scholarly journals Finding COVID-19 from Chest X-rays using Deep Learning on a Small Dataset

2020 ◽  
Author(s):  
Lawrence Hall ◽  
Dmitry Goldgof ◽  
Rahul Paul ◽  
Gregory M. Goldgof
Keyword(s):  
False Negative ◽  
True Positive Rate ◽  
Small Data ◽  
Good Resolution ◽  
X Rays ◽  
True Positive ◽  
Data Set ◽  
X Ray ◽  
Negative Rate ◽  
Positive Rate

<p>Testing for COVID-19 has been unable to keep up with the demand. Further, the false negative rate is projected to be as high as 30% and test results can take some time to obtain. X-ray machines are widely available and provide images for diagnosis quickly. This paper explores how useful chest X-ray images can be in diagnosing COVID-19 disease. We have obtained 135 chest X-rays of COVID-19 and 320 chest X-rays of viral and bacterial pneumonia. </p><p> A pre-trained deep convolutional neural network, Resnet50 was tuned on 102 COVID-19 cases and 102 other pneumonia cases in a 10-fold cross validation. The results were </p><p> an overall accuracy of 89.2% with a COVID-19 true positive rate of 0.8039 and an AUC of 0.95. Pre-trained Resnet50 and VGG16 plus our own small CNN were tuned or trained on a balanced set of COVID-19 and pneumonia chest X-rays. An ensemble of the three types of CNN classifiers was applied to a test set of 33 unseen COVID-19 and 218 pneumonia cases. The overall accuracy was 91.24% with the true positive rate for COVID-19 of 0.7879 with 6.88% false positives for a true negative rate of 0.9312 and AUC of 0.94. </p><p> This preliminary study has flaws, most critically a lack of information about where in the disease process the COVID-19 cases were and the small data set size. More COVID-19 case images at good resolution will enable a better answer to the question of how useful chest X-rays can be for diagnosing COVID-19.</p>

scholarly journals Finding COVID-19 from Chest X-rays using Deep Learning on a Small Dataset

2020 ◽  
Author(s):  
Lawrence Hall ◽  
Dmitry Goldgof ◽  
Rahul Paul ◽  
Gregory M. Goldgof
Keyword(s):  
False Negative ◽  
True Positive Rate ◽  
Small Data ◽  
Good Resolution ◽  
X Rays ◽  
True Positive ◽  
Data Set ◽  
X Ray ◽  
Negative Rate ◽  
Positive Rate

<p>Testing for COVID-19 has been unable to keep up with the demand. Further, the false negative rate is projected to be as high as 30% and test results can take some time to obtain. X-ray machines are widely available and provide images for diagnosis quickly. This paper explores how useful chest X-ray images can be in diagnosing COVID-19 disease. We have obtained 135 chest X-rays of COVID-19 and 320 chest X-rays of viral and bacterial pneumonia. </p><p> A pre-trained deep convolutional neural network, Resnet50 was tuned on 102 COVID-19 cases and 102 other pneumonia cases in a 10-fold cross validation. The results were </p><p> an overall accuracy of 89.2% with a COVID-19 true positive rate of 0.8039 and an AUC of 0.95. Pre-trained Resnet50 and VGG16 plus our own small CNN were tuned or trained on a balanced set of COVID-19 and pneumonia chest X-rays. An ensemble of the three types of CNN classifiers was applied to a test set of 33 unseen COVID-19 and 218 pneumonia cases. The overall accuracy was 91.24% with the true positive rate for COVID-19 of 0.7879 with 6.88% false positives for a true negative rate of 0.9312 and AUC of 0.94. </p><p> This preliminary study has flaws, most critically a lack of information about where in the disease process the COVID-19 cases were and the small data set size. More COVID-19 case images at good resolution will enable a better answer to the question of how useful chest X-rays can be for diagnosing COVID-19.</p>

scholarly journals Finding COVID-19 from Chest X-rays using Deep Learning on a Small Dataset

2020 ◽  
Author(s):  
Lawrence Hall ◽  
Dmitry Goldgof ◽  
Rahul Paul ◽  
Gregory M. Goldgof
Keyword(s):  
Bacterial Pneumonia ◽  
True Positive Rate ◽  
Small Data ◽  
Good Resolution ◽  
X Rays ◽  
True Positive ◽  
Data Set ◽  
X Ray ◽  
Negative Rate ◽  
Positive Rate

