Minimum Redundancy Maximum Relevance Method Research Articles

Magnetic resonance imaging (MRI)-based intratumoral and peritumoral radiomics for prognosis prediction in glioma patients

The purpose of this study was to identify robust radiological features from intratumoral and peritumoral regions, evaluate MRI protocols, and machine learning methods for overall survival stratification of glioma patients, and explore the relationship between radiological features and the tumour microenvironment. A retrospective analysis was conducted on 163 glioma patients, divided into a training set (n=113) and a testing set (n=50). For each patient, 2135 features were extracted from clinical MRI. Feature selection was performed using the Minimum Redundancy Maximum Relevance method and the Random Forest (RF) algorithm. Prognostic factors were assessed using the Cox proportional hazards model. Four machine learning models (RF, Logistic Regression, Support Vector Machine, and XGBoost) were trained on clinical and radiological features from tumour and peritumoral regions. Model evaluations on the testing set used receiver operating characteristic curves. Among the 163 patients, 96 had an overall survival (OS) of less than three years postsurgery, while 67 had an OS of more than three years. Univariate Cox regression in the validation set indicated that age (p=0.003) and tumour grade (p<0.001) were positively associated with the risk of death within three years postsurgery. The final predictive model incorporated 13 radiological and 7 clinical features. The RF model, combining intratumor and peritumor radiomics, achieved the best predictive performance (AUC=0.91; ACC=0.86), outperforming single-region models. Combined intratumoral and peritumoral radiomics can improve survival prediction and have potential as a practical imaging biomarker to guide clinical decision-making.

Interpretable multiphasic CT-based radiomic analysis for preoperatively differentiating benign and malignant solid renal tumors: a multicenter study

BackgroundTo develop and compare machine learning models based on triphasic contrast-enhanced CT (CECT) for distinguishing between benign and malignant renal tumors.Materials and MethodsIn total, 427 patients were enrolled from two medical centers: Center 1 (serving as the training set) and Center 2 (serving as the external validation set). First, 1781 radiomic features were individually extracted from corticomedullary phase (CP), nephrographic phase (NP), and excretory phase (EP) CECT images, after which 10 features were selected by the minimum redundancy maximum relevance method. Second, random forest (RF) models were constructed from single-phase features (CP, NP, and EP) as well as from the combination of features from all three phases (TP). Third, the RF models were assessed in the training and external validation sets. Finally, the internal prediction mechanisms of the models were explained by the SHapley Additive exPlanations (SHAP) approach.ResultsA total of 266 patients with renal tumors from Center 1 and 161 patients from Center 2 were included. In the training set, the AUCs of the RF models constructed from the CP, NP, EP, and TP features were 0.886, 0.912, 0.930, and 0.944, respectively. In the external validation set, the models achieved AUCs of 0.860, 0.821, 0.921, and 0.908, respectively. The “original_shape_Flatness” feature played the most important role in the prediction outcome for the RF model based on EP features according to the SHAP method.ConclusionsThe four RF models efficiently differentiated benign from malignant solid renal tumors, with the EP feature-based RF model displaying the best performance.Graphical

Union is strength: the combination of radiomics features and 3D-deep learning in a sole model increases diagnostic accuracy in demented patients: a whole brain 18FDG PET-CT analysis.

