Biphasic majority voting-based comparative COVID-19 diagnosis using chest X-ray images

The COVID-19 pandemic has been affecting the world since December 2019, and nowadays, the number of infected is increasing rapidly. Chest X-ray images are clinical adjuncts that can be used in the diagnosis of COVID-19 disease. Because of the rapid spread of COVID-19 disease worldwide and the limited number of expert radiologists, the proposed method uses the automatic diagnosis method rather than a manual diagnosis method. In the paper, COVID-19 Positive/Negative (2275 Positive, 4626 Negative) and Normal/Pneumonia (2313 Normal, 2313 Pneumonia) are diagnosed using chest X-ray images. Herein, 80 % and 20 % of the images are used in the training and validation set, respectively. In the proposed method, six different classifiers are trained using chest X-ray images, and the five most successful classifiers are used in both phases. In Phase-1 and Phase-2, image features are extracted using the Bag of Features method for Cosine K-Nearest Neighbor (KNN), Linear Discriminant, Logistic Regression, Bagged Trees Ensemble, Medium Gaussian Support Vector Machine (SVM), excluding SqueezeNet Deep Learning (K = 2000 and K = 1500 for Phase-1 and Phase-2, respectively). In both phases, the five most successful classifiers are determined, and images classify with the help of the Majority Voting (Mathematical Evaluation) method. The application of the proposed method is designed for users to diagnose COVID-19 Positive, Normal, and Pneumonia. The results show that accuracy values obtained by Majority Voting (Mathematical Evaluation) method for Phase-1 and Phase-2 are equal to 99.86 % and 99.28 %, respectively. Thus, it indicates that the accuracy of the whole system is 99.63 %. When we analyze the classification performance metrics for Phase-1 and Phase-2, Specificity (%), Precision (%), Recall (%), F₁ Score (%), Area Under Curve (AUC), and Matthews Correlation Coefficient (MCC) are equal to 99.98-99.83-99.07-99.51-0.9974-0.9855 and 99.73-99.69-98.63-99.23-0.9928-0.9518, respectively. Moreover, if the classification performance metrics of the whole system are examined, it is seen that Specificity (%), Precision (%), Recall (%), F₁ Score (%), AUC, and MCC are 99.88, 99.78, 98.90, 99.40, 0.9956, and 0.9720, respectively. When the studies in the literature are examined, the results show that the proposed model is better than its counterparts. Because the best performance metrics for the dataset used were obtained in this study. In addition, since the biphasic majority voting technique is used in the study, it is seen that the proposed model is more reliable. On the other hand, although there are tens of thousands of studies on this subject, the usability of these models is debatable since most of them do not have graphical user interface applications. Already, in artificial intelligence technologies, besides the performance of the developed models, their usability is also important. Because the developed models can generally be used by people who are less knowledgeable about artificial intelligence.

A hybrid ensemble approach to accelerate the classification accuracy for predicting malnutrition among under-five children in sub-Saharan African countries

BACKGROUND

The proper intake of nutrients is essential to the growth and maturation of youngsters. In sub-Saharan Africa, 1 in 7 children dies before age 5 y, and more than a third of these deaths are attributed to malnutrition. The main purpose of this study was to develop a majority voting-based hybrid ensemble (MVBHE) learning model to accelerate the prediction accuracy of malnutrition data of under-five children in sub-Saharan Africa.

METHODS

This study used available under-five nutritional secondary data from the Demographic and Health Surveys performed in sub-Saharan African countries. The research used bagging, boosting, and voting algorithms, such as random forest, decision tree, eXtreme Gradient Boosting, and k-nearest neighbors machine learning methods, to generate the MVBHE model.

RESULTS

We evaluated the model performances in contrast to each other using different measures, including accuracy, precision, recall, and the F1 score. The results of the experiment showed that the MVBHE model (96%) was better at predicting malnutrition than the random forest (81%), decision tree (60%), eXtreme Gradient Boosting (79%), and k-nearest neighbors (74%).

CONCLUSIONS

The random forest algorithm demonstrated the highest prediction accuracy (81%) compared with the decision tree, eXtreme Gradient Boosting, and k-nearest neighbors algorithms. The accuracy was then enhanced to 96% using the MVBHE model. The MVBHE model is recommended by the present study as the best way to predict malnutrition in under-five children.

