Application of Deep Learning to Detect Ground Deformation in InSAR Data

2020 ◽  
Author(s):  
Pui Anantrasirichai ◽  
Juliet Biggs ◽  
Fabien Albino ◽  
David Bull
Keyword(s):  
Deep Learning ◽  
False Positive ◽  
Data Augmentation ◽  
Ground Deformation ◽  
Signal To Noise Ratio ◽  
Matrix Completion ◽  
False Positive Rate ◽  
Synthetic Approach ◽  
Positive Rate ◽  
Machine Learning Applications

<p>Satellite interferometric synthetic aperture radar (InSAR) can be used for measuring surface deformation for a variety of applications. Recent satellite missions, such as Sentinel-1, produce a large amount of data, meaning that visual inspection is impractical. Here we use deep learning, which has proved successful at object detection, to overcome this problem. Initially we present the use of convolutional neural networks (CNNs) for detecting rapid deformation events, which we test on a global dataset of over 30,000 wrapped interferograms at 900 volcanoes. We compare two potential training datasets: data augmentation applied to archive examples and synthetic models. Both are able to detect true positive results, but the data augmentation approach has a false positive rate of 0.205% and the synthetic approach has a false positive rate of 0.036%.  Then, I will present an enhanced technique for measuring slow, sustained deformation over a range of scales from volcanic unrest to urban sources of deformation such as coalfields. By rewrapping cumulative time series, the detection performance is improved when the deformation rate is slow, as more fringes are generated without altering the signal to noise ratio. We adapt the method to use persistent scatterer InSAR data, which is sparse in nature,  by using spatial interpolation methods such as modified matrix completion Finally, future perspectives for machine learning applications on InSAR data will be discussed.</p>

scholarly journals Convolutional Neural Networks for the Segmentation of Microcalcification in Mammography Imaging

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Gabriele Valvano ◽  
Gianmarco Santini ◽  
Nicola Martini ◽  
Andrea Ripoli ◽  
Chiara Iacconi ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
False Positive ◽  
False Positive Rate ◽  
Novel Approach ◽  
Positive Rate ◽  
Microcalcification Detection ◽  
Microcalcification Clusters

Cluster of microcalcifications can be an early sign of breast cancer. In this paper, we propose a novel approach based on convolutional neural networks for the detection and segmentation of microcalcification clusters. In this work, we used 283 mammograms to train and validate our model, obtaining an accuracy of 99.99% on microcalcification detection and a false positive rate of 0.005%. Our results show how deep learning could be an effective tool to effectively support radiologists during mammograms examination.

scholarly journals Deep Learning Model Improves Radiologists’ Performance in Detection and Classification of Breast Lesions

2021 ◽  
Author(s):  
Ying-Shi Sun ◽  
Yu-Hong Qu ◽  
Dong Wang ◽  
Yi Li ◽  
Lin Ye ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Roc Curve ◽  
False Positive ◽  
Large Scale ◽  
False Positive Rate ◽  
Training Dataset ◽  
Validation Dataset ◽  
Breast Lesions ◽  
Positive Rate

Abstract Background: Computer-aided diagnosis using deep learning algorithms has been initially applied in the field of mammography, but there is no large-scale clinical application.Methods: This study proposed to develop and verify an artificial intelligence model based on mammography. Firstly, retrospectively collected mammograms from six centers were randomized to a training dataset and a validation dataset for establishing the model. Secondly, the model was tested by comparing 12 radiologists’ performance with and without it. Finally, prospectively multicenter mammograms were diagnosed by radiologists with the model. The detection and diagnostic capabilities were evaluated using the free-response receiver operating characteristic (FROC) curve and ROC curve.Results: The sensitivity of model for detecting lesion after matching was 0.908 for false positive rate of 0.25 in unilateral images. The area under ROC curve (AUC) to distinguish the benign from malignant lesions was 0.855 (95% CI: 0.830, 0.880). The performance of 12 radiologists with the model was higher than that of radiologists alone (AUC: 0.852 vs. 0.808, P = 0.005). The mean reading time of with the model was shorter than that of reading alone (80.18 s vs. 62.28 s, P = 0.03). In prospective application, the sensitivity of detection reached 0.887 at false positive rate of 0.25; the AUC of radiologists with the model was 0.983 (95% CI: 0.978, 0.988), with sensitivity, specificity, PPV, and NPV of 94.36%, 98.07%, 87.76%, and 99.09%, respectively.Conclusions: The artificial intelligence model exhibits high accuracy for detecting and diagnosing breast lesions, improves diagnostic accuracy and saves time.Trial registration: NCT, NCT03708978. Registered 17 April 2018, https://register.clinicaltrials.gov/prs/app/ NCT03708978

