• Multi-stage optimization of a deep model: A case study on ground motion modeling
    Journal of PloS one, September 2018
    Other Authors: Amir H Gandomi, Simon Fong, Anke Meyer-Baese, Simon Y

    In this study, a multi-stage optimization procedure is proposed to develop deep neural network models which results in a powerful deep learning pipeline called intelligent deep learning (iDeepLe). The proposed pipeline is then evaluated by a challenging real-world problem, the modeling of the spectral acceleration experienced by a particle during earthquakes. This approach has three main stages to optimize the deep model topology, the hyper-parameters, and its performance, respectively. This pipeline optimizes the deep model via adaptive learning rate optimization algorithms for both accuracy and complexity in multiple stages, while simultaneously solving the unknown parameters of the regression model. Among the seven adaptive learning rate optimization algorithms, Nadam optimization algorithm has shown the best performance results in the current study. The proposed approach is shown to be a suitable tool to generate solid models for this complex real-world system. The results also show that the parallel pipeline of iDeepLe has the capacity to handle big data problems as well.
    Download PDF


  • Deep learning in medical imaging: fMRI big data analysis via convolutional neural networks
    Proceedings of the Practice and Experience on Advanced Research Computing, ACM, July 2018
    Other Authors: Amir H Gandomi, Ian McCann, Mieke HJ Schulte, Anna E Goudriaan, Anke Meyer-Baese

    This paper aims at implementing novel biomarkers extracted from functional magnetic resonance imaging (fMRI) images taken at resting-state using convolutional neural networks (CNN) to predict relapse in heavy smoker subjects. In this regard, two classes of subjects were studied. The first class contains 19 subjects that took the drug N-acetylcysteine (NAC), and the second class contains 20 subjects that took a placebo. The subjects underwent a double-blind smoking cessation treatment. The resting-state fMRI of the subjects' brains were recorded through 200 snapshots before and after the treatment. The relapse data was assessed after 6 months past the treatment. The data was pre-processed and an undercomplete autoencoder along with various similarity metrics was developed to extract salient features that could differentiate the pre and post treatment images. Finally, the extracted feature matrix was fed into robust classification algorithms to classify the subjects in terms of relapse and non-relapse. The XGBoost algorithm with 0.86 precision and an AUC of 0.92 outperformed the other classification methods in prediction of relapse in subjects.
    Download PDF


  • An Evolutionary Online Framework for MOOC Performance Using EEG Data
    IEEE Congress on Evolutionary Computation (CEC), July 2018
    Other Authors: Amir H Gandomi, Anke Meyer-Baese

    Massive Online Open Course (MOOC) is a scalable, free or affordable online course which emerged as one of the fastest growing distance education platforms in the past decade. One of the biggest challenges that threatens distance education is abnormality in the overall level of consciousness of students while they are taking the course. In this paper, an evolutionary online framework was proposed to improve the performance of MOOCs via noninvasive electro-physiological monitoring methods such as electroencephalography (EEG). Based on the proposed platform, EEG signals can be recorded from users while they are wearing any EEG headsets. EEG measures a brain's spontaneous voltage fluctuations resulting from ionic current within the neurons of the brain via multiple electrodes placed on the scalp. A total of eleven extracted features from EEG signals were employed as the inputs of the evolutionary classification algorithm to predict two classes of confused and not-confused for each individual. An accuracy of 89 % was considered significant enough to suggest that there is difference in the EEG signals of individuals with confusion versus not-confused individuals.
    Download PDF


  • A Pareto Front Based Evolutionary Model for Airfoil Self-Noise Prediction
    IEEE Congress on Evolutionary Computation (CEC), July 2018
    Other Authors: Amir H Gandomi, Anke Meyer-Baese

    According to NASA's report on the technologies that could reduce external aircraft noise by 10 dB, a challenge equally as important as finding approaches on airframe noise reduction is the demand to bring up strategies by which airframe noise can be predicted both accurately and rapidly. One of the components of the overall airframe noise is the self-noise of the airfoil itself. In this paper, an evolutionary symbolic implementation for airfoil self-noise prediction was proposed. Multi-objective genetic programming as a subset of evolutionary computation along with adaptive regression by mixing algorithm was used to create an executable fused model. The developed model was tested on the airfoil self-noise database and the performance of the developed model was compared to the previous works and benchmark machine learning algorithms. The reasonable results suggest that the proposed model can be applied to noise generation by low-Mach-number turbulent flows in aerospace, automobile, underwater, and wind turbine acoustic communities.
    Download PDF