FDG PET imaging plays a crucial role in the evaluation of demented patients by assessing regional cerebral glucose metabolism. In recent years, both radiomics and deep learning techniques have emerged as powerful tools for extracting valuable information from medical images. This article aims to provide a comparative analysis of radiomics features, 3D-deep learning convolutional neural network (CNN) and the fusion of them, in the evaluation of 18F-FDG PET whole brain images in patients with dementia and normal controls. 18F-FDG brain PET and clinical score were collected in 85 patients with dementia and 125 healthy controls (HC). Patients were assigned to various form of dementia on the basis of clinical evaluation, follow-up and voxels comparison with HC using a two-sample Student's t -test, to determine the regions of brain involved. Radiomics analysis was performed on the whole brain after normalization to an optimized template. After selection using the minimum redundancy maximum relevance method and Pearson's correlation coefficients, the features obtained were added to a neural network model to find the accuracy in classifying HC and demented patients. Forty subjects not included in the training were used to test the models. The results of the three models (radiomics, 3D-CNN, combined model) were compared with each other. Four radiomics features were selected. The sensitivity was 100% for the three models, but the specificity was higher with radiomics and combined one (100% vs. 85%). Moreover, the classification scores were significantly higher using the combined model in both normal and demented subjects. The combination of radiomics features and 3D-CNN in a single model, applied to the whole brain 18FDG PET study, increases the accuracy in demented patients.

Computed tomography-based radiomics diagnostic approach for differential diagnosis between early- and late-stage pancreatic ductal adenocarcinoma.

One of the primary reasons for the dismal survival rates in pancreatic ductal adenocarcinoma (PDAC) is that most patients are usually diagnosed at late stages. There is an urgent unmet clinical need to identify and develop diagnostic methods that could precisely detect PDAC at its earliest stages. To evaluate the potential value of radiomics analysis in the differentiation of early-stage PDAC from late-stage PDAC. A total of 71 patients with pathologically proved PDAC based on surgical resection who underwent contrast-enhanced computed tomography (CT) within 30 d prior to surgery were included in the study. Tumor staging was performed in accordance with the 8th edition of the American Joint Committee on Cancer staging system. Radiomics features were extracted from the region of interest (ROI) for each patient using Analysis Kit software. The most important and predictive radiomics features were selected using Mann-Whitney U test, univariate logistic regression analysis, and minimum redundancy maximum relevance (MRMR) method. Random forest (RF) method was used to construct the radiomics model, and 10-times leave group out cross-validation (LGOCV) method was used to validate the robustness and reproducibility of the model. A total of 792 radiomics features (396 from late arterial phase and 396 from portal venous phase) were extracted from the ROI for each patient using Analysis Kit software. Nine most important and predictive features were selected using Mann-Whitney U test, univariate logistic regression analysis, and MRMR method. RF method was used to construct the radiomics model with the nine most predictive radiomics features, which showed a high discriminative ability with 97.7% accuracy, 97.6% sensitivity, 97.8% specificity, 98.4% positive predictive value, and 96.8% negative predictive value. The radiomics model was proved to be robust and reproducible using 10-times LGOCV method with an average area under the curve of 0.75 by the average performance of the 10 newly built models. The radiomics model based on CT could serve as a promising non-invasive method in differential diagnosis between early and late stage PDAC.

Greater accuracy of radiomics compared to deep learning to discriminate normal subjects from patients with dementia: a whole brain 18FDG PET analysis.

18F-FDG brain PET and clinical score were collected in 85 patients with dementia and 125 healthy controls (HC). Patients were assigned to various form of dementia on the basis of clinical evaluation, follow-up and voxels comparison with HC using a two-sample Student's t -test, to determine the regions of brain involved. Radiomic analysis was performed on the whole brain after normalization to an optimized template. After feature selection using the minimum redundancy maximum relevance method and Pearson's correlation coefficients, a Neural Network model was tested to find the accuracy to classify HC and demented patients. Twenty subjects not included in the training were used to test the models. The results were compared with those obtained by conventional CNN model. Four radiomic features were selected. The validation and test accuracies were 100% for both models, but the probability scores were higher with radiomics, in particular for HC group ( P = 0.0004). Radiomic features extracted from standardized PET whole brain images seem to be more accurate than CNN to distinguish patients with and without dementia.

Multilevel Pain Assessment with Functional Near-Infrared Spectroscopy: Evaluating ΔHBO2 and ΔHHB Measures for Comprehensive Analysis.

