Lung cancer screening with CT: evaluation of radiologists and different computer assisted detection software (CAD) as first and second readers for lung nodule detection at different dose levels

OBJECTIVES To find the best pairing of first and second reader at highest sensitivity for detecting lung nodules with CT at various dose levels. MATERIALS AND METHODS An anthropomorphic lung phantom and artificial lung nodules were used to simulate screening CT-examination at standard dose (100 mAs, 120 kVp) and 8 different low dose levels, using 120, 100 and 80 kVp combined with 100, 50 and 25 mAs. At each dose level 40 phantoms were randomly filled with 75 solid and 25 ground glass nodules (5-12 mm). Two radiologists and 3 different computer aided detection softwares (CAD) were paired to find the highest sensitivity. RESULTS Sensitivities at standard dose were 92%, 90%, 84%, 79% and 73% for reader 1, 2, CAD1, CAD2, CAD3, respectively. Combined sensitivity for human readers 1 and 2 improved to 97%, (p1=0.063, p2=0.016). Highest sensitivities--between 97% and 99.0%--were achieved by combining any radiologist with any CAD at any dose level. Combining any two CADs, sensitivities between 85% and 88% were significantly lower than for radiologists combined with CAD (p<0.03). CONCLUSIONS Combination of a human observer with any of the tested CAD systems provide optimal sensitivity for lung nodule detection even at reduced dose at 25 mAs/80 kVp.

Detection, treatment, and prevention of carbapenemase-producing Enterobacteriaceae : Recommendations from an International Working Group

The prevalence of carbapenemase-producing Enterobacteriaceae (CPE) has increased during the past 10 years. Its detection is frequently difficult, because they do not always show a minimum inhibitory concentration (MIC) value for carbapenems in the resistance range. Both broth microdilution and agar dilution methods are more sensitive than disk diffusion method, Etest and automated systems. Studies on antimicrobial treatment are based on a limited number of patients; therefore, the optimal treatment is not well established. Combination therapy with two active drugs appears to be more effective than monotherapy. Combination of a carbapenem with another active agent — preferentially an aminoglycoside or colistin — could lower mortality provided that the MIC is #4 mg/l and probably #8 mg/l, and is administered in a higher-dose/prolonged-infusion regimen. An aggressive infection control and prevention strategy is recommended, including reinforcement of hand hygiene, using contact precautions and early detection of CPE through use of targeted surveillance.

Active Testing for Face Detection and Localization

We provide a novel search technique which uses a hierarchical model and a mutual information gain heuristic to efficiently prune the search space when localizing faces in images. We show exponential gains in computation over traditional sliding window approaches, while keeping similar performance levels.

A practical approach to designing syndromic surveillance systems for livestock and poultry

The field of animal syndromic surveillance (SyS) is growing, with many systems being developed worldwide. Now is an appropriate time to share ideas and lessons learned from early SyS design and implementation. Based on our practical experience in animal health SyS, with additions from the public health and animal health SyS literature, we put forward for discussion a 6-step approach to designing SyS systems for livestock and poultry. The first step is to formalise policy and surveillance goals which are considerate of stakeholder expectations and reflect priority issues (1). Next, it is important to find consensus on national priority diseases and identify current surveillance gaps. The geographic, demographic, and temporal coverage of the system must be carefully assessed (2). A minimum dataset for SyS that includes the essential data to achieve all surveillance objectives while minimizing the amount of data collected should be defined. One can then compile an inventory of the data sources available and evaluate each using the criteria developed (3). A list of syndromes should then be produced for all data sources. Cases can be classified into syndrome classes and the data can be converted into time series (4). Based on the characteristics of the syndrome-time series, the length of historic data available and the type of outbreaks the system must detect, different aberration detection algorithms can be tested (5). Finally, it is essential to develop a minimally acceptable response protocol for each statistical signal produced (6). Important outcomes of this pre-operational phase should be building of a national network of experts and collective action and evaluation plans. While some of the more applied steps (4 and 5) are currently receiving consideration, more emphasis should be put on earlier conceptual steps by decision makers and surveillance developers (1-3).

Towards cheap, accurate polymorphism detection

Polymorphism, along with inheritance, is one of the most important features in object-oriented languages, but it is also one of the biggest obstacles to source code comprehension. Depending on the run-time type of the receiver of a message, any one of a number of possible methods may be invoked. Several algorithms for creating accurate call-graphs using static analysis already exist, however, they consume significant time and memory resources. We propose an approach that will combine static and dynamic analysis and yield the best possible precision with a minimal trade-off between used resources and accuracy.

