scholarly journals Automated Detection and Diameter Estimation for Mouse Mesenteric Artery Using Semantic Segmentation

2021 ◽  
pp. 1-9
Author(s):  
Akinori Higaki ◽  
Ahmad U.M. Mahmoud ◽  
Pierre Paradis ◽  
Ernesto L. Schiffrin
Keyword(s):  
Mesenteric Artery ◽  
Characteristic Curve ◽  
Binary Logistic Regression ◽  
Semantic Segmentation ◽  
Expansion Ratio ◽  
Machine Learning Algorithms ◽  
Strong Positive Correlation ◽  
Vessel Size ◽  
Before And After ◽  
Model Training

<b><i>Background:</i></b> Pressurized myography is useful for the assessment of small artery structures and function. However, this procedure requires technical expertise for sample preparation and effort to choose an appropriate sized artery. In this study, we developed an automatic artery/vein differentiation and a size measurement system utilizing machine learning algorithms. <b><i>Methods and Results:</i></b> We used 654 independent mouse mesenteric artery images for model training. The model yielded an Intersection-over-Union of 0.744 ± 0.031 and a Dice coefficient of 0.881 ± 0.016. The vessel size and lumen size calculated from the predicted vessel contours demonstrated a strong linear correlation with manually determined vessel sizes (<i>R</i> = 0.722 ± 0.048, <i>p</i> &#x3c; 0.001 for vessel size and <i>R</i> = 0.908 ± 0.027, <i>p</i> &#x3c; 0.001 for lumen size). Last, we assessed the relation between the vessel size before and after dissection using a pressurized myography system. We observed a strong positive correlation between the wall/lumen ratio before dissection and the lumen expansion ratio (<i>R</i> = 0.832, <i>p</i> &#x3c; 0.01). Using multivariate binary logistic regression, 2 models estimating whether the vessel met the size criteria (lumen size of 160–240 μm) were generated with an area under the receiver operating characteristic curve of 0.761 for the upper limit and 0.747 for the lower limit. <b><i>Conclusion:</i></b> The U-Net-based image analysis method could streamline the experimental approach.

scholarly journals Automated Detection and Diameter Estimation for Mouse Mesenteric Artery using Semantic Segmentation

2020 ◽  
Author(s):  
Akinori Higaki ◽  
Ahmad U. M. Mahmoud ◽  
Pierre Paradis ◽  
Ernesto L. Schiffrin
Keyword(s):  
Mesenteric Artery ◽  
Binary Logistic Regression ◽  
Semantic Segmentation ◽  
Expansion Ratio ◽  
Machine Learning Algorithms ◽  
Strong Positive Correlation ◽  
Cardiovascular Research ◽  
Vessel Size ◽  
Before And After ◽  
Model Training

AbstractBackgroundPressurized myography is useful for the assessment of small artery structure and function, and widely used in the field of cardiovascular research. However, this procedure requires technical expertise for the sample preparation and effort to choose an appropriate size of artery. In this study we sought to develop an automatic artery-vein differentiation and size measurement system utilizing the U-Net-based machine learning algorithms.Methods and ResultsWe used 654 independent mesenteric artery images from 59 mice for the model training and validation. Our segmentation model yielded 0.744 ±0.031 in IoU and 0.881 ±0.016 in Dice coefficient with 5-fold cross validation. The vessel size and the lumen size calculated from the predicted vessel contours demonstrated a strong linear correlation with the manually determined vessel sizes (R = 0.722 ±0.048, p<0.001 for vessel size and R = 0.908 ±0.027, p<0.001 for lumen size). Lastly, we assessed the relation between the vessel size before and after dissection using pressurized myography system. We observed a strong positive correlation between the wall/lumen ratio before dissection and the lumen expansion ratio (R2 = 0.671, p<0.01). Using multivariate binary logistic regression, two models estimating whether the vessel met the size criteria (lumen size of 160 to 240 μm) were generated with area under the ROC curve of 0.761 for the upper limit and 0.747 for the lower limit.ConclusionOur novel image analysis method with U-Net could streamline the experimental approach and may facilitate cardiovascular research.

