Browsing by Author "Tuceryan, Mihran"
Now showing 1 - 10 of 77
Results Per Page
Sort Options
Item Active geometric model : multi-compartment model-based segmentation & registration(2014-08-26) Mukherjee, Prateep; Tsechpenakis, Gavriil; Raje, Rajeev; Tuceryan, MihranWe present a novel, variational and statistical approach for model-based segmentation. Our model generalizes the Chan-Vese model, proposed for concurrent segmentation of multiple objects embedded in the same image domain. We also propose a novel shape descriptor, namely the Multi-Compartment Distance Functions or mcdf. Our proposed framework for segmentation is two-fold: first, several training samples distributed across various classes are registered onto a common frame of reference; then, we use a variational method similar to Active Shape Models (or ASMs) to generate an average shape model and hence use the latter to partition new images. The key advantages of such a framework is: (i) landmark-free automated shape training; (ii) strict shape constrained model to fit test data. Our model can naturally deal with shapes of arbitrary dimension and topology(closed/open curves). We term our model Active Geometric Model, since it focuses on segmentation of geometric shapes. We demonstrate the power of the proposed framework in two important medical applications: one for morphology estimation of 3D Motor Neuron compartments, another for thickness estimation of Henle's Fiber Layer in the retina. We also compare the qualitative and quantitative performance of our method with that of several other state-of-the-art segmentation methods.Item Adversarial autoencoders for anomalous event detection in images(2017) Dimokranitou, Asimenia; Tsechpenakis, Gavriil; Zheng, Jiang Yu; Tuceryan, MihranDetection of anomalous events in image sequences is a problem in computer vision with various applications, such as public security, health monitoring and intrusion detection. Despite the various applications, anomaly detection remains an ill-defined problem. Several definitions exist, the most commonly used defines an anomaly as a low probability event. Anomaly detection is a challenging problem mainly because of the lack of abnormal observations in the data. Thus, usually it is considered an unsupervised learning problem. Our approach is based on autoencoders in combination with Generative Adversarial Networks. The method is called Adversarial Autoencoders [1], and it is a probabilistic autoencoder, that attempts to match the aggregated posterior of the hidden code vector of the autoencoder, with an arbitrary prior distribution. The adversarial error of the learned autoencoder is low for regular events and high for irregular events. We compare our approach with state of the art methods and describe our results with respect to accuracy and efficiency.Item Augmented Reality-Assisted Deep Reinforcement Learning-Based Model towards Industrial Training and Maintenance for NanoDrop Spectrophotometer(MDPI, 2023-06-29) Alatawi, Hibah; Albalawi, Nouf; Shahata, Ghadah; Aljohani, Khulud; Alhakamy, A’aeshah; Tuceryan, Mihran; Computer and Information Science, School of ScienceThe use of augmented reality (AR) technology is growing in the maintenance industry because it can improve efficiency and reduce costs by providing real-time guidance and instruction to workers during repairs and maintenance tasks. AR can also assist with equipment training and visualization, allowing users to explore the equipment’s internal structure and size. The adoption of AR in maintenance is expected to increase as hardware options expand and development costs decrease. To implement AR for job aids in mobile applications, 3D spatial information and equipment details must be addressed, and calibrated using image-based or object-based tracking, which is essential for integrating 3D models with physical components. The present paper suggests a system using AR-assisted deep reinforcement learning (RL)-based model for NanoDrop Spectrophotometer training and maintenance purposes that can be used for rapid repair procedures in the Industry 4.0 (I4.0) setting. The system uses a camera to detect the target asset via feature matching, tracking techniques, and 3D modeling. Once the detection is completed, AR technologies generate clear and easily understandable instructions for the maintenance operator’s device. According to the research findings, the model’s target technique resulted in a mean reward of 1.000 and a standard deviation of 0.000. This means that all the rewards that were obtained in the given task or environment were exactly the same. The fact that the reward standard deviation is 0.000 shows that there is no variability in the outcomes.Item Automated assessment of steatosis in murine fatty liver(PLOS, 2018-05-10) Sethunath, Deepak; Morusu, Siripriya; Tuceryan, Mihran; Cummings, Oscar W.; Zhang, Hao; Yin, Xiao-Ming; Vanderbeck, Scott; Chalasani, Naga; Gawrieh, Samer; Computer and Information Science, School of ScienceAlthough mice are commonly used to study different aspects of fatty liver disease, currently there are no validated fully automated methods to assess steatosis in mice. Accurate detection of macro- and microsteatosis in murine models of fatty liver disease is important in studying disease pathogenesis and detecting potential hepatotoxic signature during drug development. Further, precise quantification of macrosteatosis is essential for quantifying effects of therapies. Here, we develop and validate the performance of automated classifiers built using image processing and machine learning methods for detection of macro- and microsteatosis in murine fatty liver disease and study the correlation of automated quantification of macrosteatosis with expert pathologist’s semi-quantitative grades. The analysis is performed on digital images of 27 Hematoxylin & Eosin stained murine