Knowledge Modeling for The Outcome of Brain Stereotactic Radiosurgery

Purpose: To build a model that will predict the survival time for patients that were treated with stereotactic radiosurgery for brain metastases using support vector machine (SVM) regression.

Methods and Materials: This study utilized data from 481 patients, which were equally divided into training and validation datasets randomly. The SVM model used a Gaussian RBF function, along with various parameters, such as the size of the epsilon insensitive region and the cost parameter (C) that are used to control the amount of error tolerated by the model. The predictor variables for the SVM model consisted of the actual survival time of the patient, the number of brain metastases, the graded prognostic assessment (GPA) and Karnofsky Performance Scale (KPS) scores, prescription dose, and the largest planning target volume (PTV). The response of the model is the survival time of the patient. The resulting survival time predictions were analyzed against the actual survival times by single parameter classification and two-parameter classification. The predicted mean survival times within each classification were compared with the actual values to obtain the confidence interval associated with the model’s predictions. In addition to visualizing the data on plots using the means and error bars, the correlation coefficients between the actual and predicted means of the survival times were calculated during each step of the classification.

Results: The number of metastases and KPS scores, were consistently shown to be the strongest predictors in the single parameter classification, and were subsequently used as first classifiers in the two-parameter classification. When the survival times were analyzed with the number of metastases as the first classifier, the best correlation was obtained for patients with 3 metastases, while patients with 4 or 5 metastases had significantly worse results. When the KPS score was used as the first classifier, patients with a KPS score of 60 and 90/100 had similar strong correlation results. These mixed results are likely due to the limited data available for patients with more than 3 metastases or KPS scores of 60 or less.

Conclusions: The number of metastases and the KPS score both showed to be strong predictors of patient survival time. The model was less accurate for patients with more metastases and certain KPS scores due to the lack of training data.

Statistical methods for polyhedral shape classification with incomplete data - application to cryo-electron tomographic images

A certain type of bacterial inclusion, known as a bacterial microcompartment, was recently identified and imaged through cryo-electron tomography. A reconstructed 3D object from single-axis limited angle tilt-series cryo-electron tomography contains missing regions and this problem is known as the missing wedge problem. Due to missing regions on the reconstructed images, analyzing their 3D structures is a challenging problem. The existing methods overcome this problem by aligning and averaging several similar shaped objects. These schemes work well if the objects are symmetric and several objects with almost similar shapes and sizes are available. Since the bacterial inclusions studied here are not symmetric, are deformed, and show a wide range of shapes and sizes, the existing approaches are not appropriate. This research develops new statistical methods for analyzing geometric properties, such as volume, symmetry, aspect ratio, polyhedral structures etc., of these bacterial inclusions in presence of missing data. These methods work with deformed and non-symmetric varied shaped objects and do not necessitate multiple objects for handling the missing wedge problem. The developed methods and contributions include: (a) an improved method for manual image segmentation, (b) a new approach to 'complete' the segmented and reconstructed incomplete 3D images, (c) a polyhedral structural distance model to predict the polyhedral shapes of these microstructures, (d) a new shape descriptor for polyhedral shapes, named as polyhedron profile statistic, and (e) the Bayes classifier, linear discriminant analysis and support vector machine based classifiers for supervised incomplete polyhedral shape classification. Finally, the predicted 3D shapes for these bacterial microstructures belong to the Johnson solids family, and these shapes along with their other geometric properties are important for better understanding of their chemical and biological characteristics.

MicroRNA expression and function in neonatal hypoxic ischaemic encephalopathy

Hypoxic ischaemic encephalopathy (HIE) is a devastating neonatal condition which affects 2-3 per 1000 infants annually. The current gold standard of treatment - induced hypothermia, has the ability to reduce neonatal mortality and improve neonatal morbidity. However, to be effective it needs to be initiated within the therapeutic window which exists following initial insult until approximately 6 hours after birth. Current methods of assessment which are relied upon to identify infants with HIE are subjective and unreliable. To overcome this issue, an early and reliable biomarker of HIE severity must be identified. MicroRNA (miRNA) are a class of small non-coding RNA molecules which have potential as biomarkers of disease state and potential therapeutic targets. These tiny molecules can modulate gene expression by inhibiting translation of messenger RNA (mRNA) and as a result, can regulate protein synthesis. These miRNA are understood to be released into the circulation during cellular stress, where they are highly stable and relatively easy to quantify. Therefore, these miRNAs may be ideal candidates for biomarkers of HIE severity and may aid in directing the clinical management of these infants. By using both transcriptomic and proteomic approaches to analyse the expression of miRNAs and their potential targets in the umbilical cord blood, I have confirmed that infants with perinatal asphyxia and HIE have a significantly different UCB miRNA signature compared to UCB samples from healthy controls. Finally, I have identified and investigated 2 individual miRNAs; both of which show some potential as classifiers of HIE severity and predictors of long term outcome, particularly when coupled with their downstream targets. While this work will need to be validated and expanded in a new and larger cohort of infants, it suggests the potential of miRNA as biomarkers of neonatal pathological conditions such as HIE.