<p>esting for COVID-19 has been unable to keep up with the demand. Further, the false negative rate is projected to be as high as 30\ and test results can take some time to obtain. X-ray machines are widely available and provide images for diagnosis quickly. This paper explores how useful chest X-ray images can be in diagnosing COVID-19 disease. We have obtained 135 chest X-rays of COVID-19 and 320 chest X-rays of viral and bacterial pneumonia. </p><p> A pre-trained deep convolutional neural network, Resnet50 was tuned on 102 COVID-19 cases and 102 other pneumonia cases in a 10-fold cross validation. The results were </p><p> an overall accuracy of 90.7% with a COVID-19 true positive rate of 0.83 and an AUC of 0.987,</p><p> Pre-trained Resnet50 and VGG16 plus our own small CNN were tuned or trained on a balanced set of COVID-19 and pneumonia chest X-rays. An ensemble of the three types of CNN classifiers was applied to a test set of 33 unseen COVID-19 and 208 pneumonia cases. The overall accuracy was 94.4% with the true positive rate for COVID-19 of 0.969 with 6% false positives for a true negative rate of 0.94 and AUC of 0.99. </p><p> </p><p> This preliminary study has flaws, most critically a lack of information about where in the disease process the COVID-19 cases were and the small data set size. More COVID-19 case images at good resolution will enable a better answer to the question of how useful chest X-rays can be for diagnosing COVID-19. </p><p> </p><p> Note an earlier version of this work inadvertently used chest X-rays of viral and bacterial pneumonia that came from a dataset of children under 5 years old and those results should be ignored. </p>

scholarly journals Finding COVID-19 from Chest X-rays using Deep Learning on a Small Dataset

2020 ◽  
Author(s):  
Lawrence Hall ◽  
Dmitry Goldgof ◽  
Rahul Paul ◽  
Gregory M. Goldgof
Keyword(s):  
False Negative ◽  
False Negative Rate ◽  
Disease Process ◽  
Small Data ◽  
X Rays ◽  
Data Set ◽  
X Ray ◽  
Set Size ◽  
Lack Of Information ◽  
Chest X Ray

<p>Testing for COVID-19 has been unable to keep up with the demand. Further, the false negative rate is projected to be as high as 30% and test results can take some time to obtain. X-ray machines are widely available and provide images for diagnosis quickly. This paper explores how useful chest X-ray images can be in diagnosing COVID-19 disease. We have obtained 122 chest X-rays of COVID-19 and over 4,000 chest X-rays of viral and bacterial pneumonia. A pre-trained deep convolutional neural network has been tuned on 102 COVID-19 cases and 102 other pneumonia cases in a 10-fold cross validation. The results were all 102 COVID-19 cases were correctly classified and there were 8 false positives resulting in an AUC of 0.997. On a test set of 20 unseen COVID-19 cases all were correctly classified and more than 95% of 4,171 other pneumonia examples were correctly classified. This study has flaws, most critically a lack of information about where in the disease process the COVID-19 cases were and the small data set size. More COVID-19 case images will enable a better answer to the question of how useful chest X-rays can be for diagnosing COVID-19 (so please send them). </p>

Mastoid, middle ear and inner ear analysis in CT scan – a possible contribution for the identification of remains

2020 ◽  
Vol 60 (2) ◽  
pp. 102-111
Author(s):  
Henrique Rodrigues ◽  
Rosa Ramos ◽  
Leoni Fagundes ◽  
Orlando Galego ◽  
David Navega ◽  
...  
Keyword(s):  
Positive Predictive Value ◽  
Predictive Value ◽  
Visual Assessment ◽  
True Positive Rate ◽  
Observer Agreement ◽  
True Positive ◽  
True Negative ◽  
True Negative Rate ◽  
Negative Rate ◽  
Positive Rate

Objective We aimed to evaluate whether the internal structures of the human ear have anatomical characteristics that are sufficiently distinctive to contribute to human identification and use in a forensic context. Materials and methods After data anonymisation, a dataset containing temporal bone CT scans of 100 subjects was processed by a radiologist who was not involved in the study. Four reference images were selected for each subject. Of the original sample, 10 examinations were used for visual comparison, case by case, against the dataset of 100 patients. This visual assessment was performed independently by four observers, who evaluated the anatomical agreement using a Likert scale (1–5). Inter-observer agreement, true positive rate, positive predictive value, true negative rate, negative predictive value, false positive rate, false negative rate and positive likelihood ratio (LR+) were evaluated. Results Inter-observer agreement obtained an overall Cohen’s Kappa = 99.59%. True positive rate, positive predictive value, true negative rate and negative predictive value were all 100%. Conclusion Visual assessment of the mastoid examinations was shown to be a robust and reliable approach to identify unique osseous features and contribute to human identification. The statistical analysis indicates that regardless of the examiner’s background and training, the approach has a high degree of accuracy.