  • Magnetic resonance imaging of the breast and radiomics analysis for an improved early prediction of the response to neoadjuvant chemotherapy in breast cancer patients
    Cancer Research, July 2018
    Other Authors: Katja Pinker-Domenig, Georg J. Wengert, Thomas Helbich, Zsuzsanna Bago-Horvath, Sousan Akaei, Elizabeth A. Morris, Anke Meyer-Baese

    Background and Aim: In patients undergoing neoadjuvant chemotherapy for breast cancer the achievement of a pathological complete response (pCR) is associated with a significantly improved disease-free and overall survival. Therefore, accurate means to predict treatment response as early as possible are desirable to identify women who don't benefit from this cytotoxic therapy. Several studies have demonstrated that dynamic contrast-enhanced MRI is the most sensitive method for the assessment and prediction of treatment response. In the past decade, the field of medical image analysis has grown exponentially, with an increased number of pattern recognition tools and an increase in data set sizes. These advances have facilitated the development of processes for high-throughput extraction of quantitative features that result in the conversion of images into mineable data and the subsequent analysis of these data for decision support. This emerging field in medical research is termed radiomics. The aim of this study was to assess radiomics with dynamic contrast-enhanced (DCE) MRI for the early prediction of pathological complete response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy.
    Methods and materials: In this IRB approved prospective study 41 women with breast cancer scheduled for NAC were included and underwent MRI of the breast at 3T with DCE and T2-weighted imaging prior to and after two cycles of NAC. For each lesion a total of 14 features were extracted ranging from morphological and kinetic MRI ADC parameters. A recursive feature elimination method along with five different classifiers was performed including: linear support vector machine (SVM), linear discriminant analysis (LDA), logistic regression (LR), random forest (RF), and stochastic gradient descent (SGD) was employed to rank the features. Histopathology using the Residual Cancer Burden (RCB) score and class calculated from post-treatment surgical specimen and patient outcomes were used as the standard of reference.
    Results: Classification accuracy was assessed for pCR as defined by the RCB score, metastases and disease specific death. Radiomics analysis of MRI data achieved AUCs for RCB score (AUC 0.85), metastases (AUC 0.87) based on RF and death (AUC 0.92) based on SVM. The most relevant parameters for prediction of RCB score were mass internal enhancement characteristics, shape and margins with DCE, for metastasis peri-tumoral edema on T2-weighted imaging, mass margins and internal enhancement characteristics, and for death high signal intensity on T2-weighted imaging, mass margins, and internal enhancement characteristics.
    Conclusion: Radiomics with MRI of the breast using DCE and T2-weighted imaging enables prediction of response to NAC with high accuracy and thus can provide predictive information to guide treatment decisions.


  • Radiomics with magnetic resonance imaging of the breast for early prediction of response to neo-adjuvant chemotherapy in breast cancer patients
    Joint Annual Meeting ISMRM-ESMRMB, June 2018
    Other Authors: Katja Pinker-Domenig, Georg J. Wengert, Thomas Helbich, Zsuzsanna Bago-Horvath, Sousan Akaei, Elizabeth A. Morris, Anke Meyer-Baese

    Breast cancer patients that achieve pCR after NAC have a significantly improved DFS and OS. The aim of this study was to assess radiomics with multiparametric MRI using DCE and T2w imaging for the early prediction of pCR to NAC in breast cancer patients. In 41 women radiomics analysis of MRI data was performed. Histopathology using the Residual Cancer Burden (RCB) score and class were the standard of reference. Radiomics analysis of MRI achieved AUCs for RCB score (AUC 0.85), metastases (AUC 0.87) and death (AUC 0.92). Radiomicswith multiparametric MRI enables prediction of response to NAC with high accuracy.


  • Reconfigurable instrument for measuring variations of capacitor's dielectric: an application to olive oil quality monitoring
    Sensing for Agriculture and Food Quality and Safety X, May 2018
    Other Authors: Francisco J Romero-Maldonado, Santiago Juarez, Inmaculada Ortiz-Gomez, Diego P Morales, Alfonso Salinas-Castillo, Encarnacion Castillo, Antonio García, Anke Meyer-Bäse