liver biopsy samples. An expert liver pathologist scored the amount of macrosteatosis and also annotated macro- and microsteatosis lesions on the biopsy images using a web-application. Using these annotations, supervised machine learning and image processing techniques, we created classifiers to detect macro- and microsteatosis. For macrosteatosis prediction, the model’s precision, sensitivity and area under the receiver operator characteristic (AUROC) were 94.2%, 95%, 99.1% respectively. When correlated with pathologist’s semi-quantitative grade of steatosis, the model fits with a coefficient of determination value of 0.905. For microsteatosis prediction, the model has precision, sensitivity and AUROC of 79.2%, 77%, 78.1% respectively. Validation by the expert pathologist of classifier’s predictions made on unseen images of biopsy samples showed 100% and 63% accuracy for macro- and microsteatosis, respectively. This novel work demonstrates that fully automated assessment of steatosis is feasible in murine liver biopsies images. Our classifier has excellent sensitivity and accuracy for detection of macrosteatosis in murine fatty liver disease.Item Automated Computer-Based Enumeration of Acellular Capillaries for Assessment of Diabetic Retinopathy(SPIE, 2020-02) Tuceryan, Mihran; Hemmady, Anish N.; Schebler, Craig; Alex, Alpha; Bhatwadekar, Ashay D.; Computer and Information Science, School of ScienceDiabetic retinopathy (DR) is the most common complications of diabetes; if untreated the DR can lead to a vision loss. The treatment options for DR are limited and the development of newer therapies are of considerable interest. Drug screening for the retinopathy treatment is undertaken using animal models in which the quantification of acellular capillaries (capillary without any cells) is used as a marker to assess the severity of retinopathy and the treatment response. The traditional approach to quantitate acellular capillaries is through manual counting. The purpose of this investigation was to develop an automated technique for the quantitation of acellular capillaries using computer-based image processing algorithms. We developed a custom procedure using the Python, the medial axis transform (MAT) and the connected component algorithm. The program was tested on the retinas of wild-type and diabetic mice and the results were compared to single blind manual counts by two independent investigators. The program successfully identified and enumerated acellular capillaries. The acellular capillary counts were comparable to the traditional manual counting. In conclusion, we developed an automated computer-based program, which can be effectively used for future pharmacological development of treatments for DR. This algorithm will enhance consistency in retinopathy assessment and reduce the time for analysis, thus, contributing substantially towards the development of future pharmacological agents for the treatment of DR.Item Automated Methods To Detect And Quantify Histological Features In Liver Biopsy Images To Aid In The Diagnosis Of Non-Alcoholic Fatty Liver Disease(2016-03-31) Morusu, Siripriya; Tuceryan, Mihran; Zheng, Jiang; Tsechpenakis, Gavriil; Fang, ShiaofenThe ultimate goal of this study is to build a decision support system to aid the pathologists in diagnosing Non-Alcoholic Fatty Liver Disease (NAFLD) in both adults and children. The disease is caused by accumulation of excess fat in liver cells. It is prevalent in approximately 30% of the general population in United States, Europe and Asian countries. The growing prevalence of the disease is directly related to the obesity epidemic in developed countries. We built computational methods to detect and quantify the histological features of a liver biopsy which aid in staging and phenotyping NAFLD. Image processing and supervised machine learning techniques are predominantly used to develop a robust and reliable system. The contributions of this study include development of a rich web interface for acquiring annotated data from expert pathologists, identifying and quantifying macrosteatosis in rodent liver biopsies as well as lobular inflammation and portal inflammation in human liver biopsies. Our work on detection of macrosteatosis in mouse liver shows 94.2% precision and 95% sensitivity. The model developed for lobular inflammation detection performs with precision and sensitivity of 79.3% and 81.3% respectively. We also present the first study on portal inflammation identification with 82.1% precision and 88.3% sensitivity. The thesis also presents results obtained for correlation between model computed scores for each of these lesions and expert pathologists' grades.Item Brain Connectome Network Properties Visualization(2018-12) Zhang, Chenfeng; Fang, Shiaofen; Tuceryan, Mihran; Mukhopadhyay, SnehasisBrain connectome network visualization could help the neurologists inspect the brain structure easily and quickly. In the thesis, the model of the brain connectome network is visualized in both three dimensions (3D) environment and two dimensions (2D) environment. One is named “Brain Explorer for Connectomic Analysis” (BECA) developed by the previous research already. It could present the 3D model of brain structure with region of interests (ROIs) in different colors [5]. The other is mainly for the information visualization of brain connectome in 2D. It adopts the force-directed layout to visualize the network. However, the brain network visualization could not bring the user intuitively ideas about brain structure. Sometimes, with the increasing scales of ROIs (nodes), the visualization would bring more visual clutter for readers [3]. So, brain connectome network properties visualization becomes a useful complement to brain network visualization. For a better understanding of the effect of Alzheimer’s disease on the brain nerves, the thesis