Scaleable Code Clone Detection

Code clone detection helps connect developers across projects, if we do it on a large scale. The cornerstones that allow clone detection to work on a large scale are: (1) bad hashing (2) lightweight parsing using regular expressions and (3) MapReduce pipelines. Bad hashing means to determine whether or not two artifacts are similar by checking whether their hashes are identical. We show a bad hashing scheme that works well on source code. Lightweight parsing using regular expressions is our technique of obtaining entire parse trees from regular expressions, robustly and efficiently. We detail the algorithm and implementation of one such regular expression engine. MapReduce pipelines are a way of expressing a computation such that it can automatically and simply be parallelized. We detail the design and implementation of one such MapReduce pipeline that is efficient and debuggable. We show a clone detector that combines these cornerstones to detect code clones across all projects, across all versions of each project.

Unified detection and tracking of instruments during retinal microsurgery

Methods for tracking an object have generally fallen into two groups: tracking by detection and tracking through local optimization. The advantage of detection-based tracking is its ability to deal with target appearance and disappearance, but it does not naturally take advantage of target motion continuity during detection. The advantage of local optimization is efficiency and accuracy, but it requires additional algorithms to initialize tracking when the target is lost. To bridge these two approaches, we propose a framework for unified detection and tracking as a time-series Bayesian estimation problem. The basis of our approach is to treat both detection and tracking as a sequential entropy minimization problem, where the goal is to determine the parameters describing a target in each frame. To do this we integrate the Active Testing (AT) paradigm with Bayesian filtering, and this results in a framework capable of both detecting and tracking robustly in situations where the target object enters and leaves the field of view regularly. We demonstrate our approach on a retinal tool tracking problem and show through extensive experiments that our method provides an efficient and robust tracking solution.

Vision-based Proximity Detection in Retinal Surgery

In retinal surgery, surgeons face difficulties such as indirect visualization of surgical targets, physiological tremor, and lack of tactile feedback, which increase the risk of retinal damage caused by incorrect surgical gestures. In this context, intraocular proximity sensing has the potential to overcome current technical limitations and increase surgical safety. In this paper, we present a system for detecting unintentional collisions between surgical tools and the retina using the visual feedback provided by the opthalmic stereo microscope. Using stereo images, proximity between surgical tools and the retinal surface can be detected when their relative stereo disparity is small. For this purpose, we developed a system comprised of two modules. The first is a module for tracking the surgical tool position on both stereo images. The second is a disparity tracking module for estimating a stereo disparity map of the retinal surface. Both modules were specially tailored for coping with the challenging visualization conditions in retinal surgery. The potential clinical value of the proposed method is demonstrated by extensive testing using a silicon phantom eye and recorded rabbit in vivo data.

Passive wireless sensor systems can recognize activites of daily living

The ability to determine what activity of daily living a person performs is of interest in many application domains. It is possible to determine the physical and cognitive capabilities of the elderly by inferring what activities they perform in their houses. Our primary aim was to establish a proof of concept that a wireless sensor system can monitor and record physical activity and these data can be modeled to predict activities of daily living. The secondary aim was to determine the optimal placement of the sensor boxes for detecting activities in a room. A wireless sensor system was set up in a laboratory kitchen. The ten healthy participants were requested to make tea following a defined sequence of tasks. Data were collected from the eight wireless sensor boxes placed in specific places in the test kitchen and analyzed to detect the sequences of tasks performed by the participants. These sequence of tasks were trained and tested using the Markov Model. Data analysis focused on the reliability of the system and the integrity of the collected data. The sequence of tasks were successfully recognized for all subjects and the averaged data pattern of tasks sequences between the subjects had a high correlation. Analysis of the data collected indicates that sensors placed in different locations are capable of recognizing activities, with the movement detection sensor contributing the most to detection of tasks. The central top of the room with no obstruction of view was considered to be the best location to record data for activity detection. Wireless sensor systems show much promise as easily deployable to monitor and recognize activities of daily living.

