scholarly journals Deep learning algorithms for detecting and visualising intussusception on plain abdominal radiography in children: a retrospective multicenter study

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Gitaek Kwon ◽  
Jongbin Ryu ◽  
Jaehoon Oh ◽  
Jongwoo Lim ◽  
Bo-kyeong Kang ◽  
...  
Keyword(s):  
Characteristic Curve ◽  
External Validation ◽  
Youden Index ◽  
P Value ◽  
Data Sets ◽  
Single Shot ◽  
X Rays ◽  
Hospital Data ◽  
Data Set ◽  
Mean Values

Abstract This study aimed to verify a deep convolutional neural network (CNN) algorithm to detect intussusception in children using a human-annotated data set of plain abdominal X-rays from affected children. From January 2005 to August 2019, 1449 images were collected from plain abdominal X-rays of patients ≤ 6 years old who were diagnosed with intussusception while 9935 images were collected from patients without intussusception from three tertiary academic hospitals (A, B, and C data sets). Single Shot MultiBox Detector and ResNet were used for abdominal detection and intussusception classification, respectively. The diagnostic performance of the algorithm was analysed using internal and external validation tests. The internal test values after training with two hospital data sets were 0.946 to 0.971 for the area under the receiver operating characteristic curve (AUC), 0.927 to 0.952 for the highest accuracy, and 0.764 to 0.848 for the highest Youden index. The values from external test using the remaining data set were all lower (P-value < 0.001). The mean values of the internal test with all data sets were 0.935 and 0.743 for the AUC and Youden Index, respectively. Detection of intussusception by deep CNN and plain abdominal X-rays could aid in screening for intussusception in children.

scholarly journals Evaluating the predictive quality of the Chapman bone algorithm using aggregated data sets

2018 ◽  
Vol 6 (1) ◽  
pp. 38
Author(s):  
Noah D. Barrett ◽  
Cameron W. James ◽  
Joshua P. Tam ◽  
Elise S. Levesque ◽  
Anton S. Ketterer ◽  
...  
Keyword(s):  
Characteristic Curve ◽  
Primary Data ◽  
P Value ◽  
Mathematical Treatment ◽  
Data Sets ◽  
Mean Values ◽  
Aggregated Data ◽  
Metabolic Bone Disorder ◽  
Metabolic Bone ◽  
Feasible Alternative

Background: Due to an aging population, osteoporosis has become an increasingly prevalent metabolic bone disorder that is largely undiagnosed worldwide because of inaccessible and expensive DXA machines. The Chapman bone algorithm (CBA), a mathematical treatment that enables osteoporosis determination by using simply-assayed bone metabolites from blood serum, has been previously presented as a cheaper and feasible alternative for analyzing bone health. The CBA has a sensitivity of 1.0 and a specificity of 0.83, with an area under the Receiver Operating Characteristic curve of 0.93. Our goal was to utilize existing data from primary literature sources to determine if the CBA could be applied with similar or equal fidelity.Methods: We obtained mean values from analyses of serum Osteocalcin (s-OC) and serum Pyridinoline (s-PYD) markers in conjunction with patient age from various large-sample data sets available in primary literature.Results: Following analyses of aggregated mean values from the literature, we found that 60% of studies predicted the presence or absence of osteoporosis with the same degree of accuracy between FRAX and CBA methods. Osteoporosis was defined as having a t-score of <-2.5 (FRAX) or surpassing the threshold p-value of >0.035 (CBA).Conclusions: We expected higher agreement between the FRAX scores and our CBA, but this may be due to the aggregated nature of the data. Our findings indicated the need to advance the CBA in analyzing larger-scale primary data sets, underscoring the importance of raw data analysis, to determine the full efficacy of this diagnostic tool.

scholarly journals Application of portrait recognition system for emergency evacuation in mass emergencies

2021 ◽  
Vol 30 (1) ◽  
pp. 893-902
Author(s):  
Ke Xu
Keyword(s):  
Detection Rate ◽  
Characteristic Curve ◽  
Recognition Rate ◽  
Recognition System ◽  
Emergency Evacuation ◽  
Shopping Mall ◽  
Single Shot ◽  
Data Set ◽  
Linear Discriminant ◽  
Adaboost Algorithm

