scholarly journals Potential of High Dimensional Radiomic Features to Assess Flowing Blood Components in Non-contrast CT Scans

Author(s):  
Scherwin Mahmoudi ◽  
Simon S. Martin ◽  
Jörg Ackermann ◽  
Yauheniya Zhdanovich ◽  
Ina Koch ◽  
...  

Abstract Background: To assess the potential of radiomic features to quantify components of flowing blood to non-invasively predict moderate-to-severe anemia in non-contrast enhanced CT scans. Methods: One hundred patients (median age, 69 years; range, 19–94 years) who received CT scans of the thoracolumbar spine and blood-testing for hemoglobin and hematocrit levels ± 24h between 08/2018 and 11/2019 were retrospectively included. Intraaortic blood was segmented using a spherical volume of interest with consecutive radiomic analysis. Feature selection was performed applying analysis of correlation and collinearity. The final feature set was obtained to differentiate moderate-to-severe anemia. Random forest machine learning was applied and predictive performance was assessed. A decision-tree was obtained to propose a cut-off value of CT Hounsfield units (HU).Results: High correlation with hemoglobin and hematocrit levels was shown for first-order radiomic features (p<0.001 to p=0.032). The top 3 features showed high correlation to hemoglobin values (p) and minimal collinearity (r) to the top ranked feature Median (p<0.001), Energy (p=0.002, r=0.387), Minimum (p=0.032, r=0.437). Median (p<0.001) and Minimum (p=0.003) differed in moderate-to-severe anemia compared to non-anemic state. Median yielded superiority to the combination of Median and Minimum (p(AUC)=0.015, p(precision)=0.017, p(accuracy)=0.612) in the predictive performance employing random forest analysis. A Median HU value ≤ 36.5 indicated moderate-to-severe anemia (accuracy=0.90, precision=0.80).Conclusions: First-order radiomic features correlate with hemoglobin levels and may be feasible for the prediction of moderate-to-severe anemia. High dimensional radiomic features did not inherit the potential to augment the data in our exemplary use case of flowing blood component assessment.Trial registration: Retrospectively registered.

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Scherwin Mahmoudi ◽  
Simon S. Martin ◽  
Jörg Ackermann ◽  
Yauheniya Zhdanovich ◽  
Ina Koch ◽  
...  

Abstract Background To assess the potential of radiomic features to quantify components of blood in intraaortic vessels to non-invasively predict moderate-to-severe anemia in non-contrast enhanced CT scans. Methods One hundred patients (median age, 69 years; range, 19–94 years) who received CT scans of the thoracolumbar spine and blood-testing for hemoglobin and hematocrit levels ± 24 h between 08/2018 and 11/2019 were retrospectively included. Intraaortic blood was segmented using a spherical volume of interest of 1 cm diameter with consecutive radiomic analysis applying PyRadiomics software. Feature selection was performed applying analysis of correlation and collinearity. The final feature set was obtained to differentiate moderate-to-severe anemia. Random forest machine learning was applied and predictive performance was assessed. A decision-tree was obtained to propose a cut-off value of CT Hounsfield units (HU). Results High correlation with hemoglobin and hematocrit levels was shown for first-order radiomic features (p < 0.001 to p = 0.032). The top 3 features showed high correlation to hemoglobin values (p) and minimal collinearity (r) to the top ranked feature Median (p < 0.001), Energy (p = 0.002, r = 0.387), Minimum (p = 0.032, r = 0.437). Median (p < 0.001) and Minimum (p = 0.003) differed in moderate-to-severe anemia compared to non-anemic state. Median yielded superiority to the combination of Median and Minimum (p(AUC) = 0.015, p(precision) = 0.017, p(accuracy) = 0.612) in the predictive performance employing random forest analysis. A Median HU value ≤ 36.5 indicated moderate-to-severe anemia (accuracy = 0.90, precision = 0.80). Conclusions First-order radiomic features correlate with hemoglobin levels and may be feasible for the prediction of moderate-to-severe anemia. High dimensional radiomic features did not aid augmenting the data in our exemplary use case of intraluminal blood component assessment. Trial registration Retrospectively registered.


BJS Open ◽  
2021 ◽  
Vol 5 (1) ◽  
Author(s):  
M J Wilkinson ◽  
H Snow ◽  
K Downey ◽  
K Thomas ◽  
A Riddell ◽  
...  