Dish Detection and Segmentation for Dietary Assessment on Smartphones

Diet-related chronic diseases severely affect personal and global health. However, managing or treating these diseases currently requires long training and high personal involvement to succeed. Computer vision systems could assist with the assessment of diet by detecting and recognizing different foods and their portions in images. We propose novel methods for detecting a dish in an image and segmenting its contents with and without user interaction. All methods were evaluated on a database of over 1600 manually annotated images. The dish detection scored an average of 99% accuracy with a .2s/image run time, while the automatic and semi-automatic dish segmentation methods reached average accuracies of 88% and 91% respectively, with an average run time of .5s/image, outperforming competing solutions.

Homography-based ground plane detection using a single on-board camera

This study presents a robust method for ground plane detection in vision-based systems with a non-stationary camera. The proposed method is based on the reliable estimation of the homography between ground planes in successive images. This homography is computed using a feature matching approach, which in contrast to classical approaches to on-board motion estimation does not require explicit ego-motion calculation. As opposed to it, a novel homography calculation method based on a linear estimation framework is presented. This framework provides predictions of the ground plane transformation matrix that are dynamically updated with new measurements. The method is specially suited for challenging environments, in particular traffic scenarios, in which the information is scarce and the homography computed from the images is usually inaccurate or erroneous. The proposed estimation framework is able to remove erroneous measurements and to correct those that are inaccurate, hence producing a reliable homography estimate at each instant. It is based on the evaluation of the difference between the predicted and the observed transformations, measured according to the spectral norm of the associated matrix of differences. Moreover, an example is provided on how to use the information extracted from ground plane estimation to achieve object detection and tracking. The method has been successfully demonstrated for the detection of moving vehicles in traffic environments.

Vehicular traffic surveillance and road lane detection using radar interferometry

Speed enforcement on public roadways is an important issue in order to guarantee road security and to reduce the number and seriousness of traffic accidents. Traditionally, this task has been partially solved using radar and/or laser technologies and, more recently, using video-camera based systems. All these systems have significant shortcomings that have yet to be overcome. The main drawback of classical Doppler radar technology is that the velocity measurement fails when several vehicles are in the radars beam. Modern radar systems are able to measure speed and range between vehicle and radar. However, this is not enough to discriminate the lane where the vehicle is driving on. The limitation of several vehicles in the beam is overcome using laser technology. However, laser systems have another important limitation: They cannot measure the speed of several vehicles simultaneously. Novel video-camera systems, based on license plate identification, solve the previous drawbacks, but they have the problem that they can only measure average speed but never top-speed. This paper studies the feasibility of using an interferometric linear frequency modulated continuous wave radar to improve top-speed enforcement on roadways. Two different systems based on down-the-road and across-the-road radar configurations are presented. The main advantage of the proposed solutions is they can simultaneously measure speed, range, and lane of several vehicles, allowing the univocal identification of the offenders. A detailed analysis about the operation and accuracy of these solutions is reported. In addition, the feasibility of the proposed techniques has been demonstrated with simulations and real experiments using a Ka-band interferometric radar developed by our research group.

Vision-based vehicle detection and tracking with a mobile camera using a statistical framework