    The current method for the extraction of olive oil consists on the use of a decanter to split it by centrifugation. During this process, different olive oil samples are analyzed in a chemical laboratory in order to determine moisture levels in the oil, which is a decisive factor in olive oil quality. However, these analyses are usually both costly and slow. The developed prototype is the foundation of an instrument for real-time monitoring of moisture in olive oil. Using the olive oil as the dielectric of a parallel-plate capacitor, a model to relate the moisture in olive oil and capacitance has been created. One of the challenges for this application is the moisture range, which is usually between 1 and 2%, thus requiring the detection of pF-order variations in capacitance. This capacitance also depends on plate size and the distance between plates. The presented prototype, which is based on a PSoC (Programmable System-on-Chip), includes a reconfigurable digital and analog subsystem, which makes the determination of moisture independent of the capacitor. Finally, the measure is also sent to a smartphone via Bluetooth.
    Download PDF


  • Multi-level analysis of spatio-temporal features in non-mass enhancing breast tumors
    Smart Biomedical and Physiological Sensor Technology XV, May 2018
    Other Authors: Dat Ngo, Antonio Garcia, Encarnacin Castillo, Diego P Morales, Katja Pinker-Domenig, Mark Lobbes, Anke Meyer-Baese

    Diagnostically challenging breast tumors and Non-Mass-Enhancing (NME) lesions are often characterized by spatial and temporal heterogeneity, thus difficult to detect and classify. Differently from mass enhancing tumors they have an atypical temporal enhancement behavior that does not enable a straight-forward lesion classification into benign or malignant. The poorly defined margins do not support a concise shape description thus impacting morphological characterizations. A multi-level analysis strategy capturing the features of Non-MassLike-Enhancing (NMLEs) is shown to be superior to other methods relying only on morphological and kinetic information. In addition to this, the NMLE features such as NMLE distribution types and NMLE enhancement pattern, can be employed in radiomics analysis to make robust models in the early prediction of the response to neo-adjuvant chemotherapy in breast cancer. Therefore, this could predict treatment response early in therapy to identify women who do not benefit from cytotoxic therapy.
    Download PDF


  • Wearable biosignal acquisition system for decision aid
    Smart Biomedical and Physiological Sensor Technology XV, May 2018
    Other Authors: Victor Toral-Lopez, Salvador Criado, Francisco J Romero, Diego P Morales, Encarnación Castillo, Antonio García, Anke Meyer-Baese

    Accurate methods for breast cancer diagnosis are of capital importance for selection and guidance of treatment and optimal patient outcomes. In dynamic contrast enhancing magnetic resonance imaging (DCE-MRI), the accurate differentiation of benign and malignant breast tumors that present as non-mass enhancing (NME) lesions is challenging, often resulting in unnecessary biopsies. Here we propose a new approach for the accurate diagnosis of such lesions with high resolution DCE-MRI by taking advantage of seven robust classification methods to discriminate between malignant and benign NME lesions using their dynamic curves at the voxel level, and test it in a manually delineated dataset. The tested approaches achieve a diagnostic accuracy up to 94% accuracy, sensitivity of 99 % and specificity of 90% respectively, with superiority of high temporal compared to high spatial resolution sequences.


  • Machine learning for accurate differentiation of benign and malignant breast tumors presenting as non-mass enhancement
    Computational Imaging III, May 2018
    Other Authors: Ignacio Alvarez Illan, Javier Ramirez, Juan M Gorriz, Simon Y Foo, Katja Pinker-Domenig, Anke Mayer-Baese

    Accurate methods for breast cancer diagnosis are of capital importance for selection and guidance of treatment and optimal patient outcomes. In dynamic contrast enhancing magnetic resonance imaging (DCE-MRI), the accurate differentiation of benign and malignant breast tumors that present as non-mass enhancing (NME) lesions is challenging, often resulting in unnecessary biopsies. Here we propose a new approach for the accurate diagnosis of such lesions with high resolution DCE-MRI by taking advantage of seven robust classification methods to discriminate between malignant and benign NME lesions using their dynamic curves at the voxel level, and test it in a manually delineated dataset. The tested approaches achieve a diagnostic accuracy up to 94% accuracy, sensitivity of 99 % and specificity of 90% respectively, with superiority of high temporal compared to high spatial resolution sequences.