Deep learning for collateral evaluation in ischemic stroke with imbalanced data

PURPOSE

Collateral evaluation is typically done using visual inspection of cerebral images and thus suffers from intra- and inter-rater variability. Large open databases of ischemic stroke patients are rare, limiting the use of deep learning methods in treatment decision-making.

METHODS

We adapted a pre-trained EfficientNet B0 network through transfer learning to improve collateral evaluation using slice-based and subject-level classification. Our method uses stacking and overlapping of 2D slices from a patient's 4D computed tomography angiography (CTA) and a majority voting scheme to determine a patient's final collateral grade based on all classified 2D MIPs. Class imbalance is handled in the evaluation process by using the focal loss with class weight to penalize the majority class.

RESULTS

We evaluated our method using a nine-fold cross-validation performed with 83 subjects. Mean sensitivity of 0.71, specificity of 0.84, and a weighted F1 score of 0.71 in multi-class (good, intermediate, and poor) classification were obtained. Considering treatment effect, a dichotomized decision is also made for collateral scoring of a subject based on two classes (good/intermediate and poor) which achieves a sensitivity of 0.89 and specificity of 0.96 with a weighted F1 score of 0.95.

CONCLUSION

An automatic and robust collateral assessment method that mitigates the issues with the small imbalanced dataset was developed. Computer-aided evaluation of collaterals can help decision-making of ischemic stroke treatment strategy in clinical settings.

High-throughput 3DRA segmentation of brain vasculature and aneurysms using deep learning

BACKGROUND AND OBJECTIVES

Automatic segmentation of the cerebral vasculature and aneurysms facilitates incidental detection of aneurysms. The assessment of aneurysm rupture risk assists with pre-operative treatment planning and enables in-silico investigation of cerebral hemodynamics within and in the vicinity of aneurysms. However, ensuring precise and robust segmentation of cerebral vessels and aneurysms in neuroimaging modalities such as three-dimensional rotational angiography (3DRA) is challenging. The vasculature constitutes a small proportion of the image volume, resulting in a large class imbalance (relative to surrounding brain tissue). Additionally, aneurysms and vessels have similar image/appearance characteristics, making it challenging to distinguish the aneurysm sac from the vessel lumen.

METHODS

We propose a novel multi-class convolutional neural network to tackle these challenges and facilitate the automatic segmentation of cerebral vessels and aneurysms in 3DRA images. The proposed model is trained and evaluated on an internal multi-center dataset and an external publicly available challenge dataset.

RESULTS

On the internal clinical dataset, our method consistently outperformed several state-of-the-art approaches for vessel and aneurysm segmentation, achieving an average Dice score of 0.81 (0.15 higher than nnUNet) and an average surface-to-surface error of 0.20 mm (less than the in-plane resolution (0.35 mm/pixel)) for aneurysm segmentation; and an average Dice score of 0.91 and average surface-to-surface error of 0.25 mm for vessel segmentation. In 223 cases of a clinical dataset, our method accurately segmented 190 aneurysm cases.

CONCLUSIONS

The proposed approach can help address class imbalance problems and inter-class interference problems in multi-class segmentation. Besides, this method performs consistently on clinical datasets from four different sources and the generated results are qualified for hemodynamic simulation. Code available at https://github.com/cistib/vessel-aneurysm-segmentation.

Two-step learning for crowdsourcing data classification

Crowdsourcing learning (Bonald and Combes 2016; Dawid and Skene, J R Stat Soc: Series C (Appl Stat), 28(1):20-28 1979; Karger et al. 2011; Li et al, IEEE Trans Knowl Data Eng, 28(9):2296-2319 2016; Liu et al. 2012; Schlagwein and Bjorn-Andersen, J Assoc Inform Syst, 15(11):3 2014; Zhang et al. 2014) plays an increasingly important role in the era of big data (Liu et al., IEEE Trans Syst Man Cybern: Syst, 48(12): 451-2461, 2017; Zhang et al. 2014) due to its ability to easily solve large-scale data annotations (Musen et al., J Amer Med Informs Assoc, 22(6):1148-1152 2015). However, in the process of crowdsourcing learning, the uneven knowledge level of workers often leads to low accuracy of the label after marking, which brings difficulties to the subsequent processing (Edwards and Teddy 2013) and analysis of crowdsourcing data. In order to solve this problem, this paper proposes a two-step learning crowdsourced data classification algorithm, which optimizes the original label data by simultaneously considering the two issues of different worker abilities and the similarity between crowdsourced data (Kasikci et al. 2013) samples, so as to get more accurate label data. The two-step learning algorithm mainly includes two steps. Firstly, the worker's ability to label different samples is obtained by constructing and training the worker's ability model, and then the similarity between samples is calculated by the cosine measurement method (Muflikhah and Baharudin 2009), and finally the original label data is optimized by combining the above two results. The experimental results also show that the two-step learning classification algorithm proposed in this article has achieved better experimental results than the comparison algorithm.