Value of percutaneous transhepatic cholangiobiopsy for pathologic diagnosis of obstructive jaundice: analysis of 826 cases

2016 ◽  
Vol 58 (1) ◽  
pp. 3-9 ◽  
Author(s):  
Zhen Li ◽  
Teng-Fei Li ◽  
Jian-Zhuang Ren ◽  
Wen-Cai Li ◽  
Jing-Li Ren ◽  
...  
Keyword(s):  
Obstructive Jaundice ◽  
Biliary Stricture ◽  
False Negative ◽  
Bile Leakage ◽  
True Positive Rate ◽  
True Positive ◽  
Biliary Carcinoma ◽  
Pathologic Diagnosis ◽  
Pathologic Findings ◽  
Positive Rate

Background Obstructive jaundice (OJ) is insensitive to radiation and chemotherapy, and a pathologic diagnosis is difficult to make clinically. Percutaneous transhepatic cholangiobiopsy (PTCB) is simple to perform and minimally invasive, and clinical practice has shown it to be an accurate and reliable new method for bile duct histopathologic diagnosis. Purpose To investigate the value of PTCB for pathologic diagnosis of causes of OJ. Material and Methods From April 2001 to December 2011, PTCB was performed in 826 consecutive patients. Data on pathologic diagnosis, true positive rate, and complications were analyzed retrospectively. Patients with negative pathologic findings were diagnosed using clinical, imaging, laboratory, and prognostic data. The feasibility and safety of PTCB for OJ were evaluated and true positive rates for biliary carcinoma and non-biliary carcinoma compared. Results PTCB was successful in all cases. Of 740 patients clinically diagnosed with malignant biliary stricture and 86 with benign biliary stricture, 727 received a positive pathologic diagnosis; in 99, the pathologic findings were considered false negative. The true positive rate for PTCB was 88.01% overall, differing significantly for biliary and non-biliary carcinoma ( χ2 = 12.87, P < 0.05). Malignancy accounted for 89.59% of OJ cases; well, moderately, and poorly differentiated carcinoma represented 57.88%, 19.97%, and 22.15%. Biliary adenocarcinoma was the predominant malignant pathologic type (96.41%). Transient bilemia, bile leakage, and temporary hemobilia occurred in 47, 11, and 28 cases, respectively, with no serious complications. Conclusion PTCB is safe, feasible, and simple, with a high true positive rate for definitive diagnosis of OJ causes. Well differentiated adenocarcinoma was the predominant pathologic type.

scholarly journals A KNIME-Based Analysis of the Zebrafish Photomotor Response Clusters the Phenotypes of 14 Classes of Neuroactive Molecules

2015 ◽  
Vol 21 (5) ◽  
pp. 427-436 ◽  
Author(s):  
Daniëlle Copmans ◽  
Thorsten Meinl ◽  
Christian Dietz ◽  
Matthijs van Leeuwen ◽  
Julia Ortmann ◽  
...  
Keyword(s):  
Drug Discovery ◽  
False Negative ◽  
False Negative Rate ◽  
Automated Analysis ◽  
True Positive Rate ◽  
Zebrafish Embryos ◽  
True Positive ◽  
Neuroactive Compounds ◽  
Analysis Workflow ◽  
Positive Rate

Recently, the photomotor response (PMR) of zebrafish embryos was reported as a robust behavior that is useful for high-throughput neuroactive drug discovery and mechanism prediction. Given the complexity of the PMR, there is a need for rapid and easy analysis of the behavioral data. In this study, we developed an automated analysis workflow using the KNIME Analytics Platform and made it freely accessible. This workflow allows us to simultaneously calculate a behavioral fingerprint for all analyzed compounds and to further process the data. Furthermore, to further characterize the potential of PMR for mechanism prediction, we performed PMR analysis of 767 neuroactive compounds covering 14 different receptor classes using the KNIME workflow. We observed a true positive rate of 25% and a false negative rate of 75% in our screening conditions. Among the true positives, all receptor classes were represented, thereby confirming the utility of the PMR assay to identify a broad range of neuroactive molecules. By hierarchical clustering of the behavioral fingerprints, different phenotypical clusters were observed that suggest the utility of PMR for mechanism prediction for adrenergics, dopaminergics, serotonergics, metabotropic glutamatergics, opioids, and ion channel ligands.

