Classification and lateralization of temporal lobe epilepsies with and without hippocampal atrophy based on whole-brain automatic MRI segmentation

Brain images contain information suitable for automatically sorting subjects into categories such as healthy controls and patients. We sought to identify morphometric criteria for distinguishing controls (n = 28) from patients with unilateral temporal lobe epilepsy (TLE), 60 with and 20 without hippocampal atrophy (TLE-HA and TLE-N, respectively), and for determining the presumed side of seizure onset. The framework employs multi-atlas segmentation to estimate the volumes of 83 brain structures. A kernel-based separability criterion was then used to identify structures whose volumes discriminate between the groups. Next, we applied support vector machines (SVM) to the selected set for classification on the basis of volumes. We also computed pairwise similarities between all subjects and used spectral analysis to convert these into per-subject features. SVM was again applied to these feature data. After training on a subgroup, all TLE-HA patients were correctly distinguished from controls, achieving an accuracy of 96 ± 2% in both classification schemes. For TLE-N patients, the accuracy was 86 ± 2% based on structural volumes and 91 ± 3% using spectral analysis. Structures discriminating between patients and controls were mainly localized ipsilaterally to the presumed seizure focus. For the TLE-HA group, they were mainly in the temporal lobe; for the TLE-N group they included orbitofrontal regions, as well as the ipsilateral substantia nigra. Correct lateralization of the presumed seizure onset zone was achieved using hippocampi and parahippocampal gyri in all TLE-HA patients using either classification scheme; in the TLE-N patients, lateralization was accurate based on structural volumes in 86 ± 4%, and in 94 ± 4% with the spectral analysis approach. Unilateral TLE has imaging features that can be identified automatically, even when they are invisible to human experts. Such morphometric image features may serve as classification and lateralization criteria. The technique also detects unsuspected distinguishing features like the substantia nigra, warranting further study.     

TRUS image segmentation with non-parametric kernel density estimation shape prior

Due to noises, speckles, etc., automatic prostate segmentation is rather challenging, and using only low-level information such as intensity gradient is insufficient and unable to tackle the problem. In this paper, we propose an automatic prostate segmentation method combining intrinsic properties of TRUS images with the high-level shape prior information. First, intrinsic properties of TRUS images, such as the intensity transition near the prostate boundary as well as the speckle induced texture features obtained by Gabor filter banks, are integrated to deform the model to the target contour. These properties make our method insensitive to high gradient regions introduced by noises and speckles. Then, the preliminary segmentation is fine-tuned by the non-parametric shape prior, which is optimally distilled by non-parametric kernel density estimation as it can approximate arbitrary distributions. The refinement is along the direction of mean shift vector, and considerably strengthens the robustness of the method. The performance of our method is validated by experimental results. Compared with the state of the art, the accuracy and robustness of the method is quite promising, and the mean absolute distance is only 1.21 ± 0.85 mm.     

Evaluation of radiomic texture feature error due to MRI acquisition and reconstruction: A simulation study utilizing ground truth

The purpose of this study was to examine the dependence of image texture features on MR acquisition parameters and reconstruction using a digital MR imaging phantom. MR signal was simulated in a parallel imaging radiofrequency coil setting as well as a single element volume coil setting, with varying levels of acquisition noise, three acceleration factors, and four image reconstruction algorithms. Twenty-six texture features were measured on the simulated images, ground truth images, and clinical brain images. Subtle algorithm-dependent errors were observed on reconstructed phantom images, even in the absence of added noise. Sources of image error include Gibbs ringing at image edge gradients (tissue interfaces) and well-known artifacts due to high acceleration; two of the iterative reconstruction algorithms studied were able to mitigate these image errors. The difference of the texture features from ground truth, and their variance over reconstruction algorithm and parallel imaging acceleration factor, were compared to the clinical “effect size”, i.e., the feature difference between high- and low-grade tumors on T1- and T2-weighted brain MR images of twenty glioma patients. The measured feature error (difference from ground truth) was small for some features, but substantial for others. The feature variance due to reconstruction algorithm and acceleration factor were generally smaller than the clinical effect size. Certain texture features may be preserved by MR imaging, but adequate precautions need to be taken regarding their validity and reliability. We present a general simulation framework for assessing the robustness and accuracy of radiomic textural features under various MR acquisition/reconstruction scenarios.     

