteristic Curve ◽

High Sensitivity ◽

Receiver Operator Characteristic Curve ◽

Cutoff Score ◽

Arabic Speakers ◽

Dementia Patients ◽

Significant Difference ◽

Sensitivity Specificity ◽

Addenbrooke’S Cognitive Examination

Background: The mini-Addenbrooke’s Cognitive Examination (m-ACE) is a brief cognitive battery that assesses 5 subdomains of cognition (attention, memory, verbal fluency, visuospatial abilities, and memory recall). It is scored out of 30 and can be administered in under 5 min providing a quick screening tool for assessment of cognition. Objectives: We aimed to adapt the m-ACE in Arabic speakers in Egypt and to validate it in dementia patients to provide cutoff scores. Methods: We included 37 patients with dementia (Alzheimer’s disease [n = 25], vascular dementia [n = 8], and dementia with Lewy body [n = 4]) and 43 controls. Results: There was a statistically significant difference (p < 0.001) on the total m-ACE score between dementia patients (mean 10.54 and standard deviation [SD] 5.83) and controls (mean 24.02 and SD 2.75). There was also a statistically significant difference between dementia patients and controls on all sub-score domains of the m-ACE (p < 0.05). Performance on the m-ACE significantly correlated with both the Mini-Mental State Examination (MMSE) and the Addenbrooke’s Cognitive Examination-III (ACE-III). Using a receiver operator characteristic curve, the optimal cutoff score for dementia on the m-ACE total score was found to be 18 (92% sensitivity, 95% specificity, and 94% accuracy). Conclusions: We adapted the m-ACE in Arabic speakers in Egypt and provided objective validation of it as a screening tool for dementia, with high sensitivity, specificity, and accuracy.

Download Full-text

Detection of Incidental Esophageal Cancers on Chest CT by Deep Learning

Frontiers in Oncology ◽

10.3389/fonc.2021.700210 ◽

2021 ◽

Vol 11 ◽

Author(s):

He Sui ◽

Ruhang Ma ◽

Lin Liu ◽

Yaozong Gao ◽

Wenhai Zhang ◽

...

Keyword(s):

Esophageal Cancer ◽

Deep Learning ◽

Cancer Detection ◽

Ct Images ◽

Chest Ct ◽

Validation Dataset ◽

Esophageal Wall ◽

Detection Model ◽

Model Training ◽

Sensitivity Specificity

ObjectiveTo develop a deep learning-based model using esophageal thickness to detect esophageal cancer from unenhanced chest CT images.MethodsWe retrospectively identified 141 patients with esophageal cancer and 273 patients negative for esophageal cancer (at the time of imaging) for model training. Unenhanced chest CT images were collected and used to build a convolutional neural network (CNN) model for diagnosing esophageal cancer. The CNN is a VB-Net segmentation network that segments the esophagus and automatically quantifies the thickness of the esophageal wall and detect positions of esophageal lesions. To validate this model, 52 false negatives and 48 normal cases were collected further as the second dataset. The average performance of three radiologists and that of the same radiologists aided by the model were compared.ResultsThe sensitivity and specificity of the esophageal cancer detection model were 88.8% and 90.9%, respectively, for the validation dataset set. Of the 52 missed esophageal cancer cases and the 48 normal cases, the sensitivity, specificity, and accuracy of the deep learning esophageal cancer detection model were 69%, 61%, and 65%, respectively. The independent results of the radiologists had a sensitivity of 25%, 31%, and 27%; specificity of 78%, 75%, and 75%; and accuracy of 53%, 54%, and 53%. With the aid of the model, the results of the radiologists were improved to a sensitivity of 77%, 81%, and 75%; specificity of 75%, 74%, and 74%; and accuracy of 76%, 77%, and 75%, respectively.ConclusionsDeep learning-based model can effectively detect esophageal cancer in unenhanced chest CT scans to improve the incidental detection of esophageal cancer.

Download Full-text

Comparison of short-wavelength blue-light autofluorescence and conventional blue-light autofluorescence in geographic atrophy

British Journal of Ophthalmology ◽

10.1136/bjophthalmol-2018-311849 ◽

2018 ◽

Vol 103 (5) ◽

pp. 610-616 ◽

Cited By ~ 7

Author(s):

Enrico Borrelli ◽

Muneeswar Gupta Nittala ◽

Nizar Saleh Abdelfattah ◽

Jianqin Lei ◽

Amir H Hariri ◽

...