Identify Compounds' Target Against Alzheimer's Disease Based on In-Silico Approach

2019 ◽  
Vol 16 (3) ◽  
pp. 193-208 ◽  
Author(s):  
Yan Hu ◽  
Guangya Zhou ◽  
Chi Zhang ◽  
Mengying Zhang ◽  
Qin Chen ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Small Molecule ◽  
Characteristic Curve ◽  
Machine Learning Algorithms ◽  
Learner Model ◽  
Mao B ◽  
Number Of Patients ◽  
Sar Model ◽  
Set Up

Background: Alzheimer's disease swept every corner of the globe and the number of patients worldwide has been rising. At present, there are as many as 30 million people with Alzheimer's disease in the world, and it is expected to exceed 80 million people by 2050. Consequently, the study of Alzheimer’s drugs has become one of the most popular medical topics. Methods: In this study, in order to build a predicting model for Alzheimer’s drugs and targets, the attribute discriminators CfsSubsetEval, ConsistencySubsetEval and FilteredSubsetEval are combined with search methods such as BestFirst, GeneticSearch and Greedystepwise to filter the molecular descriptors. Then the machine learning algorithms such as BayesNet, SVM, KNN and C4.5 are used to construct the 2D-Structure Activity Relationship(2D-SAR) model. Its modeling results are utilized for Receiver Operating Characteristic curve(ROC) analysis. Results: The prediction rates of correctness using Randomforest for AChE, BChE, MAO-B, BACE1, Tau protein and Non-inhibitor are 77.0%, 79.1%, 100.0%, 94.2%, 93.2% and 94.9%, respectively, which are overwhelming as compared to those of BayesNet, BP, SVM, KNN, AdaBoost and C4.5. Conclusion: In this paper, we conclude that Random Forest is the best learner model for the prediction of Alzheimer’s drugs and targets. Besides, we set up an online server to predict whether a small molecule is the inhibitor of Alzheimer's target at http://47.106.158.30:8080/AD/. Furthermore, it can distinguish the target protein of a small molecule.

Application of a Computer Vision Tool for Automated Glottic Tracking to Vocal Fold Paralysis Patients

2021 ◽  
pp. 019459982198960
Author(s):  
Tiffany V. Wang ◽  
Nat Adamian ◽  
Phillip C. Song ◽  
Ramon A. Franco ◽  
Molly N. Huston ◽  
...  
Keyword(s):  
Vocal Fold ◽  
Assessment Tool ◽  
Medical Center ◽  
Characteristic Curve ◽  
Academic Medical Center ◽  
Vocal Fold Paralysis ◽  
Control Group ◽  
Large Patient ◽  
Patient Reported ◽  
Before And After

Objectives (1) Demonstrate true vocal fold (TVF) tracking software (AGATI [Automated Glottic Action Tracking by artificial Intelligence]) as a quantitative assessment of unilateral vocal fold paralysis (UVFP) in a large patient cohort. (2) Correlate patient-reported metrics with AGATI measurements of TVF anterior glottic angles, before and after procedural intervention. Study Design Retrospective cohort study. Setting Academic medical center. Methods AGATI was used to analyze videolaryngoscopy from healthy adults (n = 72) and patients with UVFP (n = 70). Minimum, 3rd percentile, 97th percentile, and maximum anterior glottic angles (AGAs) were computed for each patient. In patients with UVFP, patient-reported outcomes (Voice Handicap Index 10, Dyspnea Index, and Eating Assessment Tool 10) were assessed, before and after procedural intervention (injection or medialization laryngoplasty). A receiver operating characteristic curve for the logistic fit of paralysis vs control group was used to determine AGA cutoff values for defining UVFP. Results Mean (SD) 3rd percentile AGA (in degrees) was 2.67 (3.21) in control and 5.64 (5.42) in patients with UVFP ( P < .001); mean (SD) 97th percentile AGA was 57.08 (11.14) in control and 42.59 (12.37) in patients with UVFP ( P < .001). For patients with UVFP who underwent procedural intervention, the mean 97th percentile AGA decreased by 5 degrees from pre- to postprocedure ( P = .026). The difference between the 97th and 3rd percentile AGA predicted UVFP with 77% sensitivity and 92% specificity ( P < .0001). There was no correlation between AGA measurements and patient-reported outcome scores. Conclusions AGATI demonstrated a difference in AGA measurements between paralysis and control patients. AGATI can predict UVFP with 77% sensitivity and 92% specificity.

scholarly journals Semantic segmentation of PolSAR image data using advanced deep learning model