  • iDeepLe: Deep Learning in a Flash
    Disruptive Technologies in Information Sciences, May 2018

    Emerging as one of the most contemporary machine learning techniques, deep learning has shown success in areas such as image classification, speech recognition, and even playing games through the use of hierarchical architecture which includes many layers of non-linear information. In this paper, a powerful deep learning pipeline, intelligent deep learning (iDeepLe) is proposed for both regression and classification tasks. iDeepLe is written in Python with the help of various API libraries such as Keras, TensorFlow, and Scikit-Learn. The core idea of the pipeline is inspired by the sequential modeling with considering numerous layers of neurons to build the deep architecture. Each layer in the sequential deep model can perform independently as a module with minimum finitudes and does not limit the performance of the other layers. iDeepLe has the ability of employing grid search, random search, and Bayesian optimization to tune the most significant predictor input variables and hyper-parameters in the deep model via adaptive learning rate optimization algorithms for both accuracy and complexity, while simultaneously solving the unknown parameters of the regression or the classification model. The parallel pipeline of iDeepLe has the capacity to handle big data problems using Apache Spark, Apache Arrow, High Performance Computing (HPC) and GPU-enabled machines as well. In this paper, to show the importance of the optimization in deep learning, an exhaustive study of the impact of hyper-parameters in a simple and a deep model using optimization algorithms with adaptive learning rate was carried out.
    Download PDF


  • A scalable communication abstraction framework for internet of things applications using Raspberry Pi
    Disruptive Technologies in Information Sciences, May 2018
    Other Authors: Behshad Mohebali, Amir H Gandomi, Anke Meyer-Baese, Simon Y Foo

    The Internet of Things concept is described as a network of interconnected physical objects capable of gather, process, and communicate information about their environment, and potentially affect the physical world around them through their sensors, embedded processors, communication modules, and actuators, respectively. Such a network can provide vital information on events, processes, activities, and future projections about the state of a distributed system. In addition, it can give the devices inside the network awareness about their environment far beyond the range of their dedicated sensors through communication with other devices. In most cases, such network consists of devices with different processing and communication capacities and protocols, from a variety of hardware vendors. This paper introduces an abstracted messaging and commanding framework for smart objects, aimed towards making the network capable of including various communication standards. This issue is addressed by proposing a messaging structure based on JavaScript object notation (JSON) format so the new devices connecting to the network can introduce themselves to the central coordinator. The introduction includes a list of functionalities that the device is capable of, and the information it needs to carry out those tasks. This platform makes the network capable of incorporating different devices with various purposes and functions with ease and flexibility. Having a fast, reliable, and scalable communication scheme is critical for realization of a robust and flexible network.
    Download PDF


  • NewsAnalyticalToolkit: an online natural language processing platform to analyze news
    Next-Generation Analyst VI, April 2018
    Other Authors: Ian McCann, Simon Y Foo, Gordon Erlebacher, Anke Meyer-Baese

    In today’s increasingly divided political climate there is a need for a tool that can compare news articles and organizations so that a user can receive a wider range of views and philosophies. NewsAnalyticalToolkit allows a user to compare news sites and their political articles by coverage, mood, sentiment, and objectivity. The user can sort through the news by topic, which was determined using Natural Language Processing (NLP) and Latent Dirichlet Allocation (LDA). LDA is a probabilistic method used to discover latent topics within a series of documents and cluster them accordingly. Each news article can be considered a mix of multiple topics and LDA assigns a set of topics to each with a probability of it pertaining to that topic. For each topic, a user can then discover the coverage, mood, sentiment and objectivity expressed by each author and site. The mood was determined using IBM Watsons ToneAnalyzerV3, which uses linguistic analysis to detect emotional, social and language tones in written text. The analyzer is based on the theory of psycholinguistics, a field of research that explores the relationship between linguistic behavior and psychological theories. The sentiment and objectivity scores were determined using SentiWordNet, which is a lexical database that groups English words into sets of synonyms and assigns sentiment scores to them. The features were combined to plot an interactive graph of how opinionated versus how analytical an article is, so that the user can click through them to get a better understanding of the topic in question.
    Download PDF


  • Determining disease evolution driver nodes in dementia networks
    SPIE Medical Imaging, March 2018
    Other Authors: Ali Moradi Amani, Katja Pinker-Domenig, Anke Meyer-Baese