Keyword(s):

Blue Light ◽

Imaging Modality ◽

Fundus Autofluorescence ◽

Intraclass Correlation ◽

Geographic Atrophy ◽

Area Measurement ◽

Excitation Wavelength ◽

Lesion Area ◽

Significant Difference ◽

The Individual

Background/aimsTo systematically compare the intermodality and inter-reader agreement for two blue-light confocal fundus autofluorescence (FAF) systems.MethodsThirty eyes (21 patients) with a diagnosis of geographic atrophy (GA) were enrolled. Eyes were imaged using two confocal blue-light FAF devices: (1) Spectralis device with a 488 nm excitation wavelength (488-FAF); (2) EIDON device with 450 nm excitation wavelength and the capability for ‘colour’ FAF imaging including both the individual red and green components of the emission spectrum. Furthermore, a third imaging modality (450-RF image) isolating and highlighting the red emission fluorescence component (REFC) was obtained and graded. Each image was graded by two readers to assess inter-reader variability and a single image for each modality was used to assess the intermodality variability.ResultsThe 95% coefficient of repeatability (1.35 mm2 for the 488-FAF-based grading, 8.13 mm2 for the 450-FAF-based grading and 1.08 mm2 for the 450-RF-based grading), the coefficient of variation (1.11 for 488-FAF, 2.05 for 450-FAF, 0.92 for 450-RF) and the intraclass correlation coefficient (0.994 for 488-FAF, 0.711 for 450-FAF, 0.997 for 450-RF) indicated that 450-FAF-based and 450-RF-based grading have the lowest and highest inter-reader agreements, respectively. The GA area was larger for 488-FAF images (median (IQR) 2.1 mm2 (0.8–6.4 mm2)) than for 450-FAF images (median (IQR) 1.0 mm2 (0.3–4.3 mm2); p<0.0001). There was no significant difference in lesion area measurement between 488-FAF-based and 450-RF-based grading (median (IQR) 2.6 mm2 (0.8–6.8 mm2); p=1.0).ConclusionThe isolation of the REFC from the 450-FAF images allowed for a reproducible quantification of GA. This assessment had good comparability with that obtained with 488-FAF images.

Download Full-text

MRI may be able to identify the origin of neuroendocrine tumor liver metastases

Neuroendocrinology ◽

10.1159/000513015 ◽

2020 ◽

Author(s):

Maxime Barat ◽

Philippe Soyer ◽

Fatima Al Sharhan ◽

Benoit Terris ◽

Ammar Oudjit ◽

...

Keyword(s):

Multivariate Analysis ◽

Neuroendocrine Tumors ◽

Interobserver Agreement ◽

Validation Cohort ◽

Univariate Analysis ◽

Intraclass Correlation ◽

Hepatic Metastases ◽

Resonance Imaging ◽

Magnetic Resonance Imaging Mri ◽

Sensitivity Specificity

Objectives: To discriminate hepatic metastases from pancreatic neuroendocrine tumors (pNET) and hepatic metastases from midgut neuroendocrine tumors (mNET) with magnetic resonance imaging (MRI). Methods: MRI examinations of 24 patients with hepatic metastases from pNET were quantitatively and qualitatively assessed by two blinded readers and compared to those obtained in 23 patients with hepatic metastases from mNET. Inter-reader agreement was calculated with kappa and intraclass correlation coefficient (ICC). Sensitivity, specificity and accuracy of each variable for the diagnosis of hepatic metastasis from pNET were calculated. Associations between variables and primary tumor (i.e., pNET vs. mNET) were assessed at univariate and multivariate analysis. A nomogram was developed and validated using an external cohort of 20 patients with pNET and 20 patients with mNET. Results: Interobserver agreement was strong to perfect (k=0.893-1) for qualitative criteria and excellent for quantitative variables (ICC: 0.9817-0.9996). At univariate analysis, homogeneity on T1-weighted images was the most discriminating variable for the diagnosis of pNET (OR, 6.417; P=0.013) with greatest sensitivity (88%; 21/24; 95% CI: 68-97%). At multivariate analysis, tumor homogeneity on T1-weighted images (P=0.007; OR, 17.607; 95%CI: 2.179–142.295) and target sign on DW images (P=0.007; OR, 19.869; 95%CI: 2.305–171.276) were independently associated with pNET. Nomogram yielded a corrected AUC of 0.894 (95%CI: 0.796–0.992) for the diagnosis of pNET in the training cohort and 0.805 (95%CI: 0.662–0.948) in the validation cohort. Conclusions: MRI provides qualitative features that can help discriminate between hepatic metastases from pNET and those from mNET.