The compliance, true positive and false negative rates of the Charing Cross protocol for magnetic resonance imaging screening for cerebellopontine angle lesions

2007 ◽  
Vol 122 (3) ◽  
pp. 255-258
Author(s):  
J D Snelling ◽  
M Krywawych ◽  
A Majithia ◽  
J P Harcourt
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Cerebellopontine Angle ◽  
Compliance Rate ◽  
False Negative ◽  
False Negative Rate ◽  
True Positive Rate ◽  
True Positive ◽  
Resonance Imaging ◽  
Negative Rate

AbstractObjectives:To assess the effectiveness and determine the compliance to a local protocol for requesting magnetic resonance imaging scans to screen for the presence of cerebellopontine angle lesions.Methods:A combined retrospective study of all patients who had magnetic resonance imaging scans requested six months prior to and one year following introduction of the protocol and assessment of the true positive and false negative rate of the protocol by assessment of its sensitivity in cases referred from outside the department.Results:Comparison of the number of scans in each period showed a reduction in annualised rate of 142 to 46. The incidence of positive scans was the same in both periods, increasing the true positive rate from 1.4 to 4.3 per cent. The false negative rate was 1.1 per cent.Conclusions:The Charing Cross protocol has a good compliance rate within the department, has reduced the cost of screening for cerebellopontine angle lesions and has an acceptable true positive and false negative rate.

scholarly journals The True-Positive Rate of a Screening Questionnaire for Temporomandib-ular Disorders

2014 ◽  
Vol 8 (1) ◽  
pp. 236-240 ◽  
Author(s):  
Akira Nishiyama ◽  
Natsuko Otomo ◽  
Kaori Tsukagoshi ◽  
Shoko Tobe ◽  
Koji Kino
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Logistic Regression Analysis ◽  
False Negative ◽  
Mouth Opening ◽  
True Positive Rate ◽  
True Positive ◽  
Vas Score ◽  
Positive Rate ◽  
The Mean

Background: Temporomandibular disorders (TMD) occur at an incidence of 5–12% in the general population. We aimed to investigate the rate of true-positives for a screening questionnaire for TMD (SQ-TMD) and differences in the characteristics between the true-positive and false-negative groups. Materials and Methods: Seventy-six individuals (16 men, 60 women; mean age, 41.1 ± 16.5 years) were selected from pa-tients with TMD who had visited the Temporomandibular Joint Clinic at Tokyo Medical and Dental University. The patients were assessed using a questionnaire that contained items on TMD screening (SQ-TMD); pain intensity (at rest, maximum mouth-opening, and chewing), as assessed using the visual analog scale (VAS); and TMD-related limitations of daily func-tion (LDF-TMD). A logistic regression analysis was performed to assess the factors potentially influencing the true-positive rate. Results: Of the 76 subjects, 62 (81.6%) were true-positive for the questionnaire based on the SQ-TMD scores. The mean VAS score for maximum mouth-opening and chewing and the mean LDF-TMD score were significantly greater in the true-positive group than those in the false-negative group. The results of the logistic regression analysis showed that only the VAS score for chewing was a statistically significant factor (P < 0.05). Conclusion: The true-positive rate of TMD using SQ-TMD was very high. The results indicate that SQ-TMD can be used to screen TMD in patients with moderate or severe pain and difficulty in living a healthy daily life.

scholarly journals Handling Imbalanced Class Problem of Measles InfectionRisk Prediction Model

2019 ◽  
Vol 9 (1) ◽  
pp. 3431-3435
Keyword(s):  
Logistic Regression ◽  
False Positive Rate ◽  
False Negative ◽  
False Negative Rate ◽  
Sampling Technique ◽  
True Positive Rate ◽  
True Positive ◽  
Positive Rate ◽  
Imbalanced Class ◽  
Medical Dataset

Measles is an emerging infectious disease with increasing number of reported cases. It is a vaccine-preventable disease;thus, it is common to have imbalanced class problem in the dataset. This study aims to resolve the imbalanced class problem for the prediction of measles infection risk and to compare the predictive results on a balanced dataset based on three machine learningtechniques. The data that was utilized in this study contained 37,884 records of suspected measles casesthat were highly imbalanced towards negative measles cases. The Synthetic Minority Over-Sampling Technique (SMOTE) was performed to balance thedistribution of the target attribute. The balanced dataset was then modelled using logistic regression, decision tree and Naïve Bayes. The predicted results indicated that logistic regression executed on the balanced dataset by SMOTE has the highest and most accurateclassification with 94.5% overall accuracy, 93.9% true positive rate, 5.8% false positive rate and 5.1% false negative rate. Therefore, SMOTE and other over-sampling approaches may be applicable to overcome imbalanced class issues in the medical dataset.

Sign in / Sign up

Export Citation Format

Share Document