An Exploration of the challenges associated with software logging in large systems

Over the past few years, logging has evolved from from simple printf statements to more complex and widely used logging libraries. Today logging information is used to support various development activities such as fixing bugs, analyzing the results of load tests, monitoring performance and transferring knowledge. Recent research has examined how to improve logging practices by informing developers what to log and where to log. Furthermore, the strong dependence on logging has led to the development of logging libraries that have reduced the intricacies of logging, which has resulted in an abundance of log information. Two recent challenges have emerged as modern software systems start to treat logging as a core aspect of their software. In particular, 1) infrastructural challenges have emerged due to the plethora of logging libraries available today and 2) processing challenges have emerged due to the large number of log processing tools that ingest logs and produce useful information from them. In this thesis, we explore these two challenges. We first explore the infrastructural challenges that arise due to the plethora of logging libraries available today. As systems evolve, their logging infrastructure has to evolve (commonly this is done by migrating to new logging libraries). We explore logging library migrations within Apache Software Foundation (ASF) projects. We i find that close to 14% of the pro jects within the ASF migrate their logging libraries at least once. For processing challenges, we explore the different factors which can affect the likelihood of a logging statement changing in the future in four open source systems namely ActiveMQ, Camel, Cloudstack and Liferay. Such changes are likely to negatively impact the log processing tools that must be updated to accommodate such changes. We find that 20%-45% of the logging statements within the four systems are changed at least once. We construct random forest classifiers and Cox models to determine the likelihood of both just-introduced and long-lived logging statements changing in the future. We find that file ownership, developer experience, log density and SLOC are important factors in determining the stability of logging statements.

Computational Methods for Identifying Hypertrophic Cardiomyopathy using 12-lead ECG

Hypertrophic cardiomyopathy (HCM) is a cardiovascular disease where the heart muscle is partially thickened and blood flow is - potentially fatally - obstructed. It is one of the leading causes of sudden cardiac death in young people. Electrocardiography (ECG) and Echocardiography (Echo) are the standard tests for identifying HCM and other cardiac abnormalities. The American Heart Association has recommended using a pre-participation questionnaire for young athletes instead of ECG or Echo tests due to considerations of cost and time involved in interpreting the results of these tests by an expert cardiologist. Initially we set out to develop a classifier for automated prediction of young athletes’ heart conditions based on the answers to the questionnaire. Classification results and further in-depth analysis using computational and statistical methods indicated significant shortcomings of the questionnaire in predicting cardiac abnormalities. Automated methods for analyzing ECG signals can help reduce cost and save time in the pre-participation screening process by detecting HCM and other cardiac abnormalities. Therefore, the main goal of this dissertation work is to identify HCM through computational analysis of 12-lead ECG. ECG signals recorded on one or two leads have been analyzed in the past for classifying individual heartbeats into different types of arrhythmia as annotated primarily in the MIT-BIH database. In contrast, we classify complete sequences of 12-lead ECGs to assign patients into two groups: HCM vs. non-HCM. The challenges and issues we address include missing ECG waves in one or more leads and the dimensionality of a large feature-set. We address these by proposing imputation and feature-selection methods. We develop heartbeat-classifiers by employing Random Forests and Support Vector Machines, and propose a method to classify full 12-lead ECGs based on the proportion of heartbeats classified as HCM. The results from our experiments show that the classifiers developed using our methods perform well in identifying HCM. Thus the two contributions of this thesis are the utilization of computational and statistical methods for discovering shortcomings in a current screening procedure and the development of methods to identify HCM through computational analysis of 12-lead ECG signals.