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Rajat Garg ◽  
Anil Kumar ◽  
Nikunj Bansal ◽  
Manish Prateek ◽  
Shashi Kumar
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Urban Area ◽  
Urban Areas ◽  
Learning Algorithms ◽  
Semantic Segmentation ◽  
Learning Model ◽  
Machine Learning Algorithms ◽  
Deep Learning Model

AbstractUrban area mapping is an important application of remote sensing which aims at both estimation and change in land cover under the urban area. A major challenge being faced while analyzing Synthetic Aperture Radar (SAR) based remote sensing data is that there is a lot of similarity between highly vegetated urban areas and oriented urban targets with that of actual vegetation. This similarity between some urban areas and vegetation leads to misclassification of the urban area into forest cover. The present work is a precursor study for the dual-frequency L and S-band NASA-ISRO Synthetic Aperture Radar (NISAR) mission and aims at minimizing the misclassification of such highly vegetated and oriented urban targets into vegetation class with the help of deep learning. In this study, three machine learning algorithms Random Forest (RF), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM) have been implemented along with a deep learning model DeepLabv3+ for semantic segmentation of Polarimetric SAR (PolSAR) data. It is a general perception that a large dataset is required for the successful implementation of any deep learning model but in the field of SAR based remote sensing, a major issue is the unavailability of a large benchmark labeled dataset for the implementation of deep learning algorithms from scratch. In current work, it has been shown that a pre-trained deep learning model DeepLabv3+ outperforms the machine learning algorithms for land use and land cover (LULC) classification task even with a small dataset using transfer learning. The highest pixel accuracy of 87.78% and overall pixel accuracy of 85.65% have been achieved with DeepLabv3+ and Random Forest performs best among the machine learning algorithms with overall pixel accuracy of 77.91% while SVM and KNN trail with an overall accuracy of 77.01% and 76.47% respectively. The highest precision of 0.9228 is recorded for the urban class for semantic segmentation task with DeepLabv3+ while machine learning algorithms SVM and RF gave comparable results with a precision of 0.8977 and 0.8958 respectively.

scholarly journals Detecting cybersecurity attacks across different network features and learners

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Joffrey L. Leevy ◽  
John Hancock ◽  
Richard Zuech ◽  
Taghi M. Khoshgoftaar
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Machine Learning Algorithms ◽  
Feature Selection Technique ◽  
Impact Performance ◽  
Detection Model ◽  
Wide Range ◽  
Research Questions

AbstractMachine learning algorithms efficiently trained on intrusion detection datasets can detect network traffic capable of jeopardizing an information system. In this study, we use the CSE-CIC-IDS2018 dataset to investigate ensemble feature selection on the performance of seven classifiers. CSE-CIC-IDS2018 is big data (about 16,000,000 instances), publicly available, modern, and covers a wide range of realistic attack types. Our contribution is centered around answers to three research questions. The first question is, “Does feature selection impact performance of classifiers in terms of Area Under the Receiver Operating Characteristic Curve (AUC) and F1-score?” The second question is, “Does including the Destination_Port categorical feature significantly impact performance of LightGBM and Catboost in terms of AUC and F1-score?” The third question is, “Does the choice of classifier: Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Logistic Regression (LR), Catboost, LightGBM, or XGBoost, significantly impact performance in terms of AUC and F1-score?” These research questions are all answered in the affirmative and provide valuable, practical information for the development of an efficient intrusion detection model. To the best of our knowledge, we are the first to use an ensemble feature selection technique with the CSE-CIC-IDS2018 dataset.

scholarly journals Biological maturity and the anthropometric, physical and technical assessment of talent identified U16 Australian footballers

2017 ◽  
Vol 12 (3) ◽  
pp. 344-350 ◽  
Author(s):  
Ashley J Cripps ◽  
Christopher Joyce ◽  
Carl T Woods ◽  
Luke S Hopper
Keyword(s):  
Characteristic Curve ◽  
Vertical Jump ◽  
Binary Logistic Regression ◽  
Peak Height ◽  
Technical Skill ◽  
Height Velocity ◽  
State Representation ◽  
Peak Height Velocity ◽  
Biological Maturation ◽  
Australian Football