    Imaging connectomics emerged as an important field in modern neuroimaging to represent the interaction of structural and functional brain areas. Static graph networks are the mathematical structure to capture these interactions modeled by Pearson correlations between the representative area signals. Dynamical functional resting state networks seen in most fMRI experiments can not be represented by the classic correlation graph network. The changes in brain connectivity observed in many neuro-degenerative diseases in longitudinal data series suggest that more sophisticated graph networks to capture the dynamical properties of the brain networks are required. Furthermore, certain brain areas seem to act as ”disease epicenters” being responsible for the spread of neuro-degenerative diseases. To mathematically describe these aspects, we propose a novel framework based on pinning controllability applied to dynamic graphs and seek to determine the changes in the ”driver nodes” during the course of the disease. In contrast to other current research in pinning controllability, we aim to identify the best driver nodes describing disease evolution with respect to connectivity changes and location of the best driver nodes in functional 18F-Fluorodeoxyglucose Positron Emission Tomography (18FDG-PET) and structural Magnetic Resonance Imaging (MRI) connectivity graphs in healthy controls (CN), and patients with mild cognitive impairment (MCI), and Alzheimer’s disease (AD). We present the theoretical framework for determining the best driver nodes in connectivity graphs and their relation to disease evolution in dementia. We revolutionize the current graph analysis in brain networks and apply the concept of dynamic graph theory in connection with pinning controllability to reveal differences in the location of ”disease epicenters” that play an important role in the temporal evolution of dementia. The described research will constitute a leap in biomedical research related to novel disease prediction trajectories and precision dementia therapies.
    Download PDF


  • Building energy consumption forecast using multi-objective genetic programming
    Journal of Measurement , Elsevier, March 2018
    Other Author: Amir H. Gandomi

    A multi-objective genetic programming (MOGP) technique with multiple genes is proposed to formulate the energy performance of residential buildings. Here, it is assumed that loads have linear relation in terms of genes. On this basis, an equation is developed by MOGP method to predict both heating and cooling loads. The proposed evolutionary approach optimizes the most significant predictor input variables in the model for both accuracy and complexity, while simultaneously solving the unknown parameters of the model. In the proposed energy performance model, relative compactness has the most and orientation the least contribution. The proposed MOGP model is simple and has a high degree of accuracy. The results show that MOGP is a suitable tool to generate solid models for complex nonlinear systems with capability of solving big data problems via parallel algorithms.
    Download PDF


  • Stock Risk Assessment via Multi-Objective Genetic Programming
    Journal of Postdoctoral Research, March 2018
    Other Authors: Amir H Gandomi, Anke Meyer-Baese

    Recent exponential growth of investors in stock markets brings the idea to develop a predictive model to forecast the total risk of investment in stock markets. In this paper, an evolutionary approach was proposed to predict the total risk in stock investment based on an S&P 500 database in a time period of 1991-2010 employing a multi-objective genetic programming along with an adaptive regression by mixing algorithm. The reasonable results suggest that the proposed model can be applied to various stock databases to assess the total risk of investment. The proposed model along with stock selection decision support systems can overcome the disadvantages of weighted scoring stock selection.
    Download PDF


  • Radiomics with MRI for early prediction of the response to neo-adjuvant chemotherapy in breast cancer patients
    Insights into Imaging, Springer, February 2018
    Other Authors: Anke Meyer-Baese, Georg J. Wengert, Thomas H. Helbich, Katja Pinker-Domenig

    In patients undergoing neoadjuvant chemotherapy for breast cancer, the achievement of a pathological complete response (pCR) is associated with a significantly improved disease-free and overall survival. The aim of this study was to assess radiomics with dynamic contrast-enhanced (DCE) MRI for the early prediction of pathological complete response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy.
    Methods and Materials: In this IRB-approved prospective study, 41 women (median age 50 years; range 25-80 years) with breast cancer scheduled for NAC were included and underwent mpMRI using DCE MRI prior to and after two cycles of NAC. For each lesion a total of 14 features were extracted ranging from morphological, enhancement and ADC parameters. Recursive feature elimination method along with five different classifiers including linear support vector machine (SVM), linear discriminant analysis (LDA), logistic regression (LR), random forest (RF), and stochastic gradient descent (SGD) was employed to rank the features.
    Results: Radiomics analysis and classification accuracy of mpMRI achieved AUCs for residual cancer burden (RCB) score (AUC 0.85), metastases (AUC 0.89) based on RF and death (AUC 0.95) based on SVM. The most relevant parameters for prediction of RCB score were mass internal enhancement, shape and margins with DCE, for metastasis peritumoural oedema, mass margins and internal enhancement, and for death high signal intensity on T2- weighted imaging, mass margins, and internal enhancement.
    Conclusion: Radiomics with DCE-MRI enables prediction of response to NAC with high accuracy and thus can provide predictive information and guide treatment decisions.