Deep-learning and radiomics ensemble classifier for false positive reduction in brain metastases segmentation

2021 ◽  
Author(s):  
Zi Yang ◽  
Mingli Chen ◽  
Mahdieh Kazemimoghadam ◽  
Lin Ma ◽  
Strahinja Stojadinovic ◽  
...  
Keyword(s):  
Deep Learning ◽  
Brain Metastases ◽  
False Positive ◽  
False Positive Rate ◽  
Ensemble Classifier ◽  
Support Vector ◽  
Svm Classifier ◽  
Siamese Network ◽  
Proposed Model ◽  
Positive Rate

Abstract Stereotactic radiosurgery (SRS) is now the standard of care for brain metastases (BMs) patients. The SRS treatment planning process requires precise target delineation, which in clinical workflow for patients with multiple (>4) BMs (mBMs) could become a pronounced time bottleneck. Our group has developed an automated BMs segmentation platform to assist in this process. The accuracy of the auto-segmentation, however, is influenced by the presence of false-positive segmentations, mainly caused by the injected contrast during MRI acquisition. To address this problem and further improve the segmentation performance, a deep-learning and radiomics ensemble classifier was developed to reduce the false-positive rate in segmentations. The proposed model consists of a Siamese network and a radiomic-based support vector machine (SVM) classifier. The 2D-based Siamese network contains a pair of parallel feature extractors with shared weights followed by a single classifier. This architecture is designed to identify the inter-class difference. On the other hand, the SVM model takes the radiomic features extracted from 3D segmentation volumes as the input for twofold classification, either a false-positive segmentation or a true BM. Lastly, the outputs from both models create an ensemble to generate the final label. The performance of the proposed model in the segmented mBMs testing dataset reached the accuracy (ACC), sensitivity (SEN), specificity (SPE) and area under the curve (AUC) of 0.91, 0.96, 0.90 and 0.93, respectively. After integrating the proposed model into the original segmentation platform, the average segmentation false negative rate (FNR) and the false positive over the union (FPoU) were 0.13 and 0.09, respectively, which preserved the initial FNR (0.07) and significantly improved the FPoU (0.55). The proposed method effectively reduced the false-positive rate in the BMs raw segmentations indicating that the integration of the proposed ensemble classifier into the BMs segmentation platform provides a beneficial tool for mBMs SRS management.

scholarly journals Brain metastasis detection using machine learning: a systematic review and meta-analysis

2020 ◽  
Author(s):  
Se Jin Cho ◽  
Leonard Sunwoo ◽  
Sung Hyun Baik ◽  
Yun Jung Bae ◽  
Byung Se Choi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Brain Metastasis ◽  
False Positive ◽  
Data Augmentation ◽  
Meta Analysis ◽  
False Positive Rate ◽  
Relevant Literature ◽  
Inverse Variance ◽  
Positive Rate

Abstract Background Accurate detection of brain metastasis (BM) is important for cancer patients. We aimed to systematically review the performance and quality of machine-learning-based BM detection on MRI in the relevant literature. Methods A systematic literature search was performed for relevant studies reported before April 27, 2020. We assessed the quality of the studies using modified tailored questionnaires of the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) criteria and the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Pooled detectability was calculated using an inverse-variance weighting model. Results A total of 12 studies were included, which showed a clear transition from classical machine learning (cML) to deep learning (DL) after 2018. The studies on DL used a larger sample size than those on cML. The cML and DL groups also differed in the composition of the dataset, and technical details such as data augmentation. The pooled proportions of detectability of BM were 88.7% (95% CI, 84–93%) and 90.1% (95% CI, 84–95%) in the cML and DL groups, respectively. The false-positive rate per person was lower in the DL group than the cML group (10 vs 135, P < 0.001). In the patient selection domain of QUADAS-2, three studies (25%) were designated as high risk due to non-consecutive enrollment and arbitrary exclusion of nodules. Conclusion A comparable detectability of BM with a low false-positive rate per person was found in the DL group compared with the cML group. Improvements are required in terms of quality and study design.