Magnetic Resonance Imaging of the Newborn Brain: Automatic Segmentation of Brain Images into 50 Anatomical Regions

We studied methods for the automatic segmentation of neonatal and developing brain images into 50 anatomical regions, utilizing a new set of manually segmented magnetic resonance (MR) images from 5 term-born and 15 preterm infants imaged at term corrected age called ALBERTs. Two methods were compared: individual registrations with label propagation and fusion; and template based registration with propagation of a maximum probability neonatal ALBERT (MPNA). In both cases we evaluated the performance of different neonatal atlases and MPNA, and the approaches were compared with the manual segmentations by means of the Dice overlap coefficient. Dice values, averaged across regions, were 0.81±0.02 using label propagation and fusion for the preterm population, and 0.81±0.02 using the single registration of a MPNA for the term population. Segmentations of 36 further unsegmented target images of developing brains yielded visibly high-quality results. This registration approach allows the rapid construction of automatically labeled age-specific brain atlases for neonates and the developing brain.     

The Potential Value of Preoperative MRI Texture and Shape Analysis in Grading Meningiomas: A Preliminary Investigation

OBJECT: Preoperative knowledge of meningioma grade is essential for planning treatment and surgery. The purpose of this study was to investigate the diagnostic value of MRI texture and shape analysis in grading meningiomas. METHODS: A surgical database was reviewed to identify meningioma patients who had undergone tumor resection between January 2015 and December 2016. Preoperative MR images were retrieved and analyzed. Texture and shape analysis was conducted to quantitatively evaluate tumor heterogeneity and morphology. Three machine learning classifiers were trained with these features to build classification models. The performance of the features and classification models was assessed. RESULTS: A total of 131 patients were included in this study: 21 with high-grade meningiomas and 110 with low-grade meningiomas. Three texture features were selected: Horzl_RLNonUni, S(2,2)SumOfSqs, and WavEnHL_s-3; three shape features were selected: GeoFv, GeoW4, and GeoW5b. The Mann–Whitney test indicated that all six features were significantly different between high-grade and low-grade meningiomas. AUC values were generally greater than 0.50 (range, 0.73 to 0.88). Sensitivities and specificities ranged from 47.62% to 90.48% and 69.09% to 96.36%, respectively. Among the nine classification models obtained, the one built by training the SVM classifier with all six features achieved the best performance, with a sensitivity, specificity, diagnostic accuracy, and AUC of 0.86, 0.87, 0.87, and 0.87, respectively. CONCLUSIONS: Texture and shape analysis, especially when combined with a SVM classifier, can provide satisfactory performance in the preoperative determination of meningioma grade and is thus potentially useful for clinical application.     

The effect of feature selection on multivariate pattern analysis of structural brain MR images

Clinical predictions performed using structural magnetic resonance (MR) images are crucial in neuroimaging studies and can be used as a successful complementary method for clinical decision making. Multivariate pattern analysis (MVPA) is a significant tool that helps correct predictions by exhibiting a compound relationship between disease-related features. In this study, the effectiveness of determining the most relevant features for MVPA of the brain MR images are examined using ReliefF and minimum Redundancy Maximum Relevance (mRMR) algorithms to predict the Alzheimer’s disease (AD), schizophrenia, autism, and attention deficit and hyperactivity disorder (ADHD). Three state-of-the-art MVPA algorithms namely support vector machines (SVM), k-nearest neighbor (kNN) and backpropagation neural network (BP-NN) are employed to analyze the images from five different datasets that include 1390 subjects in total. Feature selection is performed on structural brain features such as volumes and thickness of anatomical structures and selected features are used to compare the effect of feature selection on different MVPA algorithms. Selecting the most relevant features for differentiating images of healthy controls from the diseased subjects using both ReliefF and mRMR methods significantly increased the performance. The most successful MVPA method was SVM for all classification tasks.     