    Download PDF


  • Determining leader nodes in dementia networks
    Insights into Imaging, Springer, February 2018
    Other Authors: Yasin Yazicioglu, Katja Pinker-Domenig, Anke Meyer-Baese

    Purpose: Fusing modern network theory and control strategies yields a novel transformational paradigm in dementia research. One research direction is determining the leader nodes in disease networks that can be directly manipulated via external inputs to influence the overall network trajectory and simulate the disease progression.
    Methods and Materials: We examine 249 subjects with FDG-PET and T1- weighted MRI images consisting of 68 control, 111 mild cognitive impairment (MCI) and 70 Alzheimer’s disease (AD). We consider only 42 out of the 116 from the AAL in the frontal, parietal, occipital and temporal lobes. Different from previous work on controllability of disease networks, we determine the disease leader nodes by relying only on the network's structure, particularly the graph distances between the nodes, and not on the existing connection weights.
    Results: We show that there is a common leader node in structural and functional brain networks reflecting the changes from controls over MCI to AD. For functional data, we see one leader node in the frontal lobe present in all three networks and a decreasing number of leader nodes from controls to AD. The same situation is observed for structural data with one node in the temporal lobe, however there are more nodes in common between controls/MCI and MCI/AD.
    Conclusion: We have established a new method to determine the leader nodes that can be directly manipulated to change the trajectory of the dementia networks. Implicitly, we can gain an understanding of dementia evolution and the subsequent development of therapeutic solutions.

    Download PDF


  • Genetic Programming Based on Error Decomposition: A Big Data Approach
    Book Genetic Programming Theory and Practice XV, Springer, July 2018
    Other Author: Amir H Gandomi

    An investigation of the deviations of error and correlation for different stages of the multi-stage genetic programming (MSGP) algorithm in multivariate nonlinear problems is presented. The MSGP algorithm consists of two main stages: (1) incorporating the individual effect of the predictor variables, (2) incorporating the interactions among the predictor variables. The MSGP algorithm formulates these two terms in an efficient procedure to optimize the error among the predicted and the actual values. In addition to this, the proposed pipeline of the MSGP algorithm is implemented with a combination of parallel processing algorithms to run multiple jobs at the same time. To demonstrate the capabilities of the MSGP, its performance is compared with standard GP in modeling a regression problem. The results illustrate that the MSGP algorithm outperforms standard GP in terms of accuracy, efficiency, and computational cost.


  • Optimized Naive-Bayes and Decision Tree Approaches for fMRI Smoking Cessation Classification
    Journal of Complexity, Hindawi, March 2018
    Other Authors: Amir H Gandomi, Mieke HJ Schulte, Anna E Goudriaan, Simon Y Foo, Anke Meyer-Baese

    This paper aims at developing new theory-driven biomarkers by implementing and evaluating novel techniques from resting-state scans that can be used in relapse prediction for nicotine-dependent patients and future treatment efficacy. Two classes of patients were studied. One class took the drug N-acetylcysteine and the other class took a placebo. Then, the patients underwent a double-blind smoking cessation treatment and the resting-state fMRI scans of their brains before and after treatment were recorded. The scientific research goal of this study was to interpret the fMRI connectivity maps based on machine learning algorithms to predict the patient who will relapse and the one who will not. In this regard, the feature matrix was extracted from the image slices of brain employing voxel selection schemes and data reduction algorithms. Then, the feature matrix was fed into the machine learning classifiers including optimized CART decision tree and Naive-Bayes classifier with standard and optimized implementation employing 10-fold cross-validation. Out of all the data reduction techniques and the machine learning algorithms employed, the best accuracy was obtained using the singular value decomposition along with the optimized Naive-Bayes classifier. This gave an accuracy of 93% with sensitivity-specificity of 99% which suggests that the relapse in nicotine-dependent patients can be predicted based on the resting-state fMRI images. The use of these approaches may result in clinical applications in the future.
    Download PDF


  • Determining the importance of parameters extracted from multi-parametric MRI in the early prediction of the response to neo-adjuvant chemotherapy in breast cancer
    Proc. SPIE Volume 10578, Medical Imaging, March 2018
    Other Authors: Katja Pinker-Domenig, Georg Wengert, Thomas Helbich, Zsuzsanna Bago-Horvath, Anke Meyer-Baese