Improving diagnosis of acute appendicitis with atypical findings by Tc-99m HMPAO leukocyte scan

2002 ◽  
Vol 41 (01) ◽  
pp. 37-41 ◽  
Author(s):  
S. Shung-Shung ◽  
S. Yu-Chien ◽  
Y. Mei-Due ◽  
W. Hwei-Chung ◽  
A. Kao
Keyword(s):  
Acute Appendicitis ◽  
False Positive ◽  
False Positive Rate ◽  
Accurate Method ◽  
Clinical Findings ◽  
Pathological Findings ◽  
Lower Quadrant ◽  
Predictive Values ◽  
Positive Rate

Summary Aim: Even with careful observation, the overall false-positive rate of laparotomy remains 10-15% when acute appendicitis was suspected. Therefore, the clinical efficacy of Tc-99m HMPAO labeled leukocyte (TC-WBC) scan for the diagnosis of acute appendicitis in patients presenting with atypical clinical findings is assessed. Patients and Methods: Eighty patients presenting with acute abdominal pain and possible acute appendicitis but atypical findings were included in this study. After intravenous injection of TC-WBC, serial anterior abdominal/pelvic images at 30, 60, 120 and 240 min with 800k counts were obtained with a gamma camera. Any abnormal localization of radioactivity in the right lower quadrant of the abdomen, equal to or greater than bone marrow activity, was considered as a positive scan. Results: 36 out of 49 patients showing positive TC-WBC scans received appendectomy. They all proved to have positive pathological findings. Five positive TC-WBC were not related to acute appendicitis, because of other pathological lesions. Eight patients were not operated and clinical follow-up after one month revealed no acute abdominal condition. Three of 31 patients with negative TC-WBC scans received appendectomy. They also presented positive pathological findings. The remaining 28 patients did not receive operations and revealed no evidence of appendicitis after at least one month of follow-up. The overall sensitivity, specificity, accuracy, positive and negative predictive values for TC-WBC scan to diagnose acute appendicitis were 92, 78, 86, 82, and 90%, respectively. Conclusion: TC-WBC scan provides a rapid and highly accurate method for the diagnosis of acute appendicitis in patients with equivocal clinical examination. It proved useful in reducing the false-positive rate of laparotomy and shortens the time necessary for clinical observation.

Predicting Fetal Chromosome Anomalies in the First Trimester Using Pregnancy Associated Plasma Protein-A: A Comparison of Statistical Methods

1993 ◽  
Vol 32 (02) ◽  
pp. 175-179 ◽  
Author(s):  
B. Brambati ◽  
T. Chard ◽  
J. G. Grudzinskas ◽  
M. C. M. Macintosh
Keyword(s):  
Logistic Regression ◽  
General Population ◽  
Likelihood Ratio ◽  
False Positive ◽  
False Positive Rate ◽  
Ratio Method ◽  
Detection Rates ◽  
Gaussian Distributions ◽  
Positive Rate ◽  
Likelihood Ratio Method

Abstract:The analysis of the clinical efficiency of a biochemical parameter in the prediction of chromosome anomalies is described, using a database of 475 cases including 30 abnormalities. A comparison was made of two different approaches to the statistical analysis: the use of Gaussian frequency distributions and likelihood ratios, and logistic regression. Both methods computed that for a 5% false-positive rate approximately 60% of anomalies are detected on the basis of maternal age and serum PAPP-A. The logistic regression analysis is appropriate where the outcome variable (chromosome anomaly) is binary and the detection rates refer to the original data only. The likelihood ratio method is used to predict the outcome in the general population. The latter method depends on the data or some transformation of the data fitting a known frequency distribution (Gaussian in this case). The precision of the predicted detection rates is limited by the small sample of abnormals (30 cases). Varying the means and standard deviations (to the limits of their 95% confidence intervals) of the fitted log Gaussian distributions resulted in a detection rate varying between 42% and 79% for a 5% false-positive rate. Thus, although the likelihood ratio method is potentially the better method in determining the usefulness of a test in the general population, larger numbers of abnormal cases are required to stabilise the means and standard deviations of the fitted log Gaussian distributions.

Identification of and Correction for Publication Bias: Comment

2019 ◽  
Author(s):  
Amanda Kvarven ◽  
Eirik Strømland ◽  
Magnus Johannesson
Keyword(s):  
Publication Bias ◽  
False Positive ◽  
Large Scale ◽  
Meta Analysis ◽  
False Positive Rate ◽  
Effect Sizes ◽  
Replication Studies ◽  
Moderate Reduction ◽  
Positive Rate ◽  
Meta Analyses

Andrews & Kasy (2019) propose an approach for adjusting effect sizes in meta-analysis for publication bias. We use the Andrews-Kasy estimator to adjust the result of 15 meta-analyses and compare the adjusted results to 15 large-scale multiple labs replication studies estimating the same effects. The pre-registered replications provide precisely estimated effect sizes, which do not suffer from publication bias. The Andrews-Kasy approach leads to a moderate reduction of the inflated effect sizes in the meta-analyses. However, the approach still overestimates effect sizes by a factor of about two or more and has an estimated false positive rate of between 57% and 100%.