Abstract Background Diagnosis of lymph node (LN) metastasis in melanoma with non-invasive methods is challenging. The aim of this study was to evaluate the diagnostic accuracy of six LN characteristics on CT in detecting melanoma-positive ilioinguinal LN metastases, and to determine whether inguinal LN characteristics can predict pelvic LN involvement. Methods This was a single-centre retrospective study of patients with melanoma LN metastases at a tertiary cancer centre between 2008 and 2016. Patients who had preoperative contrast-enhanced CT assessment and ilioinguinal LN dissection were included. CT scans containing significant artefacts obscuring the pelvis were excluded. CT scans were reanalysed for six LN characteristics (extracapsular spread (ECS), minimum axis (MA), absence of fatty hilum (FH), asymmetrical cortical nodule (CAN), abnormal contrast enhancement (ACE) and rounded morphology (RM)) and compared with postoperative histopathological findings. Results A total of 90 patients were included. Median age was 58 (range 23–85) years. Eighty-eight patients (98 per cent) had pathology-positive inguinal disease and, of these, 45 (51 per cent) had concurrent pelvic disease. The most common CT characteristics found in pathology-positive inguinal LNs were MA greater than 10 mm (97 per cent), ACE (80 per cent), ECS (38 per cent) and absence of RM (38 per cent). In multivariable analysis, inguinal LN characteristics on CT indicative of pelvic disease were RM (odds ratio (OR) 3.3, 95 per cent c.i. 1.2 to 8.7) and ECS (OR 4.2, 1.6 to 11.3). Cloquet’s node is known to be a poor predictor of pelvic spread. Pelvic LN disease was present in 50 per cent patients, but only 7 per cent had a pathology-positive Cloquet’s node. Conclusion Additional CT radiological characteristics, especially ECS and RM, may improve diagnostic accuracy and aid clinical decisions regarding the need for inguinal or ilioinguinal dissection.


2020 ◽  
Vol 2020 (12) ◽  
Author(s):  
Ke-Pan Xie ◽  
Ligong Bian ◽  
Yongcheng Wu

Abstract We study electroweak baryogenesis in the SO(6)/SO(5) composite Higgs model with the third generation quarks being embedded in the 20′ representation of SO(6). The scalar sector contains one Higgs doublet and one real singlet, and their potential is given by the Coleman-Weinberg potential evaluated from the form factors of the lightest vector and fermion resonances. We show that the resonance masses at $$ \mathcal{O}\left(1\sim 10\kern0.5em \mathrm{TeV}\right) $$ O 1 ∼ 10 TeV can generate a potential that triggers the strong first-order electroweak phase transition (SFOEWPT). The CP violating phase arising from the dimension-6 operator in the top sector is sufficient to yield the observed baryon asymmetry of the universe. The SFOEWPT parameter space is detectable at the future space-based detectors.


Atmosphere ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 552
Author(s):  
Bu-Yo Kim ◽  
Joo Wan Cha ◽  
Ki-Ho Chang ◽  
Chulkyu Lee

In this study, the visibility of South Korea was predicted (VISRF) using a random forest (RF) model based on ground observation data from the Automated Synoptic Observing System (ASOS) and air pollutant data from the European Centre for Medium-Range Weather Forecasts (ECMWF) Copernicus Atmosphere Monitoring Service (CAMS) model. Visibility was predicted and evaluated using a training set for the period 2017–2018 and a test set for 2019. VISRF results were compared and analyzed using visibility data from the ASOS (VISASOS) and the Unified Model (UM) Local Data Assimilation and Prediction System (LDAPS) (VISLDAPS) operated by the Korea Meteorological Administration (KMA). Bias, root mean square error (RMSE), and correlation coefficients (R) for the VISASOS and VISLDAPS datasets were 3.67 km, 6.12 km, and 0.36, respectively, compared to 0.14 km, 2.84 km, and 0.81, respectively, for the VISASOS and VISRF datasets. Based on these comparisons, the applied RF model offers significantly better predictive performance and more accurate visibility data (VISRF) than the currently available VISLDAPS outputs. This modeling approach can be implemented by authorities to accurately estimate visibility and thereby reduce accidents, risks to public health, and economic losses, as well as inform on urban development policies and environmental regulations.


2012 ◽  
Vol 8 (2) ◽  
pp. 44-63 ◽  
Author(s):  
Baoxun Xu ◽  
Joshua Zhexue Huang ◽  
Graham Williams ◽  
Qiang Wang ◽  
Yunming Ye

The selection of feature subspaces for growing decision trees is a key step in building random forest models. However, the common approach using randomly sampling a few features in the subspace is not suitable for high dimensional data consisting of thousands of features, because such data often contains many features which are uninformative to classification, and the random sampling often doesn’t include informative features in the selected subspaces. Consequently, classification performance of the random forest model is significantly affected. In this paper, the authors propose an improved random forest method which uses a novel feature weighting method for subspace selection and therefore enhances classification performance over high-dimensional data. A series of experiments on 9 real life high dimensional datasets demonstrated that using a subspace size of features where M is the total number of features in the dataset, our random forest model significantly outperforms existing random forest models.