BH-index: A predictive system based on serum biomarkers and ensemble learning for early colorectal cancer diagnosis in mass screening

BACKGROUND AND OBJECTIVE

Colorectal cancer is one of the most common malignancies among the general population. Artificial Intelligence methodologies based on serum parameters are in continuous development to obtain less expensive tools for highly sensitive diagnoses. This study proposes a predictive system based on serum biomarkers and ensemble learning to predict colorectal cancer presence and the related TNM stage in patients.

METHODS

We have selected 17 significant plasmatic proteins, i.e., Carcinoembryonic Antigen, CA 19-9, CA 125, CA 50, CA 72-4, Tissue Polypeptide Antigen, C-Reactive Protein, Ceruloplasmin, Haptoglobin, Transferrin, Ferritin, α-1-Antitrypsin, α-2-Macroglobulin, α-1 Acid Glycoprotein, Complement C4, Complement C3, and Retinol Binding Protein, regarding 345 patients (248 affected by the neoplastic disease). The proposed system consists of two predictors, i.e., binary and staging; the former predicts the presence/absence of cancer, while the latter identifies the related TNM stage (I, II, III, or IV). The experiments were conducted by deploying and comparing Random Forest, XGBoost, Support Vector Machine, and Multilayer Perceptron with feature selection based on Gini Importance and with dimensionality reduction via PCA.

RESULTS

The results show that the system composed of XGBoost as binary and staging predictor reaches 91.30% accuracy, 90% sensitivity, and 93.33% specificity for the absence/presence outcome, while 66.66% accuracy for the staging response. With the expansion of the training set in favor of positive patients and majority voting, the system composed of the combination of Support Vector Machine, XGBoost, and Multilayer Perceptron as the binary predictor reaches 98.03% accuracy, 100% sensitivity, and 92.30% specificity, while the combination of Random Forest, XGBoost, and Multilayer Perceptron as staging predictor achieves 60% accuracy. The final system reaches, in terms of accuracy, 98.03%, and 66.66% for the binary and staging predictors, respectively. It was also found that the biomarkers which contribute most to the binary decision are Ceruloplasmin and α-2-Macroglobulin, while the least significant dimensions are CA 50 and α-1-Antitrypsin; instead, Carcinoembryonic Antigen and α-1 Acid Glycoprotein are the most significant to the staging decision.

CONCLUSIONS

The present study proves the effectiveness of deploying serum biomarkers as feature dimensions for early colorectal cancer diagnosis and of using majority voting for noise reduction in the prediction.

Prediction of obstructive sleep apnea using ensemble of recurrence plot convolutional neural networks (RPCNNs) from polysomnography signals

Obstructive Sleep Apnea (OSA) is a common disorder characterized by periodic cessation of breathing during sleep. OSA affects daily life and poses a severe threat to human health. The standard clinical method for identifying and predicting OSA events is the use of Polysomnography signals. In this paper, a novel scheme based on an ensemble of recurrence plots (RPs) and pre-trained convolutional neural networks (RPCNNs) is proposed to improve the prediction rate of OSA. First, RPs were used to represent the dynamic behavior of single electroencephalogram (EEG) and electrocardiogram (ECG) signals for 60 s before and during OSA events. Then, using RPs, three prompt CNNs named ResNet-50 were fine-tuned, and their classification results were fused via the Majority Voting (MV) method to produce a final result concerning prediction. Next, the subject-independent Leave-One-Subject-Out Cross-Validation (LOSO-CV) and subject-dependent 10-fold Cross-Validation (10-fold CV) methods were used to validate the prediction rate from signals derived from the University College Dublin Sleep Apnea Database. Finally, the highest achieved average accuracy for the fusion level was 91.74% and 89.45% at the 10-fold CV and LOSO-CV. Additionally, our results outperformed state-of-the-art findings and could be recommended to predict and detect other biomedical signals. As a result, this predictive system can also be used to adjust the air pressure in sleep apnea patients' Automatic Positive Airway Pressure (APAP) devices.