Assessing pain in non-verbal patients is challenging, often depending on clinical judgment which can be unreliable due to fluctuations in vital signs caused by underlying medical conditions. To date, there is a notable absence of objective diagnostic tests to aid healthcare practitioners in pain assessment, especially affecting critically-ill or advanced dementia patients. Neurophysiological information, i.e., functional near-infrared spectroscopy (fNIRS) or electroencephalogram (EEG), unveils the brain's active regions and patterns, revealing the neural mechanisms behind the experience and processing of pain. This study focuses on assessing pain via the analysis of fNIRS signals combined with machine learning, utilising multiple fNIRS measures including oxygenated haemoglobin (ΔHBO2) and deoxygenated haemoglobin (ΔHHB). Initially, a channel selection process filters out highly contaminated channels with high-frequency and high-amplitude artifacts from the 24-channel fNIRS data. The remaining channels are then preprocessed by applying a low-pass filter and common average referencing to remove cardio-respiratory artifacts and common gain noise, respectively. Subsequently, the preprocessed channels are averaged to create a single time series vector for both ΔHBO2 and ΔHHB measures. From each measure, ten statistical features are extracted and fusion occurs at the feature level, resulting in a fused feature vector. The most relevant features, selected using the Minimum Redundancy Maximum Relevance method, are passed to a Support Vector Machines classifier. Using leave-one-subject-out cross validation, the system achieved an accuracy of 68.51%±9.02% in a multi-class task (No Pain, Low Pain, and High Pain) using a fusion of ΔHBO2 and ΔHHB. These two measures collectively demonstrated superior performance compared to when they were used independently. This study contributes to the pursuit of an objective pain assessment and proposes a potential biomarker for human pain using fNIRS.

Efficient prediction of SOC and aggregate OC components by continuous wavelet transform spectra under different feature selection methods

Soil Organic Carbon (SOC) fixation plays a vital role in reducing greenhouse gas emissions and the formation of soil aggregates is recognized as a crucial process in SOC fixation. In the current study, we characterized spectral information on SOC and aggregate Organic carbon (OC) components by using a rapid and robust method. Soil samples were collected from different layers to obtain the SOC and aggregate OC components to record corresponding spectra. The Continuous Wavelet Transform (CWT) spectra were then combined with various characteristic wavelength selection methods to build Multivariate Linear Regression (MLR), BP neural network (BP), and Random Forest (RF) models. Finally, the optimal combination of characteristic wavelengths based on the best-performing model for each index was determined. The results demonstrated that the model's accuracy, which was built using the set of characteristic wavelengths of the best model for all metrics, was higher than that of the best model for a single metric. This was due to the correlation between SOC and aggregate OC components. The best set of characteristic wavelengths were those selected by the Sequential Backward Selection method with wavelet decomposition scales of 23, 26, and 27, and those selected by the Minimum Redundancy Maximum Relevance method with wavelet decomposition scale 27. The RF model for Free silt and clay particles organic carbon (FSP-OC) showed the highest accuracy among the four SOC prediction models. In addition, it was discovered that as the wavelet decomposition scales become more similar, the extracted characteristic wavelengths also become more similar, resulting in similar model predictions. In summary, the accuracy of the predictive model for SOC and its constituents can be demonstrably improved by reasonable combination of characteristic wavelengths selection method and wavelet decomposition scale.

Intratumoral and Peritumoral Radiomics Based on Preoperative MRI for Evaluation of Programmed Cell Death Ligand-1 Expression in Breast Cancer.

