Prediction of blood supply in vestibular schwannomas using radiomics machine learning classifiers

This study attempts to explore the radiomics-based features of multi-parametric magnetic resonance imaging (MRI) and construct a machine-learning model to predict the blood supply in vestibular schwannoma preoperatively. By retrospectively collecting the preoperative MRI data of patients with vestibular schwannoma, patients were divided into poor and rich blood supply groups according to the intraoperative recording. Patients were divided into training and test cohorts (2:1), randomly. Stable features were retained by intra-group correlation coefficients (ICCs). Four feature selection methods and four classification methods were evaluated to construct favorable radiomics classifiers. The mean area under the curve (AUC) obtained in the test set for different combinations of feature selecting methods and classifiers was calculated separately to compare the performance of the models. Obtain and compare the best combination results with the performance of differentiation through visual observation in clinical diagnosis. 191 patients were included in this study. 3918 stable features were extracted from each patient. Least absolute shrinkage and selection operator (LASSO) and logistic regression model was selected as the optimal combinations after comparing the AUC calculated by models, which predicted the blood supply of vestibular schwannoma by K-Fold cross-validation method with a mean AUC = 0.88 and F1-score = 0.83. Radiomics machine-learning classifiers can accurately predict the blood supply of vestibular schwannoma by preoperative MRI data.

Prediction of Blood Supply in Vestibular Schwannomas Using Radiomics Machine-Learning Classifiers

ObjectiveThis study attempts to explore the radiomics-based features of multi-parametric magnetic resonance imaging (MRI) and construct a machine-learning model to predict the blood supply in vestibular schwannoma preoperatively.MethodsBy retrospectively collecting the preoperative MRI data of patients with vestibular schwannoma, patients were divided into poor and rich blood supply group according to the intraoperative recording. Patients were divided into training and test cohorts (2:1), randomly. Stable features were retained by intra-group correlation coefficients (ICCs). Four feature selection methods and four classification methods were evaluated to construct favorable radiomic classifiers. The mean area under the curve (AUC) obtained in the test set for different combinations of feature selecting methods and classifiers was calculated separately to compare the performance of the models. Obtain and compare the best combination result with the performance of differentiation through visual observation in clinical diagnosis.Results191 patients were included in this study. 3918 stable features were extracted each patient. Least absolute shrinkage and selection operator (LASSO) and logistic regression model was selected as the optimal combinations after comparing the AUC calculated by models, which predicted the blood supply of vestibular schwannoma by K-Fold cross-validation method with a mean AUC=0.90 and F1-score= 0.89.ConclusionRadiomics machine-learning classifiers can accurately predict the blood supply of vestibular schwannoma by preoperative MRI data.

Prediction of blood supply in vestibular schwannomas using radiomics machine-learning classifiers

Objective This study attempts to explore the radiomics-based features of multi-parametric magnetic resonance imaging (MRI) and construct a machine-learning model to predict the blood supply in vestibular schwannoma preoperatively. Methods By retrospectively collecting the preoperative MRI data of patients with vestibular schwannoma, patients were divided into poor and rich blood supply group according to the intraoperative recording. Patients were divided into training and test cohorts (2:1), randomly. Stable features were retained by intra-group correlation coefficients (ICCs). Four feature selection methods and four classification methods were evaluated to construct favorable radiomic classifiers. The mean area under the curve (AUC) obtained in the test set for different combinations of feature selecting methods and classifiers was calculated separately to compare the performance of the models. Obtain and compare the best combination result with the performance of differentiation through visual observation in clinical diagnosis. Results 191 patients were included in this study, with 119 in the rich blood supply group and 72 in the poor blood supply group. A total of 5226 features were extracted each patient, of which 3918 features were stable. LASSO and logistic regression model was selected as the optimal combinations after comparing the AUC calculated by models, which predicted the blood supply of vestibular schwannoma by K-Fold cross-validation method with a mean AUC = 0.90 and F1-score = 0.89, and the model outperformed the neurosurgeons' visual observation with a mean F1-score = 0.64. Conclusion Radiomics machine-learning classifiers can accurately predict the blood supply of vestibular schwannoma by preoperative MRI data.

Unraveling city-specific signature and identifying sample origin locations for the data from CAMDA MetaSUB challenge

Background Composition of microbial communities can be location-specific, and the different abundance of taxon within location could help us to unravel city-specific signature and predict the sample origin locations accurately. In this study, the whole genome shotgun (WGS) metagenomics data from samples across 16 cities around the world and samples from another 8 cities were provided as the main and mystery datasets respectively as the part of the CAMDA 2019 MetaSUB “Forensic Challenge”. The feature selecting, normalization, three methods of machine learning, PCoA (Principal Coordinates Analysis) and ANCOM (Analysis of composition of microbiomes) were conducted for both the main and mystery datasets. Results Features selecting, combined with the machines learning methods, revealed that the combination of the common features was effective for predicting the origin of the samples. The average error rates of 11.93 and 30.37% of three machine learning methods were obtained for main and mystery datasets respectively. Using the samples from main dataset to predict the labels of samples from mystery dataset, nearly 89.98% of the test samples could be correctly labeled as “mystery” samples. PCoA showed that nearly 60% of the total variability of the data could be explained by the first two PCoA axes. Although many cities overlapped, the separation of some cities was found in PCoA. The results of ANCOM, combined with importance score from the Random Forest, indicated that the common “family”, “order” of the main-dataset and the common “order” of the mystery dataset provided the most efficient information for prediction respectively. Conclusions The results of the classification suggested that the composition of the microbiomes was distinctive across the cities, which could be used to identify the sample origins. This was also supported by the results from ANCOM and importance score from the RF. In addition, the accuracy of the prediction could be improved by more samples and better sequencing depth.

Feature Selecting Hierarchical Neural Network for Industrial System Health Monitoring

Industrial System Health Monitoring relies usually on the monitoring of well-designed features. This requires both, the engineering of reliable features and a good methodology for their analysis. If traditionally, features were engineered based on the physics of the system, recent advances in machine learning demonstrated that features could be automatically learned and monitored. In particular, using Hierarchical Extreme Learning Machines (HELM), based on random features, very good results have already been achieved for health monitoring with training on healthy data only. Yet, although very useful and mathematically sound, random features have little popularity as they contradict the intuition and seem to rely on luck. This tends to increase the “blackbox” effect often associated with Machine Learning. To mitigate this, in this paper, we propose to modify the traditional HELM architecture such that, while still relying on random features, only the most useful features among a large population will be selected. Traditional HELM are made of stacked contractive autoencoders with `1- or `2-regularisation and of a classifier as last layer. To achieve our objective, we propose to opt for expanding auto-encoders instead, but trained with a strong Group-LASSO regularization. This Group-LASSO regularisation fosters the selection of as few features as possible, making the auto-encoder in reality (or in testing condition) contractive. This deterministic selection provides useful features for health monitoring, without the need of learning or manually engineering them. The proposed approach demonstrates a better performance for fault detection and isolation on case studies developed for HELM evaluation.