COVID-19 outbreak: An ensemble pre-trained deep learning model for detecting informative tweets

On 11 March 2020, the (WHO) World Health Organization declared COVID-19 (CoronaVirus Disease 2019) as a pandemic. A further crisis has manifested mass fear and panic, driven by lack of information, or sometimes outright misinformation, alongside the coronavirus pandemic. Twitter is one of the prominent and trusted social media in this current outbreak. Over time, boundless COVID-19 headlines and vast awareness have been spreading, with tweets, updates, videos, and explosive posts. Few studies have been performed on the pandemic to detect and interrelate various disease types, including current coronavirus. However, it is pretty tricky to discriminate and detect a specific category. This work is motivated by the need to inform society about limiting irrelevant information and avoiding spreading negative emotions. In this context, the current work focuses on informative tweet detection in the pandemic to provide relevant information to the government, medical organizations, victims services, etc. This paper used a Majority Voting technique-based Ensemble Deep Learning (MVEDL) model. This MVEDL model is used to identify COVID-19 related (INFORMATIVE) tweets. The state-of-art deep learning models RoBERTa, BERTweet, and CT-BERT are used for best performance with the MVEDL model. The "COVID-19 English labeled tweets" dataset is used for training and testing the MVEDL model. The MVEDL model has shown 91.75 percent accuracy, 91.14 percent F1-score and outperforms the traditional machine learning and deep learning models. We also investigate how to use the MVEDL model for sentiment analysis on 226668 unlabeled COVID-19 tweets and their informative tweets. The application section discussed a comprehensive analysis of both actual and informative tweets. According to our knowledge, this is the first work on COVID-19 sentiment analysis using a deep learning ensemble model.

Performance optimisation of deep learning models using majority voting algorithm for brain tumour classification

BACKGROUND

Although biopsy is the gold standard for tumour grading, being invasive, this procedure also proves fatal to the brain. Thus, non-invasive methods for brain tumour grading are urgently needed. Here, a magnetic resonance imaging (MRI)-based non-invasive brain tumour grading method has been proposed using deep learning (DL) and machine learning (ML) techniques.

METHOD

Four clinically applicable datasets were designed. The four datasets were trained and tested on five DL-based models (convolutional neural networks), AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50, and five ML-based models, Support Vector Machine, K-Nearest Neighbours, Naïve Bayes, Decision Tree, and Linear Discrimination using five-fold cross-validation. A majority voting (MajVot)-based ensemble algorithm has been proposed to optimise the overall classification performance of five DL and five ML-based models.

RESULTS

The average accuracy improvement of four datasets using the DL-based MajVot algorithm against AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50 models was 2.02%, 1.11%, 1.04%, 2.67%, and 1.65%, respectively. Further, a 10.12% improvement was seen in the average accuracy of four datasets using the DL method against ML. Furthermore, the proposed DL-based MajVot algorithm was validated on synthetic face data and improved the male versus female face image classification accuracy by 2.88%, 0.71%, 1.90%, 2.24%, and 0.35% against AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50, respectively.

CONCLUSION

The proposed MajVot algorithm achieved promising results for brain tumour classification and is able to utilise the combined potential of multiple models.