Download Full-text

COVIDNet-CT: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases From Chest CT Images

Frontiers in Medicine ◽

10.3389/fmed.2020.608525 ◽

2020 ◽

Vol 7 ◽

Author(s):

Hayden Gunraj ◽

Linda Wang ◽

Alexander Wong

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Network Architecture ◽

Ct Images ◽

Ct Imaging ◽

Chest Ct ◽

Deep Convolutional Neural Network ◽

Screening Tools ◽

Screening Methods ◽

Rt Pcr

The coronavirus disease 2019 (COVID-19) pandemic continues to have a tremendous impact on patients and healthcare systems around the world. In the fight against this novel disease, there is a pressing need for rapid and effective screening tools to identify patients infected with COVID-19, and to this end CT imaging has been proposed as one of the key screening methods which may be used as a complement to RT-PCR testing, particularly in situations where patients undergo routine CT scans for non-COVID-19 related reasons, patients have worsening respiratory status or developing complications that require expedited care, or patients are suspected to be COVID-19-positive but have negative RT-PCR test results. Early studies on CT-based screening have reported abnormalities in chest CT images which are characteristic of COVID-19 infection, but these abnormalities may be difficult to distinguish from abnormalities caused by other lung conditions. Motivated by this, in this study we introduce COVIDNet-CT, a deep convolutional neural network architecture that is tailored for detection of COVID-19 cases from chest CT images via a machine-driven design exploration approach. Additionally, we introduce COVIDx-CT, a benchmark CT image dataset derived from CT imaging data collected by the China National Center for Bioinformation comprising 104,009 images across 1,489 patient cases. Furthermore, in the interest of reliability and transparency, we leverage an explainability-driven performance validation strategy to investigate the decision-making behavior of COVIDNet-CT, and in doing so ensure that COVIDNet-CT makes predictions based on relevant indicators in CT images. Both COVIDNet-CT and the COVIDx-CT dataset are available to the general public in an open-source and open access manner as part of the COVID-Net initiative. While COVIDNet-CT is not yet a production-ready screening solution, we hope that releasing the model and dataset will encourage researchers, clinicians, and citizen data scientists alike to leverage and build upon them.

Download Full-text

Evaluation of textural-based radiomics features for differentiation of COVID-19 pneumonia from non-COVID pneumonia

Egyptian Journal of Radiology and Nuclear Medicine ◽

10.1186/s43055-021-00592-0 ◽

2021 ◽

Vol 52 (1) ◽

Author(s):

Yunus Soleymani ◽

Amir Reza Jahanshahi ◽

Maryam Hefzi ◽

Mona Fazel Ghaziani ◽

Amin Pourfarshid ◽

...

Keyword(s):

False Positive Rate ◽

Texture Features ◽

Study Groups ◽

Ct Images ◽

Chest Ct ◽

Textural Features ◽

Non Invasive ◽

Significant Difference ◽

Positive Rate ◽

Invasive Method

Abstract Background The false-positive rate of computed tomography (CT) images in the diagnosis of coronavirus disease 2019 (COVID-19) is a challenge for the management in the pandemic. The main purpose of this study is to investigate the textural radiomics features on chest CT images of COVID-19 pneumonia patients and compare them with those of non-COVID pneumonia. This is a retrospective study. Some textural radiomics features were extracted from the CT images of 66 patients with COVID-19 pneumonia and 40 with non-COVID pneumonia. For radiomics analysis, the regions of interest (ROIs) were manually identified inside the pulmonary ground-glass opacities. For each ROI, 12 textural features were obtained and, then, statistical analysis was performed to assess the differences in these features between the two study groups. Results 8 of the 12 texture features demonstrated a significant difference (P < 0.05) in two groups, with COVID-19 pneumonia lesions tending to be more heterogeneous in comparison with the non-COVID cases. Among the 8 significant features, only two (homogeneity and energy) were found to be higher in non-COVID cases. Conclusions Textural radiomics features can be used for differentiating COVID-19 pneumonia from non-COVID pneumonia, as a non-invasive method, and help with better prognosis and diagnosis of COVID-19 patients.

Download Full-text

Noninvasive quantitative estimation of hepatic steatosis by ultrasound: a comparison of the hepato-renal index and ultrasound attenuation index.

Medical Ultrasonography ◽

10.11152/mu-868 ◽

2016 ◽

Vol 18 (4) ◽

pp. 431 ◽

Cited By ~ 4

Author(s):

Heon-Ju Kwon ◽

Kyoung Won Kim ◽

Jin-Hee Jung ◽

Sang Hyun Choi ◽

Woo Kyoung Jeong ◽

...