Abstract A portrait recognition system can play an important role in emergency evacuation in mass emergencies. This paper designed a portrait recognition system, analyzed the overall structure of the system and the method of image preprocessing, and used the Single Shot MultiBox Detector (SSD) algorithm for portrait detection. It also designed an improved algorithm combining principal component analysis (PCA) with linear discriminant analysis (LDA) for portrait recognition and tested the system by applying it in a shopping mall to collect and monitor the portrait and establish a data set. The results showed that the missing detection rate and false detection rate of the SSD algorithm were 0.78 and 2.89%, respectively, which were lower than those of the AdaBoost algorithm. Comparisons with PCA, LDA, and PCA + LDA algorithms demonstrated that the recognition rate of the improved PCA + LDA algorithm was the highest, which was 95.8%, the area under the receiver operating characteristic curve was the largest, and the recognition time was the shortest, which was 465 ms. The experimental results show that the improved PCA + LDA algorithm is reliable in portrait recognition and can be used for emergency evacuation in mass emergencies.

scholarly journals Classification of Clinically Significant Prostate Cancer on Multi-Parametric MRI: A Validation Study Comparing Deep Learning and Radiomics

Cancers ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 12
Author(s):  
Jose M. Castillo T. ◽  
Muhammad Arif ◽  
Martijn P. A. Starmans ◽  
Wiro J. Niessen ◽  
Chris H. Bangma ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Deep Learning ◽  
Characteristic Curve ◽  
Model Development ◽  
Learning Model ◽  
Multiparametric Mri ◽  
Data Sets ◽  
Data Set ◽  
Test Sets ◽  
Deep Learning Model

The computer-aided analysis of prostate multiparametric MRI (mpMRI) could improve significant-prostate-cancer (PCa) detection. Various deep-learning- and radiomics-based methods for significant-PCa segmentation or classification have been reported in the literature. To be able to assess the generalizability of the performance of these methods, using various external data sets is crucial. While both deep-learning and radiomics approaches have been compared based on the same data set of one center, the comparison of the performances of both approaches on various data sets from different centers and different scanners is lacking. The goal of this study was to compare the performance of a deep-learning model with the performance of a radiomics model for the significant-PCa diagnosis of the cohorts of various patients. We included the data from two consecutive patient cohorts from our own center (n = 371 patients), and two external sets of which one was a publicly available patient cohort (n = 195 patients) and the other contained data from patients from two hospitals (n = 79 patients). Using multiparametric MRI (mpMRI), the radiologist tumor delineations and pathology reports were collected for all patients. During training, one of our patient cohorts (n = 271 patients) was used for both the deep-learning- and radiomics-model development, and the three remaining cohorts (n = 374 patients) were kept as unseen test sets. The performances of the models were assessed in terms of their area under the receiver-operating-characteristic curve (AUC). Whereas the internal cross-validation showed a higher AUC for the deep-learning approach, the radiomics model obtained AUCs of 0.88, 0.91 and 0.65 on the independent test sets compared to AUCs of 0.70, 0.73 and 0.44 for the deep-learning model. Our radiomics model that was based on delineated regions resulted in a more accurate tool for significant-PCa classification in the three unseen test sets when compared to a fully automated deep-learning model.

scholarly journals Investigation of the international comparability of population-based routine hospital data set derived comorbidity scores for patients with lung cancer

Thorax ◽  
2017 ◽  
Vol 73 (4) ◽  
pp. 339-349 ◽  
Author(s):  
Margreet Lüchtenborg ◽  
Eva J A Morris ◽  
Daniela Tataru ◽  
Victoria H Coupland ◽  
Andrew Smith ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Survival ◽  
Population Based ◽  
Data Sets ◽  
Hospital Data ◽  
Data Set ◽  
Discharge Data ◽  
International Differences ◽  
Cancer Data ◽  
Comorbidity Scores

IntroductionThe International Cancer Benchmarking Partnership (ICBP) identified significant international differences in lung cancer survival. Differing levels of comorbid disease across ICBP countries has been suggested as a potential explanation of this variation but, to date, no studies have quantified its impact. This study investigated whether comparable, robust comorbidity scores can be derived from the different routine population-based cancer data sets available in the ICBP jurisdictions and, if so, use them to quantify international variation in comorbidity and determine its influence on outcome.MethodsLinked population-based lung cancer registry and hospital discharge data sets were acquired from nine ICBP jurisdictions in Australia, Canada, Norway and the UK providing a study population of 233 981 individuals. For each person in this cohort Charlson, Elixhauser and inpatient bed day Comorbidity Scores were derived relating to the 4–36 months prior to their lung cancer diagnosis. The scores were then compared to assess their validity and feasibility of use in international survival comparisons.ResultsIt was feasible to generate the three comorbidity scores for each jurisdiction, which were found to have good content, face and concurrent validity. Predictive validity was limited and there was evidence that the reliability was questionable.ConclusionThe results presented here indicate that interjurisdictional comparability of recorded comorbidity was limited due to probable differences in coding and hospital admission practices in each area. Before the contribution of comorbidity on international differences in cancer survival can be investigated an internationally harmonised comorbidity index is required.