Estimating net primary productivity of semi-arid Crimean pine stands using biogeochemical modelling,remote sensing,and machine learning

The aim of the paper was to predict net primary productivity (NPP) in pure Pinus nigra J.F. Arnold (Crimean pine) stands by consecutively implementing remote sensing, biogeochemical modelling, and machine learning techniques. In this context, NPP was estimated using Carnegie-Ames-Stanford Approach (CASA). Following, NPP was re-modelled with spectral characteristics of the P.nigra using multi-temporal remotely sensed images (Landsat 8 OLI and Sentinel-2), land use, soils and meteorological information in a total of 180 temporary sample plots. The model results were validated using litterfall samples from 30 stations for each forest stand, including needle, branch, cone, bark, male flower, and others. The highest relationship was between NPP and male flowers (r =‐−0.75). In addition, reflectance (R), vegetation indices (VI) and texture (TEX) values (calculated according to filter and degree) for each sample plot were calculated from each sensor. Multiple linear regression (MLR) was applied to define the best subset to model the NPP values with R, VI and TEX values using MLR, support vector machines (SVM) and deep learning (DL) methods. The best prediction accuracy was obtained in TEX data in the SVM method and Sentinel-2 sensor combination. NPP testing determination co-efficiency (R²) values were 0.95. The performance of the male flower litterfall in the validation control was promising for the modelling of NPP in Crimean pine. The TEX properties of the satellite images were well reflected by using different filters, degrees, and functions, resulting in achieving a high success.     

Automatic Supporting System for Regionalization of Ventricular Tachycardia Exit Site in Implantable Defibrillators

Electrograms stored in Implantable Cardioverter Defibrillators (ICD-EGM) have been proven to convey useful information for roughly determining the anatomical location of the Left Ventricular Tachycardia exit site (LVTES). Our aim here was to evaluate the possibilities from a machine learning system intended to provide an estimation of the LVTES anatomical region with the use of ICD-EGM in the situation where 12-lead electrocardiogram of ventricular tachycardia are not available. Several machine learning techniques were specifically designed and benchmarked, both from classification (such as Neural Networks (NN), and Support Vector Machines (SVM)) and regression (Kernel Ridge Regression) problem statements. Classifiers were evaluated by using accuracy rates for LVTES identification in a controlled number of anatomical regions, and the regression approach quality was studied in terms of the spatial resolution. We analyzed the ICD-EGM of 23 patients (18±10 EGM per patient) during left ventricular pacing and simultaneous recording of the spatial coordinates of the pacing electrode with a navigation system. Several feature sets extracted from ICD-EGM (consisting of times and voltages) were shown to convey more discriminative information than the raw waveform. Among classifiers, the SVM performed slightly better than NN. In accordance with previous clinical works, the average spatial resolution for the LVTES was about 3 cm, as in our system, which allows it to support the faster determination of the LVTES in ablation procedures. The proposed approach also provides with a framework suitable for driving the design of improved performance future systems.     

Impact of quantization algorithm and number of gray level intensities on variability and repeatability of low field strength magnetic resonance image-based radiomics texture features

PurposeThe purpose of this work was to investigate the impact of quantization preprocessing parameter selection on variability and repeatability of texture features derived from low field strength magnetic resonance (MR) images.MethodsTexture features were extracted from low field strength images of a daily image QA phantom with four texture inserts. Feature variability over time was quantified using all combinations of three quantization algorithms and four different numbers of gray level intensities. In addition, texture features were extracted using the same combinations from the low field strength MR images of the gross tumor volume (GTV) and left kidney of patients with repeated set up scans. The impact of region of interest (ROI) preprocessing on repeatability was investigated with a test-retest study design.ResultsThe phantom ROIs quantized to 64 Gy level intensities using the histogram equalization method resulted in the greatest number of features with the least variability. There was no clear method that resulted in the highest repeatability in the GTV or left kidney. However, eight texture features extracted from the GTV were repeatable regardless of ROI processing combination.ConclusionLow field strength MR images can provide a stable basis for texture analysis with ROIs quantized to 64 Gy levels using histogram equalization, but there is no clear optimal combination for repeatability.     

A noncontact,nondestructive method for quantifying intratissue deformations and strains

The function of soft connective tissues is frequently characterized by quantifying tissue strain (e.g., during joint motion). Conventional techniques for quantifying tendon and ligament strain typically provide surface measures, using markers, stain lines or instrumentation that may influence the tissue. An alternative approach is to quantify intratendinous strain by applying texture correlation analysis to magnetic resonance (MR) images. This paper reports the accuracy and reproducibility of this approach by (1) assessing the reproducibility of MR images, (2) assessing texture correlation accuracy using simulated displacements, and (3) comparing texture correlation measures of displacement and strain from MR images to conventional techniques.     