Programmed cell death ligand-1 (PD-L1) is a promising target for immune checkpoint blockade therapy in breast cancer. However, the preoperative evaluation of PD-L1 expression in breast cancer is rarely explored. To determine the ability of radiomics signatures based on preoperative dynamic contrast-enhanced (DCE) MRI to evaluate PD-L1 expression in breast cancer. Retrospective. 196 primary breast cancer patients with preoperative MRI and postoperative pathological evaluation of PD-L1 expression, divided into training (n = 137, 28 PD-L1-positive) and test cohorts (n = 59, 12 PD-L1-positive). 3.0T; volume imaging for breast assessment DCE sequence. Radiomics features were extracted from the first phase of DCE-MRI by using the minimum redundancy maximum relevance method and least absolute shrinkage and selection operator algorithm. Three radiomics signatures were constructed based on the intratumoral, peritumoral, and combined intra- and peritumoral regions. The performance of the signatures was assessed using area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, and accuracy. Univariable and multivariable logistic regression analysis, t-tests, chi-square tests, Fisher exact test or Yates correction, ROC analysis, and one-way analysis of variance. P < 0.05 was considered significant. In the test cohort, the combined radiomics signature (AUC, 0.853) exhibited superior performance compared to the intratumoral (AUC, 0.816; P = 0.528) and peritumoral radiomics signatures (AUC, 0.846; P = 0.905) in PD-L1 status evaluation, although the differences did not reach statistical significance. Intratumoral and peritumoral radiomics signatures based on preoperative breast MRI showed some potential accuracy for the non-invasive evaluation of PD-L1 status in breast cancer. 4 TECHNICAL EFFICACY: Stage 2.

Multi-phase-combined CECT radiomics models for Fuhrman grade prediction of clear cell renal cell carcinoma.

This study aimed to evaluate the effectiveness of multi-phase-combined contrast-enhanced CT (CECT) radiomics methods for noninvasive Fuhrman grade prediction of clear cell renal cell carcinoma (ccRCC). A total of 187 patients with four-phase CECT images were retrospectively enrolled and then were categorized into training cohort (n=126) and testing cohort (n=61). All patients were confirmed as ccRCC by histopathological reports. A total of 110 3D classical radiomics features were extracted from each phase of CECT for individual ccRCC lesion, and contrast-enhanced variation features were also calculated as derived radiomics features. These features were concatenated together, and redundant features were removed by Pearson correlation analysis. The discriminative features were selected by minimum redundancy maximum relevance method (mRMR) and then input into a C-support vector classifier to build multi-phase-combined CECT radiomics models. The prediction performance was evaluated by the area under the curve (AUC) of receiver operating characteristic (ROC). The multi-phase-combined CECT radiomics model showed the best prediction performance (AUC=0.777) than the single-phase CECT radiomics model (AUC=0.711) in the testing cohort (p value=0.039). The multi-phase-combined CECT radiomics model is a potential effective way to noninvasively predict Fuhrman grade of ccRCC. The concatenation of first-order features and texture features extracted from corticomedullary phase and nephrographic phase are discriminative feature representations.

Preoperative contrast-enhanced CT-based radiomics signature for predicting hypoxia-inducible factor 1α expression in retroperitoneal sarcoma

To develop and test a contrast-enhanced computed tomography (CECT)-based radiomics signature (RS) to preoperatively predict hypoxia-inducible factor 1α (HIF-1α) expression in retroperitoneal sarcoma (RPS). This study included 129 patients with RPS retrospectively who underwent CECT, including 64 male and 65 female patients (55 [2-84] years). Participants were divided into a training set comprising 85 patients and a test set comprising 44 patients. Clinical data and CECT findings of all patients were collected. RS construction was performed by the minimum redundancy maximum relevance method and least absolute shrinkage and selection operator algorithm. The clinical information was analysed by univariate and multivariate logistic regression analysis. The RS and risk factors were included to build a radiomics nomogram. The predictive efficacy of different models was evaluated by accuracy, area under the receiver operating characteristic curve (AUC), and decision curve analysis. The RS combined signature was constructed on the basis of multi-phase CECT and had an accuracy of 0.795 and an AUC of 0.719 (95% confidence interval [CI], 0.552-0.886) in the test set, which were higher than that of the radiomics nomogram (accuracy: 0.636; AUC: 0.702 [95% CI, 0.547-0.857]) and the clinical model (accuracy: 0.682; AUC: 0.486 [95% CI, 0.324-0.647]). The decision curve analysis showed that the RS combined signature provided better clinical application than the clinical model and radiomics nomogram. The multi-phase CECT-based RS constructed can be used as a powerful tool for predicting HIF-1α expression in patients with RPS.