En esta tesis se aborda la detección y el seguimiento automático de vehículos mediante técnicas de visión artificial con una cámara monocular embarcada. Este problema ha suscitado un gran interés por parte de la industria automovilística y de la comunidad científica ya que supone el primer paso en aras de la ayuda a la conducción, la prevención de accidentes y, en última instancia, la conducción automática. A pesar de que se le ha dedicado mucho esfuerzo en los últimos años, de momento no se ha encontrado ninguna solución completamente satisfactoria y por lo tanto continúa siendo un tema de investigación abierto. Los principales problemas que plantean la detección y seguimiento mediante visión artificial son la gran variabilidad entre vehículos, un fondo que cambia dinámicamente debido al movimiento de la cámara, y la necesidad de operar en tiempo real. En este contexto, esta tesis propone un marco unificado para la detección y seguimiento de vehículos que afronta los problemas descritos mediante un enfoque estadístico. El marco se compone de tres grandes bloques, i.e., generación de hipótesis, verificación de hipótesis, y seguimiento de vehículos, que se llevan a cabo de manera secuencial. No obstante, se potencia el intercambio de información entre los diferentes bloques con objeto de obtener el máximo grado posible de adaptación a cambios en el entorno y de reducir el coste computacional. Para abordar la primera tarea de generación de hipótesis, se proponen dos métodos complementarios basados respectivamente en el análisis de la apariencia y la geometría de la escena. Para ello resulta especialmente interesante el uso de un dominio transformado en el que se elimina la perspectiva de la imagen original, puesto que este dominio permite una búsqueda rápida dentro de la imagen y por tanto una generación eficiente de hipótesis de localización de los vehículos. Los candidatos finales se obtienen por medio de un marco colaborativo entre el dominio original y el dominio transformado. Para la verificación de hipótesis se adopta un método de aprendizaje supervisado. Así, se evalúan algunos de los métodos de extracción de características más populares y se proponen nuevos descriptores con arreglo al conocimiento de la apariencia de los vehículos. Para evaluar la efectividad en la tarea de clasificación de estos descriptores, y dado que no existen bases de datos públicas que se adapten al problema descrito, se ha generado una nueva base de datos sobre la que se han realizado pruebas masivas. Finalmente, se presenta una metodología para la fusión de los diferentes clasificadores y se plantea una discusión sobre las combinaciones que ofrecen los mejores resultados. El núcleo del marco propuesto está constituido por un método Bayesiano de seguimiento basado en filtros de partículas. Se plantean contribuciones en los tres elementos fundamentales de estos filtros: el algoritmo de inferencia, el modelo dinámico y el modelo de observación. En concreto, se propone el uso de un método de muestreo basado en MCMC que evita el elevado coste computacional de los filtros de partículas tradicionales y por consiguiente permite que el modelado conjunto de múltiples vehículos sea computacionalmente viable. Por otra parte, el dominio transformado mencionado anteriormente permite la definición de un modelo dinámico de velocidad constante ya que se preserva el movimiento suave de los vehículos en autopistas. Por último, se propone un modelo de observación que integra diferentes características. En particular, además de la apariencia de los vehículos, el modelo tiene en cuenta también toda la información recibida de los bloques de procesamiento previos. El método propuesto se ejecuta en tiempo real en un ordenador de propósito general y da unos resultados sobresalientes en comparación con los métodos tradicionales. ABSTRACT This thesis addresses on-road vehicle detection and tracking with a monocular vision system. This problem has attracted the attention of the automotive industry and the research community as it is the first step for driver assistance and collision avoidance systems and for eventual autonomous driving. Although many effort has been devoted to address it in recent years, no satisfactory solution has yet been devised and thus it is an active research issue. The main challenges for vision-based vehicle detection and tracking are the high variability among vehicles, the dynamically changing background due to camera motion and the real-time processing requirement. In this thesis, a unified approach using statistical methods is presented for vehicle detection and tracking that tackles these issues. The approach is divided into three primary tasks, i.e., vehicle hypothesis generation, hypothesis verification, and vehicle tracking, which are performed sequentially. Nevertheless, the exchange of information between processing blocks is fostered so that the maximum degree of adaptation to changes in the environment can be achieved and the computational cost is alleviated. Two complementary strategies are proposed to address the first task, i.e., hypothesis generation, based respectively on appearance and geometry analysis. To this end, the use of a rectified domain in which the perspective is removed from the original image is especially interesting, as it allows for fast image scanning and coarse hypothesis generation. The final vehicle candidates are produced using a collaborative framework between the original and the rectified domains. A supervised classification strategy is adopted for the verification of the hypothesized vehicle locations. In particular, state-of-the-art methods for feature extraction are evaluated and new descriptors are proposed by exploiting the knowledge on vehicle appearance. Due to the lack of appropriate public databases, a new database is generated and the classification performance of the descriptors is extensively tested on it. Finally, a methodology for the fusion of the different classifiers is presented and the best combinations are discussed. The core of the proposed approach is a Bayesian tracking framework using particle filters. Contributions are made on its three key elements: the inference algorithm, the dynamic model and the observation model. In particular, the use of a Markov chain Monte Carlo method is proposed for sampling, which circumvents the exponential complexity increase of traditional particle filters thus making joint multiple vehicle tracking affordable. On the other hand, the aforementioned rectified domain allows for the definition of a constant-velocity dynamic model since it preserves the smooth motion of vehicles in highways. Finally, a multiple-cue observation model is proposed that not only accounts for vehicle appearance but also integrates the available information from the analysis in the previous blocks. The proposed approach is proven to run near real-time in a general purpose PC and to deliver outstanding results compared to traditional methods.