Development of a dynamic imaging method for gravitropism in pea sprouts using clinical magnetic resonance imaging system

Although magnetic resonance imaging (MRI) is a useful technique, only a few studies have investigated the dynamic behavior of small subjects using MRI owing to constraints such as experimental space and signal amount. In this study, to acquire high-resolution continuous three-dimensional gravitropism data of pea (Pisum sativum) sprouts, we developed a small-bore MRI signal receiver coil that can be used in a clinical MRI and adjusted the imaging sequence. It was expected that such an arrangement would improve signal sensitivity and improve the signal-to-noise ratio (SNR) of the acquired image. All MRI experiments were performed using a 3.0-T clinical MRI scanner. An SNR comparison using an agarose gel phantom to confirm the improved performance of the small-bore receiver coil and an imaging experiment of pea sprouts exhibiting gravitropism were performed. The SNRs of the images acquired with a standard 32-channel head coil and the new small-bore receiver coil were 5.23±0.90 and 57.75±12.53, respectively. The SNR of the images recorded using the new coil was approximately 11-fold higher than that of the standard coil. In addition, when the accuracy of MR imaging that captures the movement of pea sprout was verified, the difference in position information from the optical image was found to be small and could be used for measurements. These results of this study enable the application of a clinical MRI system for dynamic plant MRI. We believe that this study is a significant first step in the development of plant MRI technique.     

Experimental Differentiation of Intraocular Masses Using Ultrahigh-Field Magnetic Resonance Imaging – A Case Series

Purpose

The case reports presented here were compiled to demonstrate the potential for improved diagnosis and monitoring of disease progress of intraocular lesions using ultrahigh-field magnetic resonance microscopy (MRM) at 7.1 Tesla.

Methods

High-resolution ex vivo ocular magnetic resonance (MR) images were acquired on an ultrahigh-field MR system (7.1 Tesla, ClinScan, Bruker BioScan, Germany) using a 2-channel coil with 4 coil elements and T2-weighted turbo spin echo (TSE) sequences of human eyes enucleated because of different intraocular lesions. Imaging parameters were: 40×40 mm field of view, 512×512 matrix, and 700 µm slice thickness. The results were correlated with in vivo ultrasound and histology of the enucleated eyes.

Results

Imaging was performed in enucleated eyes with choroidal melanoma, malignant melanoma of iris and ciliary body with scleral perforation, ciliary body melanoma, intraocular metastasis of esophageal cancer, subretinal bleeding in the presence of perforated corneal ulcer, hemorrhagic choroidal detachment, and premature retinopathy with phthisis and ossification of bulbar structures. MR imaging allowed differentiation between solid and cystic tumor components. In case of hemorrhage, fluid-fluid levels were identified. Melanin and calcifications caused significant hypointensity. Microstructural features of eye lesions identified by MRM were confirmed by histology.

Conclusion

This study demonstrates the potential of MRM for the visualization and differential diagnosis of intraocular lesions. At present, the narrow bore of the magnet still limits the use of this technology in humans in vivo. Further advances in ultrahigh-field MR imaging will permit visualization of tumor extent and evaluation of nonclassified intraocular structures in the near future.     

Combined Metaheuristic Algorithm and Radiomics Strategy for the Analysis of Neuroanatomical Structures in Schizophrenia and Schizoaffective Disorders

ObjectivesSchizophrenia (SZ) is the most chronic disabling psychotic brain disorder. It is characterized by delusions and auditory hallucinations, as well as impairments in memory. Schizoaffective (SA) signs are co-morbid with SZ and are characterized by symptoms of SZ and mood disorder. Various researches suggest that SZ and SA share a number of equally severe cognitive deficits, but the pathophysiology has not yet been addressed in a comprehensive way. In this work, the heterogeneity in whole brain, ventricle and cerebellum region from psychotic MR brain images is examined using Machine learning and radiomic features.Materials and methodsT1 weighted MR brain images are obtained from Schizconnect database for the analysis. The shape prior level set method is used to segment the ventricle and cerebellum structures. The radiomic features which include shape and texture are extracted from these regions to discriminate the SZ and SA subjects. The performance of these features is evaluated with Binary Particle Swarm Optimization (BPSO) based Fuzzy Support Vector Machine (FSVM) classifier.ResultsThe shape constrained Level Set method is able to better segment ventricles and cerebellum regions from the images. The significant features that are extracted from whole brain, ventricle and cerebellum are identified by the BPSO based FSVM. The combination of radiomic features extracted from cerebellum region achieved high classification accuracy (90.09%) using metaheuristic algorithm. The extracted features from cerebellum are correlated with PANSS score. The causal analysis shows that there is an association been the tissue texture variation in identifying the disease severity. The symmetry analysis shows that left brain mean area is larger than the right side area. In particular SA has low cerebellum area compared to SZ. The radiomic features such as Hermite, Laws and tensor extracted from the left cerebellum show a significant texture variation in all the considered subjects (p<0.0001).ConclusionsThe results are clinically relevant in discriminating the pattern change in the structure, hence this biomarker and frame work could be used for the severity study of psychotic disorders.     