scholarly journals PRATD: A Phased Remote Access Trojan Detection Method with Double-Sided Features

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1894
Author(s):  
Chun Guo ◽  
Zihua Song ◽  
Yuan Ping ◽  
Guowei Shen ◽  
Yuhei Cui ◽  
...  
Keyword(s):  
False Positive ◽  
Detection Method ◽  
False Positive Rate ◽  
True Positive Rate ◽  
Remote Access ◽  
Detection Methods ◽  
Security Threats ◽  
True Positive ◽  
Trojan Detection ◽  
Positive Rate

Remote Access Trojan (RAT) is one of the most terrible security threats that organizations face today. At present, two major RAT detection methods are host-based and network-based detection methods. To complement one another’s strengths, this article proposes a phased RATs detection method by combining double-side features (PRATD). In PRATD, both host-side and network-side features are combined to build detection models, which is conducive to distinguishing the RATs from benign programs because that the RATs not only generate traffic on the network but also leave traces on the host at run time. Besides, PRATD trains two different detection models for the two runtime states of RATs for improving the True Positive Rate (TPR). The experiments on the network and host records collected from five kinds of benign programs and 20 famous RATs show that PRATD can effectively detect RATs, it can achieve a TPR as high as 93.609% with a False Positive Rate (FPR) as low as 0.407% for the known RATs, a TPR 81.928% and FPR 0.185% for the unknown RATs, which suggests it is a competitive candidate for RAT detection.

Evidence for Age-Adjusted D-Dimer to Rule out Pulmonary Embolism: An Institutional Study

2020 ◽  
Vol 154 (Supplement_1) ◽  
pp. S5-S5
Author(s):  
Ridin Balakrishnan ◽  
Daniel Casa ◽  
Morayma Reyes Gil
Keyword(s):  
Pulmonary Embolism ◽  
False Positive ◽  
False Positive Rate ◽  
Moderate Risk ◽  
Older Population ◽  
Statistical Measures ◽  
Positive Rate ◽  
Risk Patients ◽  
D Dimer ◽  
Rule Out

Abstract The diagnostic approach for ruling out suspected acute pulmonary embolism (PE) in the ED setting includes several tests: ultrasound, plasma d-dimer assays, ventilation-perfusion scans and computed tomography pulmonary angiography (CTPA). Importantly, a pretest probability scoring algorithm is highly recommended to triage high risk cases while also preventing unnecessary testing and harm to low/moderate risk patients. The d-dimer assay (both ELISA and immunoturbidometric) has been shown to be extremely sensitive to rule out PE in conjunction with clinical probability. In particularly, d-dimer testing is recommended for low/moderate risk patients, in whom a negative d-dimer essentially rules out PE sparing these patients from CTPA radiation exposure, longer hospital stay and anticoagulation. However, an unspecific increase in fibrin-degradation related products has been seen with increase in age, resulting in higher false positive rate in the older population. This study analyzed patient visits to the ED of a large academic institution for five years and looked at the relationship between d-dimer values, age and CTPA results to better understand the value of age-adjusted d-dimer cut-offs in ruling out PE in the older population. A total of 7660 ED visits had a CTPA done to rule out PE; out of which 1875 cases had a d-dimer done in conjunction with the CT and 5875 had only CTPA done. Out of the 1875 cases, 1591 had positive d-dimer results (>0.50 µg/ml (FEU)), of which 910 (57%) were from patients older than or equal to fifty years of age. In these older patients, 779 (86%) had a negative CT result. The following were the statistical measures of the d-dimer test before adjusting for age: sensitivity (98%), specificity (12%); negative predictive value (98%) and false positive rate (88%). After adjusting for age in people older than 50 years (d-dimer cut off = age/100), 138 patients eventually turned out to be d-dimer negative and every case but four had a CT result that was also negative for a PE. The four cases included two non-diagnostic results and two with subacute/chronic/subsegmental PE on imaging. None of these four patients were prescribed anticoagulation. The statistical measures of the d-dimer test after adjusting for age showed: sensitivity (96%), specificity (20%); negative predictive value (98%) and a decrease in the false positive rate (80%). Therefore, imaging could have been potentially avoided in 138/779 (18%) of the patients who were part of this older population and had eventual negative or not clinically significant findings on CTPA if age-adjusted d-dimers were used. This data very strongly advocates for the clinical usefulness of an age-adjusted cut-off of d-dimer to rule out PE.

Sign in / Sign up

Export Citation Format

Share Document