Keyword(s):

Hepatic Steatosis ◽

Interobserver Agreement ◽

Quantitative Estimation ◽

Statistical Significance ◽

Characteristic Curve ◽

Intraclass Correlation ◽

Correlation Coefficients ◽

Ultrasound Attenuation ◽

Attenuation Index ◽

The Difference

Aims: To compare the accuracy of the ultrasound attenuation index (USAI) and hepato-renal index (HRI) for the diagnosis of hepatic steatosis (HS). Material and methods: Two hundred and twenty-four potential living hepatic donors underwent US and subsequent US-guided liver biopsy. The USAI was calculated from US images with an 8 MHz transducer and HRI was measured on sagittal images with a clear visualization of both the liver and kidney. Using histological degrees of HS as the reference standard, we compared the performance of USAI and HRI for diagnosing HS ≥ 5% and ≥ 30% by receiver operating characteristic curve analysis. The interobserver agreement was evaluated by using intraclass correlation coefficients (ICCs) or Bland–Altman statistics. Results: Histologic degree of HS was 0–70% (median, 5%). HRI showed a tendency towards higher accuracy than USAI for diagnosing HS ≥ 5% (the area under the ROC curve, 0.856 vs. 0.820; p= 0.279) and ≥ 30% (0.937 vs. 0.909; p = 0.378) without statistical significance. There was an excellent interobserver agreement for both USAI and HRI (ICC = 0.931 and 0.973, respectively). According to the Bland–Altman method, the 95% limits of difference between two readers for HS were −8.5% to 6.6% by USAI and −4.8% to 6.2% by HRI. Most patients would have the difference of calculated HS by USAI (74.0%) and HRI (96.0%) from different operators within a range of ±5%. Conclusions: Although statistically insignificant, HRI was superior to USAI for the diagnosis and quantitative estimation of HS in terms of diagnostic performance, including accuracy and reproducibility.

Download Full-text

RSNA Expert Consensus Statement on Reporting Chest CT Findings Related to COVID-19: Interobserver Agreement Between Chest Radiologists

Canadian Association of Radiologists Journal ◽

10.1177/0846537120938328 ◽

2020 ◽

pp. 084653712093832 ◽

Cited By ~ 1

Author(s):

Danielle Byrne ◽

Siobhan B. O’Neill ◽

Nestor L. Müller ◽

C. Isabela Silva Müller ◽

John P. Walsh ◽

...

Keyword(s):

Interobserver Agreement ◽

Consensus Statement ◽

Chest Ct ◽

Reporting Guidelines ◽

Expert Consensus ◽

Strong Correlations ◽

Radiological Society ◽

Ct Findings ◽

Polymerase Chain ◽

Ct Studies

Purpose: To assess the interobserver variability between chest radiologists in the interpretation of the Radiological Society of North America (RSNA) expert consensus statement reporting guidelines in patients with suspected coronavirus disease 2019 (COVID-19) pneumonia in a setting with limited reverse transcription polymerase chain reaction testing availability. Methods: Chest computed tomography (CT) studies in 303 consecutive patients with suspected COVID-19 were reviewed by 3 fellowship-trained chest radiologists. Cases were assigned an impression of typical, indeterminate, atypical, or negative for COVID-19 pneumonia according to the RSNA expert consensus statement reporting guidelines, and interobserver analysis was performed. Objective CT features associated with COVID-19 pneumonia and distribution of findings were recorded. Results: The Fleiss kappa for all observers was almost perfect for typical (0.815), atypical (0.806), and negative (0.962) COVID-19 appearances ( P < .0001) and substantial (0.636) for indeterminate COVID-19 appearance ( P < .0001). Using Cramer V analysis, there were very strong correlations between all radiologists’ interpretations, statistically significant for all (typical, indeterminate, atypical, and negative) COVID-19 appearances ( P < .001). Objective CT imaging findings were recorded in similar percentages of typical cases by all observers. Conclusion: The RSNA expert consensus statement on reporting chest CT findings related to COVID-19 demonstrates substantial to almost perfect interobserver agreement among chest radiologists in a relatively large cohort of patients with clinically suspected COVID-19. It therefore serves as a reliable reference framework for radiologists to accurately communicate their level of suspicion based on the presence of evidence-based objective findings.