Two-stepped majority voting for efficient EEG-based emotion classification

In this paper, a novel approach that is based on two-stepped majority voting is proposed for efficient EEG-based emotion classification. Emotion recognition is important for human–machine interactions. Facial features- and body gestures-based approaches have been generally proposed for emotion recognition. Recently, EEG-based approaches become more popular in emotion recognition. In the proposed approach, the raw EEG signals are initially low-pass filtered for noise removal and band-pass filters are used for rhythms extraction. For each rhythm, the best performed EEG channels are determined based on wavelet-based entropy features and fractal dimension-based features. The k-nearest neighbor (KNN) classifier is used in classification. The best five EEG channels are used in majority voting for getting the final predictions for each EEG rhythm. In the second majority voting step, the predictions from all rhythms are used to get a final prediction. The DEAP dataset is used in experiments and classification accuracy, sensitivity and specificity are used for performance evaluation metrics. The experiments are carried out to classify the emotions into two binary classes such as high valence (HV) vs low valence (LV) and high arousal (HA) vs low arousal (LA). The experiments show that 86.3% HV vs LV discrimination accuracy and 85.0% HA vs LA discrimination accuracy is obtained. The obtained results are also compared with some of the existing methods. The comparisons show that the proposed method has potential in the use of EEG-based emotion classification.

Automatic Segmentation of Multiple Organs on 3D CT Images by Using Deep Learning Approaches

This chapter focuses on modern deep learning techniques that are proposed for automatically recognizing and segmenting multiple organ regions on three-dimensional (3D) computed tomography (CT) images. CT images are widely used to visualize 3D anatomical structures composed of multiple organ regions inside the human body in clinical medicine. Automatic recognition and segmentation of multiple organs on CT images is a fundamental processing step of computer-aided diagnosis, surgery, and radiation therapy systems, which aim to achieve precision and personalized medicines. In this chapter, we introduce our recent works on addressing the issue of multiple organ segmentation on 3D CT images by using deep learning, a completely novel approach, instead of conventional segmentation methods originated from traditional digital image processing techniques. We evaluated and compared the segmentation performances of two different deep learning approaches based on 2D- and 3D deep convolutional neural networks (CNNs) without and with a pre-processing step. A conventional method based on a probabilistic atlas algorithm, which presented the best performance within the conventional approaches, was also adopted as a baseline for performance comparison. A dataset containing 240 CT scans of different portions of human bodies was used for training the CNNs and validating the segmentation performance of the learning results. A maximum number of 17 types of organ regions in each CT scan were segmented automatically and validated with the human annotations by using ratio of intersection over union (IoU) as the criterion. Our experimental results showed that the IoUs of the segmentation results had a mean value of 79% and 67% by averaging 17 types of organs that were segmented by the proposed 3D and 2D deep CNNs, respectively. All results using the deep learning approaches showed better accuracy and robustness than the conventional segmentation method that used the probabilistic atlas algorithm. The effectiveness and usefulness of deep learning approaches were demonstrated for multiple organ segmentation on 3D CT images.

Combinations of immuno-checkpoint inhibitors predictive biomarkers only marginally improve their individual accuracy

BACKGROUND

There are no accepted universal biomarkers capable to accurately predict response to immuno-checkpoint inhibitors (ICI). Although recent literature has been flooded with studies on ICI predictive biomarkers, available data show that currently approved companion diagnostics either leave out many possible responders, as in the case of PD-L1 testing for first-line metastatic lung cancer, or apply to a small subset of patients, such as the recently approved treatment for microsatellite instability-high or mismatch repair deficiency tumors. In this study, we conducted a survey of the available data on ICI trials with matched genomic or transcriptomic datasets in order to cross-validate the proposed biomarkers, to assess whether their prediction power was confirmed and, mainly, to investigate if their combination was able to generate a better predictive tool.

METHODS

We extracted clinical information and sequencing data details from publicly available datasets, along with a list of possible biomarkers obtained from the recent literature. After an operation of data harmonization, we validated the performance of all the biomarkers taken individually. Furthermore, we tested two strategies to combine the best performing biomarkers in order to improve their predictive value.

RESULTS

When considered individually, some of the biomarkers, such as the ImmunoPhenoScore, and the IFN-γ signature, did not confirm their originally proposed predictive power. The best absolute scoring biomarkers are TIDE, one of the ICB resistance signatures and CTLA4 with a mean AUC > 0.66. Among the combinations tested, generalized linear models showed the best performance with an AUC of 0.78.

CONCLUSIONS

We confirmed that the available biomarkers, taken individually, fail to provide a satisfactory predictive value. Unfortunately, also combination of some of them only provides marginal improvements. Hence, in order to generate a more robust way to predict ICI efficacy it is necessary to analyze and combine additional biomarkers and interrogate a wider set of clinical data.