Lumbar MR-based radiomics nomogram for detecting minimal residual disease in patients with multiple myeloma.

Minimal residual disease (MRD) is a standard for assessing treatment response in multiple myeloma (MM). MRD negativity is considered to be the most powerful predictor of long-term good outcomes. This study aimed to develop and validate a radiomics nomogram based on magnetic resonance imaging (MRI) of the lumbarspine to detect MRD after MM treatment. A total of 130 MM patients (55 MRD negative and 75 MRD positive) who had undergone MRD testing through next-generation flow cytometry were divided into a training set (n = 90) and a test set (n = 40). Radiomics features were extracted from lumbar spinal MRI (T1-weighted images and fat-suppressed T2-weighted images) by means of the minimum redundancy maximum relevance method and the least absolute shrinkage and selection operator algorithm. A radiomics signature model was constructed. A clinical model was established using demographic features. A radiomics nomogram incorporating the radiomics signature and independent clinical factor was developed using multivariate logistic regression analysis. Sixteen features were used to establish the radiomics signature. The radiomics nomogram included the radiomics signature and the independent clinical factor (free light chain ratio) and showed good performance in detecting the MRD status (area under the curve: 0.980 in the training set and 0.903 in the test set). The lumbar MRI-based radiomics nomogram showed good performance in detecting MRD status in MM patients after treatment, and it is helpful for clinical decision-making. • The presence or absence of minimal residual disease status has a strong predictive significance for the prognosis of patients with multiple myeloma. • A radiomics nomogram based on lumbar MRI is a potential and reliable tool for evaluating minimal residual disease status in MM.

Identifying Functions of Proteins in Mice With Functional Embedding Features.

In current biology, exploring the biological functions of proteins is important. Given the large number of proteins in some organisms, exploring their functions one by one through traditional experiments is impossible. Therefore, developing quick and reliable methods for identifying protein functions is necessary. Considerable accumulation of protein knowledge and recent developments on computer science provide an alternative way to complete this task, that is, designing computational methods. Several efforts have been made in this field. Most previous methods have adopted the protein sequence features or directly used the linkage from a protein–protein interaction (PPI) network. In this study, we proposed some novel multi-label classifiers, which adopted new embedding features to represent proteins. These features were derived from functional domains and a PPI network via word embedding and network embedding, respectively. The minimum redundancy maximum relevance method was used to assess the features, generating a feature list. Incremental feature selection, incorporating RAndom k-labELsets to construct multi-label classifiers, used such list to construct two optimum classifiers, corresponding to two key measurements: accuracy and exact match. These two classifiers had good performance, and they were superior to classifiers that used features extracted by traditional methods.

Detecting Blood Methylation Signatures in Response to Childhood Cancer Radiotherapy via Machine Learning Methods.

Simple SummaryRadiotherapy for cancer patients can cause abnormal DNA methylation. We developed a computational workflow that can identify crucial methylation alterations related to treatment exposure in childhood cancer survivors.Radiotherapy is a helpful treatment for cancer, but it can also potentially cause changes in many molecules, resulting in adverse effects. Among these changes, the occurrence of abnormal DNA methylation patterns has alarmed scientists. To explore the influence of region-specific radiotherapy on blood DNA methylation, we designed a computational workflow by using machine learning methods that can identify crucial methylation alterations related to treatment exposure. Irrelevant methylation features from the DNA methylation profiles of 2052 childhood cancer survivors were excluded via the Boruta method, and the remaining features were ranked using the minimum redundancy maximum relevance method to generate feature lists. These feature lists were then fed into the incremental feature selection method, which uses a combination of deep forest, k-nearest neighbor, random forest, and decision tree to find the most important methylation signatures and build the best classifiers and classification rules. Several methylation signatures and rules have been discovered and confirmed, allowing for a better understanding of methylation patterns in response to different treatment exposures.