    Neo-adjuvant chemotherapy (NAC) is the treatment of choice in patients with locally advanced breast cancer to reduce tumor burden, and potentially enable breast conservation. Response to treatment is assessed by histopathology from surgical specimen, a pathological complete response (pCR), or a minimal residual disease are associated with an improved disease-free, and overall survival. Early identification of non-responders is crucial as these patients might require different, or more aggressive treatment. Multi-parametric magnetic resonance imaging (mpMRI) using different morphological and functional MRI parameters such as T2-weighted, dynamic contrast-enhanced (DCE) MRI, and diffusion weighted imaging (DWI) has emerged as the method of choice for the early response assessments to NAC. Although, mpMRI is superior to conventional mammography for predicting treatment response, and evaluating residual disease, yet there is still room for improvement. In the past decade, the field of medical imaging analysis has grown exponentially, with an increased numbers of pattern recognition tools, and an increase in data sizes. These advances have heralded the field of radiomics. Radiomics allows the high-throughput extraction of the quantitative features that result in the conversion of images into mineable data, and the subsequent analysis of the data for an improved decision support with response monitoring during NAC being no exception. In this paper, we determine the importance and ranking of the extracted parameters from mpMRI using T2-weighted, DCE, and DWI for prediction of pCR and patient outcomes with respect to metastases and disease-specific death.
    Download PDF


  • High Performance GP-Based Approach for fMRI Big Data Classification
    Proceedings of the Practice and Experience in Advanced Research Computing [PEARC17] , ACM, July 2017
    Other Authors: Amir H. Gandomi, Anke Meyer-Baese

    We consider resting-state Functional Magnetic Resonance Imaging (fMRI) of two classes of patients: one that took the drug N-acetylcysteine (NAC) and the other one a placebo before and after a smoking cessation treatment. Our goal was to classify the relapse in nicotine-dependent patients as treatment or non-treatment based on their fMRI scans. 80% accuracy was obtained using Independent Component Analysis (ICA) along with Genetic Programming (GP) classifier using High Performance Computing (HPC) which we consider significant enough to suggest that there is a difference in the resting-state fMRI images of a smoker that undergoes this smoking cessation treatment compared to a smoker that receives a placebo.
    Download PDF


  • fMRI Smoking Cessation Classification Using Genetic Programming
    Data Science meets Optimization (DSO), May 2017
    Other Authors: Amir H. Gandomi, Ian McCaan, Anneke Goudriaan, Lianne Schmaal, Anke Meyer-Baese

    Resting-state functional magnetic resonance imaging (fMRI) images allow us to see the level of activity in a patient's brain. We consider fMRI of patients before and after they underwent a smoking cessation treatment. Two classes of patients have been studied here, that one took the drug N-acetylcysteine and the ones took a placebo. Our goal was to classify the relapse in nicotine-dependent patients as treatment or non-treatment based on their fMRI scans. The image slices of brain are used as the variable and as results here we deal with a big data problem with about 240,000 inputs. To handle this problem, the data had to be reduced and the first process in doing that was to create a mask to apply to all images. The mask was created by averaging the before images for all patients and selecting the top 40% of voxels from that average. This mask was then applied to all fMRI images for all patients. The average of the difference in the before treatment and after fMRI images for each patient were found and these were flattened to one dimension. Then a matrix was made by stacking these 1D arrays on top of each other and a data reduction algorithm was applied on it. Lastly, this matrix was fed into some machine learning and Genetic Programming algorithms and leave-one-out cross-validation was used to test the accuracy. Out of all the data reduction machine learning algorithms used, the best accuracy was obtained using Principal Component Analysis along with Genetic Programming classifier. This gave an accuracy of 74%, which we consider significant enough to suggest that there is a difference in the resting-state fMRI images of a smoker that undergoes this smoking cessation treatment compared to a smoker that receives a placebo.


  • Reconfigurable wearable to monitor physiological variables and movement
    Proc. SPIE Vol. 10216, Smart Biomedical and Physiological Sensor Technology XIV, April 2017
    Other Authors: Antonio Garcia, Diego Morales, Anke Meyer-Baese

    This article presents a preliminary prototype of a wearable instrument for oxygen saturation and ECG monitoring. The proposed measuring system is based on the light reflection variability of a LED emission on the subject temple. Besides, the system has the capacity to incorporate electrodes to obtain ECG measurements. All measurements are stored and transmitted to a mobile device (tablet or smartphone) through a Bluetooth link.
    Download PDF


  • Dynamical graph theory networks techniques for the analysis of sparse connectivity networks in dementia
    Proc. SPIE Vol. 10216, Smart Biomedical and Physiological Sensor Technology XIV, April 2017
    Other Authors: Katja Pinker, Anke Meyer-Baese