Download Full-text

Deep Ensemble Learning-Based Models for Diagnosis of COVID-19 from Chest CT Images

Healthcare ◽

10.3390/healthcare10010166 ◽

2022 ◽

Vol 10 (1) ◽

pp. 166

Author(s):

Mohamed Mouhafid ◽

Mokhtar Salah ◽

Chi Yue ◽

Kewen Xia

Keyword(s):

Deep Learning ◽

Ensemble Learning ◽

Detection System ◽

Weighted Average ◽

Recognition System ◽

Ct Images ◽

Chest Ct ◽

Rt Pcr ◽

Infected People ◽

Desirable Outcome

Novel coronavirus (COVID-19) has been endangering human health and life since 2019. The timely quarantine, diagnosis, and treatment of infected people are the most necessary and important work. The most widely used method of detecting COVID-19 is real-time polymerase chain reaction (RT-PCR). Along with RT-PCR, computed tomography (CT) has become a vital technique in diagnosing and managing COVID-19 patients. COVID-19 reveals a number of radiological signatures that can be easily recognized through chest CT. These signatures must be analyzed by radiologists. It is, however, an error-prone and time-consuming process. Deep Learning-based methods can be used to perform automatic chest CT analysis, which may shorten the analysis time. The aim of this study is to design a robust and rapid medical recognition system to identify positive cases in chest CT images using three Ensemble Learning-based models. There are several techniques in Deep Learning for developing a detection system. In this paper, we employed Transfer Learning. With this technique, we can apply the knowledge obtained from a pre-trained Convolutional Neural Network (CNN) to a different but related task. In order to ensure the robustness of the proposed system for identifying positive cases in chest CT images, we used two Ensemble Learning methods namely Stacking and Weighted Average Ensemble (WAE) to combine the performances of three fine-tuned Base-Learners (VGG19, ResNet50, and DenseNet201). For Stacking, we explored 2-Levels and 3-Levels Stacking. The three generated Ensemble Learning-based models were trained on two chest CT datasets. A variety of common evaluation measures (accuracy, recall, precision, and F1-score) are used to perform a comparative analysis of each method. The experimental results show that the WAE method provides the most reliable performance, achieving a high recall value which is a desirable outcome in medical applications as it poses a greater risk if a true infected patient is not identified.

Download Full-text

Validation of a Classroom Version of the Eating in the Absence of Hunger Paradigm in Preschoolers

Frontiers in Nutrition ◽

10.3389/fnut.2021.787461 ◽

2022 ◽

Vol 8 ◽

Author(s):

Emily E. Hohman ◽

Katherine M. McNitt ◽

Sally G. Eagleton ◽

Lori A. Francis ◽

Kathleen L. Keller ◽

...

Keyword(s):

Eating Behavior ◽

Weight Status ◽

Eating Behaviors ◽

Ecological Validity ◽

Intraclass Correlation ◽

Correlation Coefficients ◽

Free Access ◽

Classroom Setting ◽

Significant Difference ◽

The Individual

Eating in the absence of hunger (EAH), a measure of children's propensity to eat beyond satiety in the presence of highly palatable food, has been associated with childhood obesity and later binge eating behavior. The EAH task is typically conducted in a research laboratory setting, which is resource intensive and lacks ecological validity. Assessing EAH in a group classroom setting is feasible and may be a more efficient alternative, but the validity of the classroom assessment against the traditional individually-administered paradigm has not been tested. The objective of this study was to compare EAH measured in a classroom setting to the one-on-one version of the paradigm in a sample of Head Start preschoolers. Children (n = 35) from three classrooms completed both classroom and individual EAH tasks in a random, counterbalanced order. In the group condition, children sat with peers at their classroom lunch tables; in the individual condition, children met individually with a researcher in a separate area near their classroom. In both conditions, following a meal, children were provided free access to generous portions of six snack foods (~750 kcal) and a selection of toys for 7 min. Snacks were pre- and post-weighed to calculate intake. Parents completed a survey of their child's eating behaviors, and child height and weight were measured. Paired t-tests and intraclass correlation coefficients were used to compare energy intake between conditions, and correlations between EAH intake and child BMI, eating behaviors, and parent feeding practices were examined to evaluate concurrent validity. Average intake was 63.0 ± 50.4 kcal in the classroom setting and 53.7 ± 44.6 in the individual setting, with no significant difference between settings. The intraclass correlation coefficient was 0.57, indicating moderate agreement between conditions. Overall, the EAH protocol appears to perform similarly in classroom and individual settings, suggesting the classroom protocol is a valid alternative. Future studies should further examine the role of age, sex, and weight status on eating behavior measurement paradigms.

Download Full-text