Fusion of deep learning models of MRI scans, Mini-Mental State Examination, and logical memory test enhances diagnosis of mild cognitive impairment

Introduction

Our aim was to investigate if the accuracy of diagnosing mild cognitive impairment (MCI) using the Mini–Mental State Examination (MMSE) and logical memory (LM) test could be enhanced by adding MRI data.

Methods

Data of individuals with normal cognition and MCI were obtained from the National Alzheimer Coordinating Center database (n = 386). Deep learning models trained on MRI slices were combined to generate a fused MRI model using different voting techniques to predict normal cognition versus MCI. Two multilayer perceptron (MLP) models were developed with MMSE and LM test results. Finally, the fused MRI model and the MLP models were combined using majority voting.

Results

The fusion model was superior to the individual models alone and achieved an overall accuracy of 90.9%.

Discussion

This study is a proof of principle that multimodal fusion of models developed using MRI scans, MMSE, and LM test data is feasible and can better predict MCI.

An Alzheimers disease related genes identification method based on multiple classifier integration

BACKGROUND AND OBJECTIVE

Alzheimers disease (AD) is a fatal neurodegenerative disease and the onset of AD is insidious. Full understanding of the AD-related genes (ADGs) has not been completed. The National Center for Biotechnology Information (NCBI) provides an AD dataset of 22,283 genes. Among these genes, 71 genes have been identified as ADGs. But there may still be underlying ADGs that have not yet been identified in the remaining 22,212 genes. This paper aims to identify additional ADGs using machine learning techniques.

METHODS

To improve the accuracy of ADG identification, we propose a gene identification method through multiple classifier integration. First, a feature selection algorithm is applied to select the most relevant attributes. Second, a two-stage cascading classifier is developed to identify ADGs. The first stage classification task is based on the relevance vector machine and, in the second stage, the results of three classifiers, support vector machine, random forest and extreme learning machine, are combined through voting.

RESULTS

According to our results, feature selection improves accuracy and reduces training time. Voting based classifier reduces the classification errors. The proposed ADG identification system provides accuracy, sensitivity and specificity at levels of 78.77%, 83.10% and 74.67%, respectively. Based on the proposed ADG identification method, potentially additional ADGs are identified and top 13 genes (predicted ADGs) are presented.

CONCLUSIONS

In this paper, an ADG identification method for identifying ADGs is presented. The proposed method which combines feature selection, cascading classifier and majority voting leads to higher specificity and significantly increases the accuracy and sensitivity of ADG identification. Potentially new ADGs are identified.

iACP-GAEnsC: Evolutionary genetic algorithm based ensemble classification of anticancer peptides by utilizing hybrid feature space

Cancer is a fatal disease, responsible for one-quarter of all deaths in developed countries. Traditional anticancer therapies such as, chemotherapy and radiation, are highly expensive, susceptible to errors and ineffective techniques. These conventional techniques induce severe side-effects on human cells. Due to perilous impact of cancer, the development of an accurate and highly efficient intelligent computational model is desirable for identification of anticancer peptides. In this paper, evolutionary intelligent genetic algorithm-based ensemble model, 'iACP-GAEnsC', is proposed for the identification of anticancer peptides. In this model, the protein sequences are formulated, using three different discrete feature representation methods, i.e., amphiphilic Pseudo amino acid composition, g-Gap dipeptide composition, and Reduce amino acid alphabet composition. The performance of the extracted feature spaces are investigated separately and then merged to exhibit the significance of hybridization. In addition, the predicted results of individual classifiers are combined together, using optimized genetic algorithm and simple majority technique in order to enhance the true classification rate. It is observed that genetic algorithm-based ensemble classification outperforms than individual classifiers as well as simple majority voting base ensemble. The performance of genetic algorithm-based ensemble classification is highly reported on hybrid feature space, with an accuracy of 96.45%. In comparison to the existing techniques, 'iACP-GAEnsC' model has achieved remarkable improvement in terms of various performance metrics. Based on the simulation results, it is observed that 'iACP-GAEnsC' model might be a leading tool in the field of drug design and proteomics for researchers.

Prediction of labor onset type: Spontaneous vs induced; role of electrohysterography?