Machine learning classification of surgical pathology reports and chunk recognition for information extraction noise reduction

Background and aims: Machine learning techniques for the text mining of cancer-related clinical documents have not been sufficiently explored. Here some techniques are presented for the pre-processing of free-text breast cancer pathology reports, with the aim of facilitating the extraction of information relevant to cancer staging.

Materials and methods: The first technique was implemented using the freely available software RapidMiner to classify the reports according to their general layout: ‘semi-structured’ and ‘unstructured’. The second technique was developed using the open source language engineering framework GATE and aimed at the prediction of chunks of the report text containing information pertaining to the cancer morphology, the tumour size, its hormone receptor status and the number of positive nodes. The classifiers were trained and tested respectively on sets of 635 and 163 manually classified or annotated reports, from the Northern Ireland Cancer Registry.

Results: The best result of 99.4% accuracy – which included only one semi-structured report predicted as unstructured – was produced by the layout classifier with the k nearest algorithm, using the binary term occurrence word vector type with stopword filter and pruning. For chunk recognition, the best results were found using the PAUM algorithm with the same parameters for all cases, except for the prediction of chunks containing cancer morphology. For semi-structured reports the performance ranged from 0.97 to 0.94 and from 0.92 to 0.83 in precision and recall, while for unstructured reports performance ranged from 0.91 to 0.64 and from 0.68 to 0.41 in precision and recall. Poor results were found when the classifier was trained on semi-structured reports but tested on unstructured.

Conclusions: These results show that it is possible and beneficial to predict the layout of reports and that the accuracy of prediction of which segments of a report may contain certain information is sensitive to the report layout and the type of information sought.

Joint Analysis of Multiple Algorithms and Performance Measures

There has been an increasing interest in the development of new methods using Pareto optimality to deal with multi-objective criteria (for example, accuracy and time complexity). Once one has developed an approach to a problem of interest, the problem is then how to compare it with the state of art. In machine learning, algorithms are typically evaluated by comparing their performance on different data sets by means of statistical tests. Standard tests used for this purpose are able to consider jointly neither performance measures nor multiple competitors at once. The aim of this paper is to resolve these issues by developing statistical procedures that are able to account for multiple competing measures at the same time and to compare multiple algorithms altogether. In particular, we develop two tests: a frequentist procedure based on the generalized likelihood-ratio test and a Bayesian procedure based on a multinomial-Dirichlet conjugate model. We further extend them by discovering conditional independences among measures to reduce the number of parameters of such models, as usually the number of studied cases is very reduced in such comparisons. Data from a comparison among general purpose classifiers is used to show a practical application of our tests.

Fast classification in incrementally growing spaces

[EN]The classification speed of state-of-the-art classifiers such as SVM is an important aspect to be considered for emerging applications and domains such as data mining and human-computer interaction. Usually, a test-time speed increase in SVMs is achieved by somehow reducing the number of support vectors, which allows a faster evaluation of the decision function. In this paper a novel approach is described for fast classification in a PCA+SVM scenario. In the proposed approach, classification of an unseen sample is performed incrementally in increasingly larger feature spaces. As soon as the classification confidence is above a threshold the process stops and the class label is retrieved...

The High-Redshift Quasar Luminosity Function from Multi-Epoch Imaging Surveys

Thesis (Ph.D.)--University of Washington, 2016-08

Multiclass Adaboost Based on an Ensemble of Binary Adaboosts

This paper presents a multi-class AdaBoost based on incorporating an ensemble of binary AdaBoosts which is organized as Binary Decision Tree (BDT). It is proved that binary AdaBoost is extremely successful in producing accurate classification but it does not perform very well for multi-class problems. To avoid this performance degradation, the multi-class problem is divided into a number of binary problems and binary AdaBoost classifiers are invoked to solve these classification problems. This approach is tested with a dataset consisting of 6500 binary images of traffic signs. Haar-like features of these images are computed and the multi-class AdaBoost classifier is invoked to classify them. A classification rate of 96.7% and 95.7% is achieved for the traffic sign boarders and pictograms, respectively. The proposed approach is also evaluated using a number of standard datasets such as Iris, Wine, Yeast, etc. The performance of the proposed BDT classifier is quite high as compared with the state of the art and it converges very fast to a solution which indicates it as a reliable classifier.