Performance of preoperative plasma HE4 and CA-125 levels in predicting ovarian cancer mortality in women with epithelial ovarian cancer (EOC).

2017 ◽  
Vol 35 (15_suppl) ◽  
pp. e17076-e17076 ◽  
Author(s):  
Isabelle Bairati ◽  
Jean Gregoire ◽  
Marie Plante ◽  
Pierre Douville
Keyword(s):  
Ovarian Cancer ◽  
External Validation ◽  
Survival Rates ◽  
Disease Free Survival ◽  
Roc Curves ◽  
Ca 125 ◽  
Youden Index ◽  
P Value ◽  
Optimal Thresholds ◽  
Lr Test

e17076 Background: Additional prognostic biomarkers are needed to better manage women with EOC, especially dichotomized indicators for decision making. The objective of this external validation study was to assess the performance of preoperative plasma HE4 and CA-125 levels in predicting mortality by EOC. Methods: Eligible EOC women were newly diagnosed cases treated by upfront debulking surgery in a gynecology oncology center (CHU de Québec, L’Hôtel-Dieu, Canada) in 1988-2006 (cohort 1, n=136) and in 2007-2013 (cohort 2, n=177). All FIGO stages were included. Preoperative plasma HE4 and CA-125 levels were measured by Elecsys® automated immunoassay (Roche Diagnostics). Dates and causes of death were obtained by record linkage with the Quebec mortality files. In cohort 1, time-dependent receiver operating characteristic (ROC) curves were performed and optimal thresholds for HE4 and CA-125 were generated using the Youden index J. In cohort 2, crude and standardized Cox proportional models were done to validate the usefulness of these biomarkers according to their optimal thresholds. Standardized models included standard prognostic factors. The Likelihood Ratio (LR) tests were done to compare the standardized models with and without each biomarker. Results: In cohorts 1 and 2, medians of follow-up were respectively 5.3 and 3.2 years. Five-year disease free survival rates were 53% in cohort 1 and 54% in cohort 2. In cohort 1, the AUC for HE4 and CA-125 were respectively 64.2 (95% CI: 54.7-73.6) and 63.1 (95%CI: 53.6-72.6). The optimal thresholds were 277 pmol/L for HE4 and 282 U/ml for CA-125. In cohort 2, higher levels of plasma HE4 (≥277 pmol/L) were significantly associated with death by EOC (adjusted hazard ratio (aHR): 1.80; 95% CI: 1.03-3.15; p-value for LR test: 0.03), while higher levels of CA-125 (≥282 U/ml) were not associated with death by EOC (aHR: 1.50; 95% CI: 0.88-2.55; p-value for LR-test: 0.12). In serous EOC, the associations with mortality were respectively 2.46 (95% CI: 1.26-4.80) for HE4 and 1.56 (0.87-2.80) for CA-125. Conclusions: Preoperative plasma HE4 is a promising prognostic biomarker in women with EOC and performs better than CA-125 to predict mortality.

scholarly journals The probability distribution of 3D shapes of galaxy clusters from 2D X-ray images

2021 ◽  
Vol 503 (2) ◽  
pp. 2791-2803
Author(s):  
Swapnil Shankar ◽  
Rishi Khatri
Keyword(s):  
Probability Distribution ◽  
Galaxy Clusters ◽  
Galaxy Cluster ◽  
Data Sets ◽  
X Rays ◽  
Data Set ◽  
X Ray ◽  
Individual Object ◽  
3D Shape ◽  
3D Shapes