This study compared biological maturation, anthropometric, physical and technical skill measures between talent and non-talent identified junior Australian footballers. Players were recruited from the under 16 Western Australian Football League and classified as talent (state representation; n = 25, 15.7 ± 0.3 y) or non-talent identified (non-state representation; n = 25, 15.6 ± 0.4 y). Players completed a battery of anthropometric, physical and technical skill assessments. Maturity was estimated using years from peak height velocity calculations. Binary logistic regression was used to identify the variables demonstrating the strongest association with the main effect of ‘status’. A receiver operating characteristic curve was used to assess the level of discrimination provided by the strongest model. Talent identified under 16 players were biologically older, had greater stationary and dynamic leaps and superior handball skill when compared to their non-talent identified counterparts. The strongest model of status included standing height, non-dominant dynamic vertical jump and handball outcomes (AUC = 83.4%, CI = 72.1%–95.1%). Biological maturation influences anthropometric and physical capacities that are advantageous for performance in Australian football; talent identification methods should factor biological maturation as a confound in the search for junior players who are most likely to succeed in senior competition.

Remnant Lipoprotein Cholesterol as a Factor Related to Adult Fatty Liver Disease

2021 ◽  
Author(s):  
Shuang Zhang ◽  
Shitong Cheng ◽  
Xue He ◽  
Wei Wang ◽  
Ke Yun ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Characteristic Curve ◽  
Health Check ◽  
Lipoprotein Cholesterol ◽  
Strong Positive Correlation ◽  
Variable Model ◽  
Remnant Lipoprotein

Abstract Context Dyslipidemia is related to fatty liver disease (FLD), whose relationship with remnant lipoprotein cholesterol (RLP-C), a component of blood lipids, remains unclear. Objective To clarify the correlation between RLP-C and the occurrence and severity of FLD and establish an FLD discriminant model based on health check indicators. Methods Retrospective study of participants who underwent health check-up in the First Affiliated Hospital of China Medical University (Shenyang, China) between January and December 2019. We categorized participants according to liver ultrasound results and analyzed the correlation between RLP-C and occurrence of FLD (n = 38 885) through logistic regression, restricted cubic spline, and receiver operating characteristic curve. We categorized the severity of FLD according to the control attenuation parameter and analyzed the correlation between RLP-C and FLD severity through multiple logistic regression; only males were included (n = 564). Results The adjusted OR (aOR) per SD between RLP-C and FLD was 2.33 (95% CI 2.21-2.46, P &lt; .001), indicating a dose–response relationship (P &lt; .0001). The optimal cut-off value of RLP-C was 0.45 mmol/L and the area under the curve (AUC) was 0.79. The AUC of the 8-variable model was 0.89 in both the training and the validation sets. FLD severity was related to the level of RLP-C (aOR per SD = 1.29, 95% CI 1.07-1.55, P = .008). Conclusion RLP-C has a strong positive correlation with FLD occurrence and FLD severity. These results may help clinicians identify and implement interventions in individuals with high FLD risk and reduce FLD prevalence.

scholarly journals Influence of the Computer-Aided Decision Support System Design on Ultrasound-Based Breast Cancer Classification

Cancers ◽  
2022 ◽  
Vol 14 (2) ◽  
pp. 277
Author(s):  
Zuzanna Anna Magnuska ◽  
Benjamin Theek ◽  
Milita Darguzyte ◽  
Moritz Palmowski ◽  
Elmar Stickeler ◽  
...  
Keyword(s):  
Breast Lesion ◽  
Characteristic Curve ◽  
Cancer Diagnostics ◽  
Lesion Detection ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
P Value ◽  
Future Design ◽  
Sensitivity Specificity ◽  
Derivatives Of

Automation of medical data analysis is an important topic in modern cancer diagnostics, aiming at robust and reproducible workflows. Therefore, we used a dataset of breast US images (252 malignant and 253 benign cases) to realize and compare different strategies for CAD support in lesion detection and classification. Eight different datasets (including pre-processed and spatially augmented images) were prepared, and machine learning algorithms (i.e., Viola–Jones; YOLOv3) were trained for lesion detection. The radiomics signature (RS) was derived from detection boxes and compared with RS derived from manually obtained segments. Finally, the classification model was established and evaluated concerning accuracy, sensitivity, specificity, and area under the Receiver Operating Characteristic curve. After training on a dataset including logarithmic derivatives of US images, we found that YOLOv3 obtains better results in breast lesion detection (IoU: 0.544 ± 0.081; LE: 0.171 ± 0.009) than the Viola–Jones framework (IoU: 0.399 ± 0.054; LE: 0.096 ± 0.016). Interestingly, our findings show that the classification model trained with RS derived from detection boxes and the model based on the RS derived from a gold standard manual segmentation are comparable (p-value = 0.071). Thus, deriving radiomics signatures from the detection box is a promising technique for building a breast lesion classification model, and may reduce the need for the lesion segmentation step in the future design of CAD systems.