IntelliChair: a non-intrusive sitting posture and sitting activity recognition system

Current Ambient Intelligence and Intelligent Environment research focuses on the interpretation of a subject’s behaviour at the activity level by logging the Activity of Daily Living (ADL) such as eating, cooking, etc. In general, the sensors employed (e.g. PIR sensors, contact sensors) provide low resolution information. Meanwhile, the expansion of ubiquitous computing allows researchers to gather additional information from different types of sensor which is possible to improve activity analysis. Based on the previous research about sitting posture detection, this research attempts to further analyses human sitting activity. The aim of this research is to use non-intrusive low cost pressure sensor embedded chair system to recognize a subject’s activity by using their detected postures. There are three steps for this research, the first step is to find a hardware solution for low cost sitting posture detection, second step is to find a suitable strategy of sitting posture detection and the last step is to correlate the time-ordered sitting posture sequences with sitting activity. The author initiated a prototype type of sensing system called IntelliChair for sitting posture detection. Two experiments are proceeded in order to determine the hardware architecture of IntelliChair system. The prototype looks at the sensor selection and integration of various sensor and indicates the best for a low cost, non-intrusive system. Subsequently, this research implements signal process theory to explore the frequency feature of sitting posture, for the purpose of determining a suitable sampling rate for IntelliChair system. For second and third step, ten subjects are recruited for the sitting posture data and sitting activity data collection. The former dataset is collected byasking subjects to perform certain pre-defined sitting postures on IntelliChair and it is used for posture recognition experiment. The latter dataset is collected by asking the subjects to perform their normal sitting activity routine on IntelliChair for four hours, and the dataset is used for activity modelling and recognition experiment. For the posture recognition experiment, two Support Vector Machine (SVM) based classifiers are trained (one for spine postures and the other one for leg postures), and their performance evaluated. Hidden Markov Model is utilized for sitting activity modelling and recognition in order to establish the selected sitting activities from sitting posture sequences.2. After experimenting with possible sensors, Force Sensing Resistor (FSR) is selected as the pressure sensing unit for IntelliChair. Eight FSRs are mounted on the seat and back of a chair to gather haptic (i.e., touch-based) posture information. Furthermore, the research explores the possibility of using alternative non-intrusive sensing technology (i.e. vision based Kinect Sensor from Microsoft) and find out the Kinect sensor is not reliable for sitting posture detection due to the joint drifting problem. A suitable sampling rate for IntelliChair is determined according to the experiment result which is 6 Hz. The posture classification performance shows that the SVM based classifier is robust to “familiar” subject data (accuracy is 99.8% with spine postures and 99.9% with leg postures). When dealing with “unfamiliar” subject data, the accuracy is 80.7% for spine posture classification and 42.3% for leg posture classification. The result of activity recognition achieves 41.27% accuracy among four selected activities (i.e. relax, play game, working with PC and watching video). The result of this thesis shows that different individual body characteristics and sitting habits influence both sitting posture and sitting activity recognition. In this case, it suggests that IntelliChair is suitable for individual usage but a training stage is required.

Anomaly Detection in Noisy Images

Finding rare events in multidimensional data is an important detection problem that has applications in many fields, such as risk estimation in insurance industry, finance, flood prediction, medical diagnosis, quality assurance, security, or safety in transportation. The occurrence of such anomalies is so infrequent that there is usually not enough training data to learn an accurate statistical model of the anomaly class. In some cases, such events may have never been observed, so the only information that is available is a set of normal samples and an assumed pairwise similarity function. Such metric may only be known up to a certain number of unspecified parameters, which would either need to be learned from training data, or fixed by a domain expert. Sometimes, the anomalous condition may be formulated algebraically, such as a measure exceeding a predefined threshold, but nuisance variables may complicate the estimation of such a measure. Change detection methods used in time series analysis are not easily extendable to the multidimensional case, where discontinuities are not localized to a single point. On the other hand, in higher dimensions, data exhibits more complex interdependencies, and there is redundancy that could be exploited to adaptively model the normal data. In the first part of this dissertation, we review the theoretical framework for anomaly detection in images and previous anomaly detection work done in the context of crack detection and detection of anomalous components in railway tracks. In the second part, we propose new anomaly detection algorithms. The fact that curvilinear discontinuities in images are sparse with respect to the frame of shearlets, allows us to pose this anomaly detection problem as basis pursuit optimization. Therefore, we pose the problem of detecting curvilinear anomalies in noisy textured images as a blind source separation problem under sparsity constraints, and propose an iterative shrinkage algorithm to solve it. Taking advantage of the parallel nature of this algorithm, we describe how this method can be accelerated using graphical processing units (GPU). Then, we propose a new method for finding defective components on railway tracks using cameras mounted on a train. We describe how to extract features and use a combination of classifiers to solve this problem. Then, we scale anomaly detection to bigger datasets with complex interdependencies. We show that the anomaly detection problem naturally fits in the multitask learning framework. The first task consists of learning a compact representation of the good samples, while the second task consists of learning the anomaly detector. Using deep convolutional neural networks, we show that it is possible to train a deep model with a limited number of anomalous examples. In sequential detection problems, the presence of time-variant nuisance parameters affect the detection performance. In the last part of this dissertation, we present a method for adaptively estimating the threshold of sequential detectors using Extreme Value Theory on a Bayesian framework. Finally, conclusions on the results obtained are provided, followed by a discussion of possible future work.