    Graph network models in dementia have become an important computational technique in neuroscience to study fundamental organizational principles of brain structure and function of neurodegenerative diseases such as dementia. The graph connectivity is reflected in the connectome, the complete set of structural and functional connections of the graph network, which is mostly based on simple Pearson correlation links. In contrast to simple Pearson correlation networks, the partial correlations (PC) only identify direct correlations while indirect associations are eliminated. In addition to this, the state-of-the-art techniques in brain research are based on static graph theory, which is unable to capture the dynamic behavior of the brain connectivity, as it alters with disease evolution. We propose a new research avenue in neuroimaging connectomics based on combining dynamic graph network theory and modeling strategies at different time scales. We present the theoretical framework for area aggregation and time-scale modeling in brain networks as they pertain to disease evolution in dementia. This novel paradigm is extremely powerful, since we can derive both static parameters pertaining to node and area parameters, as well as dynamic parameters, such as system’s eigenvalues. By implementing and analyzing dynamically both disease driven PC-networks and regular concentration networks, we reveal differences in the structure of these network that play an important role in the temporal evolution of this disease. The described research is key to advance biomedical research on novel disease prediction trajectories and dementia therapies.


  • The driving regulators of the connectivity protein network of brain malignancies
    Proc. SPIE Vol. 10216, Smart Biomedical and Physiological Sensor Technology XIV, April 2017
    Other Authors: Katja Pinker, Anke Meyer-Baese

    An important problem in modern therapeutics at the proteomic level remains to identify therapeutic targets in a plentitude of high-throughput data from experiments relevant to a variety of diseases. This paper presents the application of novel modern control concepts, such as pinning controllability and observability applied to the glioma cancer stem cells (GSCs) protein graph network with known and novel association to glioblastoma (GBM). The theoretical frameworks provides us with the minimal number of "driver nodes", which are necessary, and their location to determine the full control over the obtained graph network in order to provide a change in the network’s dynamics from an initial state (disease) to a desired state (non-disease). The achieved results will provide biochemists with techniques to identify more metabolic regions and biological pathways for complex diseases, to design and test novel therapeutic solutions.


  • Characteristics of Nano-Structures
    SciComp Conference, August 2016

    As a final project of the Scientific Communications class, a Poster plus ten minutes talk under supervision of Dr. John Burkardt has been preseneted.


  • Modeling the Zombie Apocalypse
    XSEDE Competition, July 2016
    Other Team Members: Brian Bartoldson, Eitan Lees, Alex Townsend, Ian McCann

    We simulated a model for the zombie apocalypse on an island where humans can meet zombies and interact by being bitten and becoming a zombie, being killed, or killing the zombie.


  • Pharmecokinetic Model of Drug Dosage and Concentrations
    XSEDE Competition, April 2016
    Other Team Members: Brian Bartoldson, Eitan Lees, Alex Townsend, Ian McCann

    In order to be effective, the concentration of a drug in the bloodstream needs to reach a medicinal level. Below this level, the drug will be ineffective. For some drugs, there is also the limitation that above some concentration level they become toxic. Thus, it is critical to vary the dosage such that the steady state concentration is between the effective and toxic dose. We have coded the aforementioned model of drug dosage and concentrations in Python. That was for XSEDE 2016 competition at Florida State University.


  • Fluid Flow Through Carbon Nanotubes And Graphene Based Nanostructures
    OhioLINK ETD, August 2015

    Abstract: The investigation into the behavior of the fluids in nanoscale channels, such as carbon nanotubes leads us to a new approach in the field of nanoscience. This is referred to as nano-fluidics, which can be used in nano-scale filtering and as nano-pipes for conveying fluids. The behavior of fluids in nano-fluidic devices is very different from the corresponding behavior in microscopic and macroscopic channels. In this study, we investigate the fluid flow through carbon nanotubes and graphene based nanostructures using a molecular dynamics (MD) method at a constant temperature.Three different models were created which contain single-walled carbon nanotube, graphene, and a combination of both. Liquid argon is used as fluid in the system. In the previous investigations, they were considered bombarding the atoms towards the carbon nanotubes like bullets from a gun, and due to the interactions, they lost most of their momentum. Thus, the chance for the atoms to pass through the carbon nanotube was very low. Here, we employed a new approach using a moving graphene wall to push the argon fluid towards the confinements of the systems. By performing this method, we have tried to make a continuum flow to find out how the physical quantities such as, position, velocity, pressure, and energy change when the fluid flow reaches the confinements of the systems.