scholarly journals Predicting Metabolic Syndrome With Machine Learning Models Using a Decision Tree Algorithm: Retrospective Cohort Study (Preprint)

2019 ◽  
Author(s):  
Cheng-Sheng Yu ◽  
Yu-Jiun Lin ◽  
Chang-Hsien Lin ◽  
Sen-Te Wang ◽  
Shiyng-Yu Lin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Metabolic Syndrome ◽  
Logistic Regression ◽  
Decision Tree ◽  
Characteristic Curve ◽  
Significant Risk ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Health Examination ◽  
Multivariate Logistic Regression

BACKGROUND Metabolic syndrome is a cluster of disorders that significantly influence the development and deterioration of numerous diseases. FibroScan is an ultrasound device that was recently shown to predict metabolic syndrome with moderate accuracy. However, previous research regarding prediction of metabolic syndrome in subjects examined with FibroScan has been mainly based on conventional statistical models. Alternatively, machine learning, whereby a computer algorithm learns from prior experience, has better predictive performance over conventional statistical modeling. OBJECTIVE We aimed to evaluate the accuracy of different decision tree machine learning algorithms to predict the state of metabolic syndrome in self-paid health examination subjects who were examined with FibroScan. METHODS Multivariate logistic regression was conducted for every known risk factor of metabolic syndrome. Principal components analysis was used to visualize the distribution of metabolic syndrome patients. We further applied various statistical machine learning techniques to visualize and investigate the pattern and relationship between metabolic syndrome and several risk variables. RESULTS Obesity, serum glutamic-oxalocetic transaminase, serum glutamic pyruvic transaminase, controlled attenuation parameter score, and glycated hemoglobin emerged as significant risk factors in multivariate logistic regression. The area under the receiver operating characteristic curve values for classification and regression trees and for the random forest were 0.831 and 0.904, respectively. CONCLUSIONS Machine learning technology facilitates the identification of metabolic syndrome in self-paid health examination subjects with high accuracy.

scholarly journals Predicting the Risk of Hypertension Based on Several Easy-to-Collect Risk Factors: A Machine Learning Method

2021 ◽  
Vol 9 ◽  
Author(s):  
Huanhuan Zhao ◽  
Xiaoyu Zhang ◽  
Yang Xu ◽  
Lisheng Gao ◽  
Zuchang Ma ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Logistic Regression ◽  
Risk Prediction ◽  
Disease Risk ◽  
Learning Algorithms ◽  
Large Population ◽  
Machine Learning Algorithms ◽  
Hypertension Risk ◽  
Model Training

Hypertension is a widespread chronic disease. Risk prediction of hypertension is an intervention that contributes to the early prevention and management of hypertension. The implementation of such intervention requires an effective and easy-to-implement hypertension risk prediction model. This study evaluated and compared the performance of four machine learning algorithms on predicting the risk of hypertension based on easy-to-collect risk factors. A dataset of 29,700 samples collected through a physical examination was used for model training and testing. Firstly, we identified easy-to-collect risk factors of hypertension, through univariate logistic regression analysis. Then, based on the selected features, 10-fold cross-validation was utilized to optimize four models, random forest (RF), CatBoost, MLP neural network and logistic regression (LR), to find the best hyper-parameters on the training set. Finally, the performance of models was evaluated by AUC, accuracy, sensitivity and specificity on the test set. The experimental results showed that the RF model outperformed the other three models, and achieved an AUC of 0.92, an accuracy of 0.82, a sensitivity of 0.83 and a specificity of 0.81. In addition, Body Mass Index (BMI), age, family history and waist circumference (WC) are the four primary risk factors of hypertension. These findings reveal that it is feasible to use machine learning algorithms, especially RF, to predict hypertension risk without clinical or genetic data. The technique can provide a non-invasive and economical way for the prevention and management of hypertension in a large population.

Sign in / Sign up

Export Citation Format

Share Document