Leveraging Multiple Features for Image Retrieval and Matching

The goal of image retrieval and matching is to find and locate object instances in images from a large-scale image database. While visual features are abundant, how to combine them to improve performance by individual features remains a challenging task. In this work, we focus on leveraging multiple features for accurate and efficient image retrieval and matching. We first propose two graph-based approaches to rerank initially retrieved images for generic image retrieval. In the graph, vertices are images while edges are similarities between image pairs. Our first approach employs a mixture Markov model based on a random walk model on multiple graphs to fuse graphs. We introduce a probabilistic model to compute the importance of each feature for graph fusion under a naive Bayesian formulation, which requires statistics of similarities from a manually labeled dataset containing irrelevant images. To reduce human labeling, we further propose a fully unsupervised reranking algorithm based on a submodular objective function that can be efficiently optimized by greedy algorithm. By maximizing an information gain term over the graph, our submodular function favors a subset of database images that are similar to query images and resemble each other. The function also exploits the rank relationships of images from multiple ranked lists obtained by different features. We then study a more well-defined application, person re-identification, where the database contains labeled images of human bodies captured by multiple cameras. Re-identifications from multiple cameras are regarded as related tasks to exploit shared information. We apply a novel multi-task learning algorithm using both low level features and attributes. A low rank attribute embedding is joint learned within the multi-task learning formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered. To locate objects in images, we design an object detector based on object proposals and deep convolutional neural networks (CNN) in view of the emergence of deep networks. We improve a Fast RCNN framework and investigate two new strategies to detect objects accurately and efficiently: scale-dependent pooling (SDP) and cascaded rejection classifiers (CRC). The SDP improves detection accuracy by exploiting appropriate convolutional features depending on the scale of input object proposals. The CRC effectively utilizes convolutional features and greatly eliminates negative proposals in a cascaded manner, while maintaining a high recall for true objects. The two strategies together improve the detection accuracy and reduce the computational cost.

RICH AND EFFICIENT VISUAL DATA REPRESENTATION

Increasing the size of training data in many computer vision tasks has shown to be very effective. Using large scale image datasets (e.g. ImageNet) with simple learning techniques (e.g. linear classifiers) one can achieve state-of-the-art performance in object recognition compared to sophisticated learning techniques on smaller image sets. Semantic search on visual data has become very popular. There are billions of images on the internet and the number is increasing every day. Dealing with large scale image sets is intense per se. They take a significant amount of memory that makes it impossible to process the images with complex algorithms on single CPU machines. Finding an efficient image representation can be a key to attack this problem. A representation being efficient is not enough for image understanding. It should be comprehensive and rich in carrying semantic information. In this proposal we develop an approach to computing binary codes that provide a rich and efficient image representation. We demonstrate several tasks in which binary features can be very effective. We show how binary features can speed up large scale image classification. We present learning techniques to learn the binary features from supervised image set (With different types of semantic supervision; class labels, textual descriptions). We propose several problems that are very important in finding and using efficient image representation.

Estudo comparativo entre técnicas de aprendizado de máquina para estimação de risco de crédito

Dissertação (mestrado)—Universidade de Brasília, Faculdade de Economia, Administração e Contabilidade, Programa de Pós-Graduação em Administração, 2016.