Radiomic Features on Multiparametric MRI for Preoperative Evaluation of Pituitary Macroadenomas Consistency: Preliminary Findings.

Preoperative assessment of the consistency of pituitary macroadenomas (PMA) might be needed for surgical planning. To investigate the diagnostic performance of radiomics models based on multiparametric magnetic resonance imaging (mpMRI) for preoperatively evaluating the tumor consistency of PMA. Retrospective. One hundred and fifty-six PMA patients (soft consistency, N=104 vs. hard consistency, N=52), divided into training (N=108) and test (N=48) cohorts. The tumor consistency was determined on surgical findings. T1-weighted imaging (T1WI), contrast-enhanced T1WI (T1CE), and T2-weighted imaging (T2WI) using spin-echo sequences with a 3.0-T scanner. An automated three-dimensional (3D) segmentation was performed to generate the volume of interest (VOI) on T2WI, then T1WI/T1CE were coregistered to T2WI. A total of 388 radiomic features were extracted on each VOI of mpMRI. The top-discriminative features were identified using the minimum-redundancy maximum-relevance method and 0.632+ bootstrapping. The radiomics models based on each sequence and their combinations were established via the random forest (RF) and support vector machine (SVM), and independently evaluated for their ability in distinguishing PMA consistency. Mann-Whitney U-test and Chi-square test were used for comparison analysis. The area under the receiver operating characteristic curve (AUC), accuracy (ACC), sensitivity (SEN), specificity (SPE), and relative standard deviation (RSD) were calculated to evaluate each model's performance. ACC with P-value<0.05 was considered statistically significant. Eleven mpMRI-based features exhibited statistically significant differences between soft and hard PMA in the training cohort. The radiomics model built on combined T1WI/T1CE/T2WI demonstrated the best performance among all the radiomics models with an AUC of 0.90 (95% confidence interval [CI]: 0.87-0.92), ACC of 0.87 (CI: 0.84-0.89), SEN of 0.83 (CI: 0.81-0.85), and SPE of 0.87 (CI: 0.85-0.99) in the test cohort. Radiomic features based on mpMRI have good performance in the presurgical evaluation of PMA consistency. 3 TECHNICAL EFFICACY: Stage 2.

A Radiomic Nomogram for the Ultrasound-Based Evaluation of Extrathyroidal Extension in Papillary Thyroid Carcinoma.

PurposeTo construct a sequence diagram based on radiological and clinical factors for the evaluation of extrathyroidal extension (ETE) in patients with papillary thyroid carcinoma (PTC).Materials and MethodsBetween January 2016 and January 2020, 161 patients with PTC who underwent preoperative ultrasound examination in the Affiliated People’s Hospital of Jiangsu University were enrolled in this retrospective study. According to the pathology results, the enrolled patients were divided into a non-ETE group and an ETE group. All patients were randomly divided into a training cohort (n = 97) and a validation cohort (n = 64). A total of 479 image features of lesion areas in ultrasonic images were extracted. The radiomic signature was developed using least absolute shrinkage and selection operator algorithms after feature selection using the minimum redundancy maximum relevance method. The radiomic nomogram model was established by multivariable logistic regression analysis based on the radiomic signature and clinical risk factors. The discrimination, calibration, and clinical usefulness of the nomogram model were evaluated in the training and validation cohorts.ResultsThe radiomic signature consisted of six radiomic features determined in ultrasound images. The radiomic nomogram included the parameters tumor location, radiological ETE diagnosis, and the radiomic signature. Area under the curve (AUC) values confirmed good discrimination of this nomogram in the training cohort [AUC, 0.837; 95% confidence interval (CI), 0.756–0.919] and the validation cohort (AUC, 0.824; 95% CI, 0.723–0.925). The decision curve analysis showed that the radiomic nomogram has good clinical application value.ConclusionThe newly developed radiomic nomogram model is a noninvasive and reliable tool with high accuracy to predict ETE in patients with PTC.