2021 ◽  
pp. 1-15
Author(s):  
Zhaozhao Xu ◽  
Derong Shen ◽  
Yue Kou ◽  
Tiezheng Nie

Due to high-dimensional feature and strong correlation of features, the classification accuracy of medical data is not as good enough as expected. feature selection is a common algorithm to solve this problem, and selects effective features by reducing the dimensionality of high-dimensional data. However, traditional feature selection algorithms have the blindness of threshold setting and the search algorithms are liable to fall into a local optimal solution. Based on it, this paper proposes a hybrid feature selection algorithm combining ReliefF and Particle swarm optimization. The algorithm is mainly divided into three parts: Firstly, the ReliefF is used to calculate the feature weight, and the features are ranked by the weight. Then ranking feature is grouped according to the density equalization, where the density of features in each group is the same. Finally, the Particle Swarm Optimization algorithm is used to search the ranking feature groups, and the feature selection is performed according to a new fitness function. Experimental results show that the random forest has the highest classification accuracy on the features selected. More importantly, it has the least number of features. In addition, experimental results on 2 medical datasets show that the average accuracy of random forest reaches 90.20%, which proves that the hybrid algorithm has a certain application value.


2020 ◽  
Vol 10 (1) ◽  
pp. 1-11
Author(s):  
Arvind Shrivastava ◽  
Nitin Kumar ◽  
Kuldeep Kumar ◽  
Sanjeev Gupta

The paper deals with the Random Forest, a popular classification machine learning algorithm to predict bankruptcy (distress) for Indian firms. Random Forest orders firms according to their propensity to default or their likelihood to become distressed. This is also useful to explain the association between the tendency of firm failure and its features. The results are analyzed vis-à-vis Tree Net. Both in-sample and out of sample estimations have been performed to compare Random Forest with Tree Net, which is a cutting edge data mining tool known to provide satisfactory estimation results. An exhaustive data set comprising companies from varied sectors have been included in the analysis. It is found that Tree Net procedure provides improved classification and predictive performance vis-à-vis Random Forest methodology consistently that may be utilized further by industry analysts and researchers alike for predictive purposes.


mBio ◽  
2020 ◽  
Vol 11 (3) ◽  
Author(s):  
Begüm D. Topçuoğlu ◽  
Nicholas A. Lesniak ◽  
Mack T. Ruffin ◽  
Jenna Wiens ◽  
Patrick D. Schloss

ABSTRACT Machine learning (ML) modeling of the human microbiome has the potential to identify microbial biomarkers and aid in the diagnosis of many diseases such as inflammatory bowel disease, diabetes, and colorectal cancer. Progress has been made toward developing ML models that predict health outcomes using bacterial abundances, but inconsistent adoption of training and evaluation methods call the validity of these models into question. Furthermore, there appears to be a preference by many researchers to favor increased model complexity over interpretability. To overcome these challenges, we trained seven models that used fecal 16S rRNA sequence data to predict the presence of colonic screen relevant neoplasias (SRNs) (n = 490 patients, 261 controls and 229 cases). We developed a reusable open-source pipeline to train, validate, and interpret ML models. To show the effect of model selection, we assessed the predictive performance, interpretability, and training time of L2-regularized logistic regression, L1- and L2-regularized support vector machines (SVM) with linear and radial basis function kernels, a decision tree, random forest, and gradient boosted trees (XGBoost). The random forest model performed best at detecting SRNs with an area under the receiver operating characteristic curve (AUROC) of 0.695 (interquartile range [IQR], 0.651 to 0.739) but was slow to train (83.2 h) and not inherently interpretable. Despite its simplicity, L2-regularized logistic regression followed random forest in predictive performance with an AUROC of 0.680 (IQR, 0.625 to 0.735), trained faster (12 min), and was inherently interpretable. Our analysis highlights the importance of choosing an ML approach based on the goal of the study, as the choice will inform expectations of performance and interpretability. IMPORTANCE Diagnosing diseases using machine learning (ML) is rapidly being adopted in microbiome studies. However, the estimated performance associated with these models is likely overoptimistic. Moreover, there is a trend toward using black box models without a discussion of the difficulty of interpreting such models when trying to identify microbial biomarkers of disease. This work represents a step toward developing more-reproducible ML practices in applying ML to microbiome research. We implement a rigorous pipeline and emphasize the importance of selecting ML models that reflect the goal of the study. These concepts are not particular to the study of human health but can also be applied to environmental microbiology studies.


Sign in / Sign up

Export Citation Format

Share Document