Evaluation of combining bony anatomy and soft tissue position correction strategies for IMRT prostate cancer patients

Background

Radiotherapy treatment requires delivering high homogenous dose to target volume while sparing organs at risk. That is why accurate patient positioning is one of the most important steps during the treatment process. It reduces set-up errors which have a strong influence on the doses given to the target and surrounding tissues.

Aim

The aim of this study was to investigate the efficiency of combining bony anatomy and soft tissue imaging position correction strategies for patients with prostate cancer.

Materials and methods

The study based on pre-treatment position verification results determined for 10 patients using kV images and CBCT match. At the same patients’ position, two orthogonal kV images and set of CT scans were acquired. Both verification methods gave the information about patients’ position changes in vertical, longitudinal and lateral directions.

Results

For 93 verifications, the mean values of kV shifts in vertical, longitudinal and lateral directions equaled: −0.11 ± 0.54 cm, 0.26 ± 0.38 cm and −0.06 ± 0.47 cm, respectively. The same values achieved for CBCT matching equaled: 0.07 ± 0.62 cm, 0.22 ± 0.36 cm and −0.02 ± 0.45 cm. Statistically significant changes between the values of shifts received during the first week of treatment and the rest time of the irradiation process were found for 2 patients in the lateral direction and 2 patients in vertical direction among kV results and for 3 patients in the longitudinal direction among CBCT results. A significant difference between kV and CBCT match results was found in the vertical direction.

Conclusions

In clinical practice, CBCT combined with kV or even portal imaging improves precision and effectiveness of prostate cancer treatment accuracy.     

Heterogeneous ensemble approach with discriminative features and modified-SMOTEbagging for pre-miRNA classification

An ensemble classifier approach for microRNA precursor (pre-miRNA) classification was proposed based upon combining a set of heterogeneous algorithms including support vector machine (SVM), k-nearest neighbors (kNN) and random forest (RF), then aggregating their prediction through a voting system. Additionally, the proposed algorithm, the classification performance was also improved using discriminative features, self-containment and its derivatives, which have shown unique structural robustness characteristics of pre-miRNAs. These are applicable across different species. By applying preprocessing methods—both a correlation-based feature selection (CFS) with genetic algorithm (GA) search method and a modified-Synthetic Minority Oversampling Technique (SMOTE) bagging rebalancing method—improvement in the performance of this ensemble was observed. The overall prediction accuracies obtained via 10 runs of 5-fold cross validation (CV) was 96.54%, with sensitivity of 94.8% and specificity of 98.3%—this is better in trade-off sensitivity and specificity values than those of other state-of-the-art methods. The ensemble model was applied to animal, plant and virus pre-miRNA and achieved high accuracy, >93%. Exploiting the discriminative set of selected features also suggests that pre-miRNAs possess high intrinsic structural robustness as compared with other stem loops. Our heterogeneous ensemble method gave a relatively more reliable prediction than those using single classifiers. Our program is available at http://ncrna-pred.com/premiRNA.html.     

Epithelium segmentation and automated Gleason grading of prostate cancer via deep learning in label‐free multiphoton microscopic images

In the current clinical care practice, Gleason grading system is one of the most powerful prognostic predictors for prostate cancer (PCa). The grading system is based on the architectural pattern of cancerous epithelium in histological images. However, the standard procedure of histological examination often involves complicated tissue fixation and staining, which are time‐consuming and may delay the diagnosis and surgery. In this study, label‐free multiphoton microscopy (MPM) was used to acquire subcellular‐resolution images of unstained prostate tissues. Then, a deep learning architecture (U‐net) was introduced for epithelium segmentation of prostate tissues in MPM images. The obtained segmentation results were then merged with the original MPM images to train a classification network (AlexNet) for automated Gleason grading. The developed method achieved an overall pixel accuracy of 92.3% with a mean F1 score of 0.839 for epithelium segmentation. By merging the segmentation results with the MPM images, the accuracy of Gleason grading was improved from 72.42% to 81.13% in hold‐out test set. Our results suggest that MPM in combination with deep learning holds the potential to be used as a fast and powerful clinical tool for PCa diagnosis.     