Deep transfer learning approaches for bleeding detection in endoscopy images.

Wireless capsule endoscopy is a non-invasive, wireless imaging tool that has developed rapidly over the last several years. One of the main limiting factors using this technology is that it produces a huge number of images, whose analysis, to be done by a doctor, is an extremely time-consuming process. In this research area, the management of this problem has been addressed with the development of Computer-aided Diagnosis systems thanks to which the automatic inspection and analysis of images acquired by the capsule has clearly improved. Recently, a big advance in classification of endoscopic images is achieved with the emergence of deep learning methods. The proposed expert system employs three pre-trained deep convolutional neural networks for feature extraction. In order to construct efficient feature sets, the features from VGG19, InceptionV3 and ResNet50 models are then selected and fused using the minimum Redundancy Maximum Relevance method and different fusion rules. Finally, supervised machine learning algorithms are employed to classify the images using the extracted features into two categories: bleeding and nonbleeding images. For performance evaluation a series of experiments are performed on two standard benchmark datasets. It has been observed that the proposed architecture outclass the single deep learning architectures, with an average accuracy in detection bleeding regions of 97.65 % and 95.70 % on well-known state-of-the-art datasets considering three different fusion rules, with the best combination in terms of accuracy and training time obtained using mean value pooling as fusion rule and Support Vector Machine as classifier.

Identifying Transcriptomic Signatures and Rules for SARS-CoV-2 Infection.

The world-wide Coronavirus Disease 2019 (COVID-19) pandemic was triggered by the widespread of a new strain of coronavirus named as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Multiple studies on the pathogenesis of SARS-CoV-2 have been conducted immediately after the spread of the disease. However, the molecular pathogenesis of the virus and related diseases has still not been fully revealed. In this study, we attempted to identify new transcriptomic signatures as candidate diagnostic models for clinical testing or as therapeutic targets for vaccine design. Using the recently reported transcriptomics data of upper airway tissue with acute respiratory illnesses, we integrated multiple machine learning methods to identify effective qualitative biomarkers and quantitative rules for the distinction of SARS-CoV-2 infection from other infectious diseases. The transcriptomics data was first analyzed by Boruta so that important features were selected, which were further evaluated by the minimum redundancy maximum relevance method. A feature list was produced. This list was fed into the incremental feature selection, incorporating some classification algorithms, to extract qualitative biomarker genes and construct quantitative rules. Also, an efficient classifier was built to identify patients infected with SARS-COV-2. The findings reported in this study may help in revealing the potential pathogenic mechanisms of COVID-19 and finding new targets for vaccine design.

A system call refinement-based enhanced Minimum Redundancy Maximum Relevance method for ransomware early detection

Ransomware is a special type of malicious software that encrypts the user's assets and makes it unavailable to the users until a ransom is paid to the ransomware author. Such attacks have become one of the most widespread malware that poses serious threat to both individuals and business organizations. Against this destructive malicious program, the dynamic analysis approach is the most popular approach for detecting such an attack. The majority of dynamic analysis relies on the system calls, as these provide an interface for programs to request service from the operating system. However, the redundancy and the irrelevant system calls that the ransomware authors inject in the actual execution flow of suspicious binaries generate a high noisy behavioural sequence that adversely impacts in the detection performance of anti-ransomware tools. To this end, we proposed a non-signature-based detection approach based on the effective windows API call sequences using supervised machine learning techniques. To achieve this objective, we propose an Enhanced Maximum-Relevance and Minimum-Redundancy (EmRmR) filter method to remove the noisy features and select the most relevant subset of features to characterize the real behaviour of the ransomware. Unlike the original mRmR, the EmRmR avoids unnecessary computations intrinsic in the original mRmR algorithms with a small number of evaluations. In addition, this work has introduced a refinement process to reduce the size of the program's call traces by removing those windows API calls that do not have a strong indication for describing the critical behaviour of the ransomware. After accomplishing extensive experimental evaluations, and comparing with existing behavioural-based detection approaches, the proposed method has shown to be effective for discriminating the behaviour of ransomware, and indicates a high detection accuracy with few false-positive rates.