ABSTRACT We present a new method to determine the probability distribution of the 3D shapes of galaxy clusters from the 2D images using stereology. In contrast to the conventional approach of combining different data sets (such as X-rays, Sunyaev–Zeldovich effect, and lensing) to fit a 3D model of a galaxy cluster for each cluster, our method requires only a single data set, such as X-ray observations or Sunyaev–Zeldovich effect observations, consisting of sufficiently large number of clusters. Instead of reconstructing the 3D shape of an individual object, we recover the probability distribution function (PDF) of the 3D shapes of the observed galaxy clusters. The shape PDF is the relevant statistical quantity, which can be compared with the theory and used to test the cosmological models. We apply this method to publicly available Chandra X-ray data of 89 well-resolved galaxy clusters. Assuming ellipsoidal shapes, we find that our sample of galaxy clusters is a mixture of prolate and oblate shapes, with a preference for oblateness with the most probable ratio of principle axes 1.4 : 1.3 : 1. The ellipsoidal assumption is not essential to our approach and our method is directly applicable to non-ellipsoidal shapes. Our method is insensitive to the radial density and temperature profiles of the cluster. Our method is sensitive to the changes in shape of the X-ray emitting gas from inner to outer regions and we find evidence for variation in the 3D shape of the X-ray emitting gas with distance from the centre.

scholarly journals The Stunting Tool for Early Prevention: development and external validation of a novel tool to predict risk of stunting in children at 3 years of age

2019 ◽  
Vol 4 (6) ◽  
pp. e001801
Author(s):  
Sarah Hanieh ◽  
Sabine Braat ◽  
Julie A Simpson ◽  
Tran Thi Thu Ha ◽  
Thach D Tran ◽  
...  
Keyword(s):  
Characteristic Curve ◽  
External Validation ◽  
Model Development ◽  
Validation Data ◽  
Data Set ◽  
Growth Faltering ◽  
Development Data ◽  
Gestational Age At Birth ◽  
Development And Validation ◽  
The Impact

IntroductionGlobally, an estimated 151 million children under 5 years of age still suffer from the adverse effects of stunting. We sought to develop and externally validate an early life predictive model that could be applied in infancy to accurately predict risk of stunting in preschool children.MethodsWe conducted two separate prospective cohort studies in Vietnam that intensively monitored children from early pregnancy until 3 years of age. They included 1168 and 475 live-born infants for model development and validation, respectively. Logistic regression on child stunting at 3 years of age was performed for model development, and the predicted probabilities for stunting were used to evaluate the performance of this model in the validation data set.ResultsStunting prevalence was 16.9% (172 of 1015) in the development data set and 16.4% (70 of 426) in the validation data set. Key predictors included in the final model were paternal and maternal height, maternal weekly weight gain during pregnancy, infant sex, gestational age at birth, and infant weight and length at 6 months of age. The area under the receiver operating characteristic curve in the validation data set was 0.85 (95% Confidence Interval, 0.80–0.90).ConclusionThis tool applied to infants at 6 months of age provided valid prediction of risk of stunting at 3 years of age using a readily available set of parental and infant measures. Further research is required to examine the impact of preventive measures introduced at 6 months of age on those identified as being at risk of growth faltering at 3 years of age.

Geostatistical Joint Interpretation of Gravity and Magnetotelluric Data of the US Cordillera

2021 ◽  
Author(s):  
Mohammad Shehata ◽  
Hideki Mizunaga
Keyword(s):  
Gravity Data ◽  
Three Dimensional ◽  
Data Sets ◽  
Spatial Expansion ◽  
Magnetotelluric Data ◽  
Data Set ◽  
Entire Area ◽  
Mean Values ◽  
Local Means ◽  
The Us

&lt;p&gt;Long-period magnetotelluric and gravity data were acquired to investigate the US cordillera's crustal structure. The magnetotelluric data are being acquired across the continental USA on a quasi-regular grid of &amp;#8764;70 km spacing as an electromagnetic component of the National Science Foundation EarthScope/USArray Program. International Gravimetreique Bureau compiled gravity Data at high spatial resolution. Due to the difference in data coverage density, the geostatistical joint integration was utilized to map the subsurface structures with adequate resolution. First, a three-dimensional inversion of each data set was applied separately.&lt;/p&gt;&lt;p&gt;The inversion results of both data sets show a similarity of structure for data structuralizing. The individual result of both data sets is resampled at the same locations using the kriging method by considering each inversion model to estimate the coefficient. Then, the Layer Density Correction (LDC) process's enhanced density distribution was applied to MT data's spatial expansion process. Simple Kriging with varying Local Means (SKLM) was applied to the residual analysis and integration. For this purpose, the varying local means of the resistivity were estimated using the corrected gravity data by the Non-Linear Indicator Transform (NLIT), taking into account the spatial correlation. After that, the spatial expansion analysis of MT data obtained sparsely was attempted using the estimated local mean values and SKLM method at the sections where the MT survey was carried out and for the entire area where density distributions exist. This research presents the integration results and the stand-alone inversion results of three-dimensional gravity and magnetotelluric data.&lt;/p&gt;