Ensemble Modeling for Robustness Analysis in engineering non-native metabolic pathways

Metabolic pathways in cells must be sufficiently robust to tolerate fluctuations in expression levels and changes in environmental conditions. Perturbations in expression levels may lead to system failure due to the disappearance of a stable steady state. Increasing evidence has suggested that biological networks have evolved such that they are intrinsically robust in their network structure. In this article, we presented Ensemble Modeling for Robustness Analysis (EMRA), which combines a continuation method with the Ensemble Modeling approach, for investigating the robustness issue of non-native pathways. EMRA investigates a large ensemble of reference models with different parameters, and determines the effects of parameter drifting until a bifurcation point, beyond which a stable steady state disappears and system failure occurs. A pathway is considered to have high bifurcational robustness if the probability of system failure is low in the ensemble. To demonstrate the utility of EMRA, we investigate the bifurcational robustness of two synthetic central metabolic pathways that achieve carbon conservation: non-oxidative glycolysis and reverse glyoxylate cycle. With EMRA, we determined the probability of system failure of each design and demonstrated that alternative designs of these pathways indeed display varying degrees of bifurcational robustness. Furthermore, we demonstrated that target selection for flux improvement should consider the trade-offs between robustness and performance.     

基于多光谱影像的森林树种识别及其空间尺度响应

当前,不同空间分辨率卫星影像对森林类型识别结果中普遍存在的尺度效应,而且纹理参量对不同尺度下树种识别精度的影响仍缺乏广泛认知.本研究以中国东北旺业甸林场为研究区,采用观测时相同步、地理坐标匹配的GF-1 PMS、GF-2 PMS、GF-1 WFV,以及Landsat-8 OLI卫星传感器数据组成空间尺度观测序列(1、2、4、8、16、30 m),并结合支持向量机(SVM)模型,探讨了区域内5种优势树种遥感识别结果的尺度变化规律及其纹理特征参数的影响,同时检验了基于尺度上推转换影像的树种识别结果差异.结果表明: 影像空间分辨率对区域树种识别结果具有显著影响,其中,研究区森林树种识别的最佳影像分辨率为4 m,当分辨率降低至30 m时,树种识别结果最差.在1～8 m影像分辨率范围内,增加纹理信息能够显著提高不同优势树种的识别精度,使总分类精度提升了2.0%～3.6%,但纹理信息对16～30 m影像的识别结果没有显著影响.与真实尺度卫星影像相比,基于升尺度转换影像的树种识别结果及其尺度响应特征存在显著差异,表明在面向多个空间尺度的遥感观测和应用研究中,需要采用真实分辨率影像以确保结果的准确性.     

Prediction of nicotinamide adenine dinucleotide interacting sites based on ensemble support vector machine

Nicotinamide adenine dinucleotide (NAD) plays an important role in cellular metabolism and acts as hydrideaccepting and hydride-donating coenzymes in energy production. Identification of NAD protein interacting sites can significantly aid in understanding the NAD dependent metabolism and pathways, and it could further contribute useful information for drug development. In this study, a computational method is proposed to predict NAD-protein interacting sites using the sequence information and structure-based information. All models developed in this work are evaluated using the 7-fold cross validation technique. Results show that using the position specific scoring matrix (PSSM) as an input feature is quite encouraging for predicting NAD interacting sites. After considering the unbalance dataset, the ensemble support vector machine (SVM), which is an assembly of many individual SVM classifiers, is developed to predict the NAD interacting sites. It was observed that the overall accuracy (Acc) thus obtained was 87.31% with Matthew's correlation coefficient (MCC) equal to 0.56. In contrast, the corresponding rate by the single SVM approach was only 80.86% with MCC of 0.38. These results indicated that the prediction accuracy could be remarkably improved via the ensemble SVM classifier approach.