Diagnostic accuracy of unenhanced CT texture analysis to differentiate mass-forming pancreatitis from pancreatic ductal adenocarcinoma.

To investigate the value of texture analysis on unenhanced computed tomography (CT) to potentially differentiate mass-forming pancreatitis (MFP) from pancreatic ductal adenocarcinoma (PDAC). A retrospective study consisting of 109 patients (30 MFP patients vs 79 PDAC patients) who underwent preoperative unenhanced CT between January 2012 and December 2017 was performed. Synthetic minority oversampling technique (SMOTE) algorithm was adopted to reconstruct and balance MFP and PDAC samples. A total of 396 radiomic features were extracted from unenhanced CT images. Mann-Whitney U test and minimum redundancy maximum relevance (MRMR) methods were used for the purpose of dimension reduction. Predictive models were constructed using random forest (RF) method, and were validated using leave group out cross-validation (LGOCV) method. Diagnostic performance of the predictive model, including sensitivity, specificity, accuracy, positive predicting value (PPV), and negative predicting value (NPV), was recorded. We applied 200% of SMOTE to MFP and PDAC patients, resulting in 90 MFP patients compared with 120 PDAC patients. Dimension reduction steps yielded 30 radiomic features using Mann-Whitney U test and MRMR methods. Ten radiomic features were retained using RF method. Four most predictive parameters, including GreyLevelNonuniformity_angle90_offset1, VoxelValueSum, HaraVariance, and ClusterProminence_AllDirection_offset1_SD, were used to generate the predictive model with preferable 92.2% sensitivity, 94.2% specificity, 93.3% accuracy, 92.2% PPV, and 94.2% NPV. Finally, in LGOCV analysis, a high pooled mean sensitivity, specificity, and accuracy (82.6%, 80.8%, and 82.1%, respectively) indicate a relatively reliable and stable predictive model. Unenhanced CT texture analysis can be a promising noninvasive method in discriminating MFP from PDAC.

Automatic A-line coronary plaque classification using combined deep learning and textural features in intravascular OCT images.

We developed a fully automated method for classifying A-line coronary plaques in intravascular optical coherence tomography images using combined deep learning and textural features. The proposed method was trained on 4,292 images from 48 pullbacks giving 80 manually labeled, volumes of interest. Preprocessing steps including guidewire/shadow removal, lumen boundary detection, pixel shifting, and noise reduction were employed. We built a convolutional neural network to extract the deep learning features from the preprocessed image. Traditional textural features were also extracted and combined with deep learning features. Feature selection was performed using the minimum redundancy maximum relevance method. Combined features were utilized as inputs for a random forest classifier. After classification, conditional random field (CRF) method was used for classification noise cleaning. We determined a sub-feature set with the most predictive power. With CRF noise cleaning, sensitivities/specificities were 82.2%/90.8% and 82.4%/89.2% for fibrolipidic and fibrocalcific classes, respectively, with good Dice coefficients. The classification noise cleaning step improved performance metrics by nearly 10-15%. The predicted en face classification maps of entire pullbacks agreed favorably to the manually labeled counterparts. Both assessments suggested that our automated measurements gave clinically relevant results. The proposed method is very promising with regards to both clinical treatment planning and research applications.