scholarly journals QOLP-30. CLINICAL PREDICTIVE MODEL FOR THE DEVELOPMENT OF VENOUS THROMBOEMBOLISM IN GLIOBLASTOMA

2019 ◽  
Vol 21 (Supplement_6) ◽  
pp. vi204-vi204
Author(s):  
Shlomit Yust-Katz ◽  
Vijaya Donthireddy ◽  
Jacob Mandel ◽  
Hussna Abunafeesa ◽  
Neha Patil ◽  
...  
Keyword(s):  
Venous Thromboembolism ◽  
Adjuvant Chemotherapy ◽  
Predictive Model ◽  
Model Building ◽  
External Validation ◽  
High Sensitivity ◽  
High Specificity ◽  
P Value ◽  
Data Set ◽  
Henry Ford

Abstract INTRODUCTION The risk of venous thromboembolism (VTE) remains high for patients with glioblastoma (GBM) throughout the disease trajectory. Our previous work demonstrated the Khorana scale lacks specificity in this population. We therefore constructed, and attempted to validate a predictive model specific for the development of VTE during adjuvant chemotherapy in glioblastoma patients. METHODS A prior study of GBM patients treated at MD Anderson (MDACC) during the years 2005–2011 found from a multivariate analysis that male sex, BMI ≥ 35, KPS ≤ 80, and steroid therapy were significantly associated with the development of VTE. A predictive model from the MDACC cohort was created using these risk factors, and we attempted to validate the model in an independent cohort of GBM patients treated at Henry Ford from 2010–2015. RESULTS To develop the model 315 patients from the MDACC cohort were randomly divided into two parts: training (75% of data) used for model building, and validation (25% of data) used for model validation. Using the predictive model, the MDACC validation cohort found 80% sensitivity and 80% specificity. We then validated the model in the Henry Ford cohort of 190 GBM patients of which 50 developed a VTE. In the external validation set, the predictive model was found to have a sensitivity = 78% and specificity = 49.3% (Fisher test p-value = 0.0008). CONCLUSIONS Our predictive model for the development of VTE during adjuvant chemotherapy in GBM patients retained high sensitivity in an external data set, however high specificity was lost. While the specificity in our model was higher than in previous studies examining the Khorona scale in GBM patients, further refinement to improve the models reliability to correctly identify people who will not later develop a VTE may be helpful.

scholarly journals Detection of features associated with neovascular age-related macular degeneration in ethnically distinct data sets by an optical coherence tomography: trained deep learning algorithm

2020 ◽  
pp. bjophthalmol-2020-316984
Author(s):  
Tyler Hyungtaek Rim ◽  
Aaron Y Lee ◽  
Daniel S Ting ◽  
Kelvin Teo ◽  
Bjorn Kaijun Betzler ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Macular Degeneration ◽  
External Validation ◽  
Age Related Macular Degeneration ◽  
Data Sets ◽  
Optical Coherence ◽  
Data Set ◽  
Saliency Maps ◽  
Age Related

BackgroundThe ability of deep learning (DL) algorithms to identify eyes with neovascular age-related macular degeneration (nAMD) from optical coherence tomography (OCT) scans has been previously established. We herewith evaluate the ability of a DL model, showing excellent performance on a Korean data set, to generalse onto an American data set despite ethnic differences. In addition, expert graders were surveyed to verify if the DL model was appropriately identifying lesions indicative of nAMD on the OCT scans.MethodsModel development data set—12 247 OCT scans from South Korea; external validation data set—91 509 OCT scans from Washington, USA. In both data sets, normal eyes or eyes with nAMD were included. After internal testing, the algorithm was sent to the University of Washington, USA, for external validation. Area under the receiver operating characteristic curve (AUC) and precision–recall curve (AUPRC) were calculated. For model explanation, saliency maps were generated using Guided GradCAM.ResultsOn external validation, AUC and AUPRC remained high at 0.952 (95% CI 0.942 to 0.962) and 0.891 (95% CI 0.875 to 0.908) at the individual level. Saliency maps showed that in normal OCT scans, the fovea was the main area of interest; in nAMD OCT scans, the appropriate pathological features were areas of model interest. Survey of 10 retina specialists confirmed this.ConclusionOur DL algorithm exhibited high performance for nAMD identification in a Korean population, and generalised well to an ethnically distinct, American population. The model correctly focused on the differences within the macular area to extract features associated with nAMD.

Sign in / Sign up

Export Citation Format

Share Document