BACKGROUND AND OBJECTIVE

Induction of labor (IOL) is a medical procedure used to initiate uterine contractions to achieve delivery. IOL entails medical risks and has a significant impact on both the mother's and newborn's well-being. The assistance provided by an automatic system to help distinguish patients that will achieve labor spontaneously from those that will need late-term IOL would help clinicians and mothers to take an informed decision about prolonging pregnancy. With this aim, we developed and evaluated predictive models using not only traditional obstetrical data but also electrophysiological parameters derived from the electrohysterogram (EHG).

METHODS

EHG recordings were made on singleton term pregnancies. A set of 10 temporal and spectral parameters was calculated to characterize EHG bursts and a further set of 6 common obstetrical parameters was also considered in the predictive models design. Different models were implemented based on single layer Support Vector Machines (SVM) and with aggregation of majority voting of SVM (double layer), to distinguish between the two groups: term spontaneous labor (≤41 weeks of gestation) and IOL late-term labor. The areas under the curve (AUC) of the models were compared.

RESULTS

The obstetrical and EHG parameters of the two groups did not show statistically significant differences. The best results of non-contextualized single input parameter SVM models were achieved by the Bishop Score (AUC= 0.65) and GA at recording time (AUC= 0.68) obstetrical parameters. The EHG parameter median frequency, when contextualized with the two obstetrical parameters improved these results, reaching AUC= 0.76. Multiple input SVM obtained AUC= 0.70 for all EHG parameters. Aggregation of majority voting of SVM models using contextualized EHG parameters achieved the best result AUC= 0.93.

CONCLUSIONS

Measuring the electrophysiological uterine condition by means of electrohysterographic recordings yielded a promising clinical decision support system for distinguishing patients that will spontaneously achieve active labor before the end of full term from those who will require late term IOL. The importance of considering these EHG measurements in the patient's individual context was also shown by combining EHG parameters with obstetrical parameters. Clinicians considering elective labor induction would benefit from this technique.

A new classification scheme of plastic wastes based upon recycling labels

Since recycling of materials is widely assumed to be environmentally and economically beneficial, reliable sorting and processing of waste packaging materials such as plastics is very important for recycling with high efficiency. An automated system that can quickly categorize these materials is certainly needed for obtaining maximum classification while maintaining high throughput. In this paper, first of all, the photographs of the plastic bottles have been taken and several preprocessing steps were carried out. The first preprocessing step is to extract the plastic area of a bottle from the background. Then, the morphological image operations are implemented. These operations are edge detection, noise removal, hole removing, image enhancement, and image segmentation. These morphological operations can be generally defined in terms of the combinations of erosion and dilation. The effect of bottle color as well as label are eliminated using these operations. Secondly, the pixel-wise intensity values of the plastic bottle images have been used together with the most popular subspace and statistical feature extraction methods to construct the feature vectors in this study. Only three types of plastics are considered due to higher existence ratio of them than the other plastic types in the world. The decision mechanism consists of five different feature extraction methods including as Principal Component Analysis (PCA), Kernel PCA (KPCA), Fisher's Linear Discriminant Analysis (FLDA), Singular Value Decomposition (SVD) and Laplacian Eigenmaps (LEMAP) and uses a simple experimental setup with a camera and homogenous backlighting. Due to the giving global solution for a classification problem, Support Vector Machine (SVM) is selected to achieve the classification task and majority voting technique is used as the decision mechanism. This technique equally weights each classification result and assigns the given plastic object to the class that the most classification results agree on. The proposed classification scheme provides high accuracy rate, and also it is able to run in real-time applications. It can automatically classify the plastic bottle types with approximately 90% recognition accuracy. Besides this, the proposed methodology yields approximately 96% classification rate for the separation of PET or non-PET plastic types. It also gives 92% accuracy for the categorization of non-PET plastic types into HPDE or PP.

Cancer diagnosis by nuclear morphometry using spatial information

Methods for extracting quantitative information regarding nuclear morphology from histopathology images have been long used to aid pathologists in determining the degree of differentiation in numerous malignancies. Most methods currently in use, however, employ the naïve Bayes approach to classify a set of nuclear measurements extracted from one patient. Hence, the statistical dependency between the samples (nuclear measurements) is often not directly taken into account. Here we describe a method that makes use of statistical dependency between samples in thyroid tissue to improve patient classification accuracies with respect to standard naïve Bayes approaches. We report results in two sample diagnostic challenges.