introduces several methods about the brain graph properties visualization. There are the five selected graph properties discussed in the thesis. The degree and closeness are node properties. The shortest path, maximum flow, and clique are edge properties. Except for clique, the other properties are visualized in both 3D and 2D. The clique is visualized only in 2D. For the clique, a new hypergraph visualization method is proposed with three different algorithms. Instead of using an extra node to present a clique, the thesis uses a “belt” to connect all nodes within the same clique. The methods of node connections are based on the traveling salesman problem (TSP) and Law of cosines. In addition, the thesis also applies the result of the clique to adjust the force-directed layout of brain graph in 2D to dramatically eliminate the visual clutter. Therefore, with the support of the graph properties visualization, the brain connectome network visualization tools become more flexible.Item A Collaborative Augmented Reality Framework Based on Distributed Visual Slam(IEEE, 2017-09) Egodagamage, Ruwan; Tuceryan, Mihran; Computer and Information Science, School of ScienceVisual Simultaneous Localization and Mapping (SLAM) has been used for markerless tracking in augmented reality applications. Distributed SLAM helps multiple agents to collaboratively explore and build a global map of the environment while estimating their locations in it. One of the main challenges in Distributed SLAM is to identify local map overlaps of these agents, especially when their initial relative positions are not known. We developed a collaborative AR framework with freely moving agents having no knowledge of their initial relative positions. Each agent in our framework uses a camera as the only input device for its SLAM process. Furthermore, the framework identifies map overlaps of agents using an appearance-based method.Item A Compressed Data Collection System For Use In Wireless Sensor Networks(2013-03-06) Erratt, Newlyn S.; Liang, Yao; Raje, Rajeev; Tuceryan, MihranOne of the most common goals of a wireless sensor network is to collect sensor data. The goal of this thesis is to provide an easy to use and energy-e fficient system for deploying data collection sensor networks. There are numerous challenges associated with deploying a wireless sensor network for collection of sensor data; among these challenges are reducing energy consumption and the fact that users interested in collecting data may not be familiar with software design. This thesis presents a complete system, comprised of the Compression Data-stream Protocol and a general gateway for data collection in wireless sensor networks, which attempts to provide an easy to use, energy efficient and complete system for data collection in sensor networks. The Compressed Data-stream Protocol is a transport layer compression protocol with a primary goal, in this work, to reduce energy consumption. Energy consumption of the radio in wireless sensor network nodes is expensive and the Com-pressed Data-stream Protocol has been shown in simulations to reduce energy used on transmission and reception by around 26%. The general gateway has been designed in such a way as to make customization simple without requiring vast knowledge of sensor networks and software development. This, along with the modular nature of the Compressed Data-stream Protocol, enables the creation of an easy to deploy and easy to configure sensor network for data collection. Findings show that individual components work well and that the system as a whole performs without errors. This system, the components of which will eventually be released as open source, provides a platform for researchers purely interested in the data gathered to deploy a sensor network without being restricted to specific vendors of hardware.Item Computational Analysis of Flow Cytometry Data(2013-07-12) Irvine, Allison W.; Dundar, Murat; Tuceryan, Mihran; Mukhopadhyay, Snehasis; Fang, ShiaofenThe objective of this thesis is to compare automated methods for performing analysis of flow cytometry data. Flow cytometry is an important and efficient tool for analyzing the characteristics of cells. It is used in several fields, including immunology, pathology, marine biology, and molecular biology. Flow cytometry measures light scatter from cells and fluorescent emission from dyes which are attached to cells. There are two main tasks that must be performed. The first is the adjustment of measured fluorescence from the cells to correct for the overlap of the spectra of the fluorescent markers used to characterize a cell’s chemical characteristics. The second is to use the amount of markers present in each cell to identify its phenotype. Several methods are compared to perform these tasks. The Unconstrained Least Squares, Orthogonal Subspace Projection, Fully Constrained Least Squares and Fully Constrained One Norm methods are used to perform compensation and compared. The fully constrained least squares method of compensation gives the overall best results in terms of accuracy and running time. Spectral Clustering, Gaussian Mixture Modeling, Naive Bayes classification, Support Vector Machine and Expectation Maximization using a gaussian mixture model are used to classify cells based on the amounts of dyes present in each cell. The generative models created by the Naive Bayes and Gaussian mixture modeling methods performed classification of cells most accurately. These supervised methods may be the most useful when online classification is necessary, such as in cell sorting applications of flow cytometers. Unsupervised methods may be used to completely replace manual analysis when no training data is given. Expectation Maximization combined with a cluster merging post-processing step gives the best results of the unsupervised methods considered.