Supervised classification of minimally invasive surgery psychomotor competence based on instruments motion analysis

Background Objective assessment of psychomotor skills has become an important challenge in the training of minimally invasive surgical (MIS) techniques. Currently, no gold standard defining surgical competence exists for classifying residents according to their surgical skills. Supervised classification has been proposed as a means for objectively establishing competence thresholds in psychomotor skills evaluation. This report presents a study comparing three classification methods for establishing their validity in a set of tasks for basic skills’ assessment. Methods Linear discriminant analysis (LDA), support vector machines (SVM), and adaptive neuro-fuzzy inference systems (ANFIS) were used. A total of 42 participants, divided into an experienced group (4 expert surgeons and 14 residents with >10 laparoscopic surgeries performed) and a nonexperienced group (16 students and 8 residents with <10 laparoscopic surgeries performed), performed three box trainer tasks validated for assessment of MIS psychomotor skills. Instrument movements were captured using the TrEndo tracking system, and nine motion analysis parameters (MAPs) were analyzed. The performance of the classifiers was measured by leave-one-out cross-validation using the scores obtained by the participants. Results The mean accuracy performances of the classifiers were 71 % (LDA), 78.2 % (SVM), and 71.7 % (ANFIS). No statistically significant differences in the performance were identified between the classifiers. Conclusions The three proposed classifiers showed good performance in the discrimination of skills, especially when information from all MAPs and tasks combined were considered. A correlation between the surgeons’ previous experience and their execution of the tasks could be ascertained from results. However, misclassifications across all the classifiers could imply the existence of other factors influencing psychomotor competence.

Traffic sign detection and tracking using robust 3D analysis

In this paper we present an innovative technique to tackle the problem of automatic road sign detection and tracking using an on-board stereo camera. It involves a continuous 3D analysis of the road sign during the whole tracking process. Firstly, a color and appearance based model is applied to generate road sign candidates in both stereo images. A sparse disparity map between the left and right images is then created for each candidate by using contour-based and SURF-based matching in the far and short range, respectively. Once the map has been computed, the correspondences are back-projected to generate a cloud of 3D points, and the best-fit plane is computed through RANSAC, ensuring robustness to outliers. Temporal consistency is enforced by means of a Kalman filter, which exploits the intrinsic smoothness of the 3D camera motion in traffic environments. Additionally, the estimation of the plane allows to correct deformations due to perspective, thus easing further sign classification.

Efficient hybrid monocular-stereo approach to on-board, video-based traffic sign detection and tracking

In this paper we propose an innovative method for the automatic detection and tracking of road traffic signs using an onboard stereo camera. It involves a combination of monocular and stereo analysis strategies to increase the reliability of the detections such that it can boost the performance of any traffic sign recognition scheme. Firstly, an adaptive color and appearance based detection is applied at single camera level to generate a set of traffic sign hypotheses. In turn, stereo information allows for sparse 3D reconstruction of potential traffic signs through a SURF-based matching strategy. Namely, the plane that best fits the cloud of 3D points traced back from feature matches is estimated using a RANSAC based approach to improve robustness to outliers. Temporal consistency of the 3D information is ensured through a Kalman-based tracking stage. This also allows for the generation of a predicted 3D traffic sign model, which is in turn used to enhance the previously mentioned color-based detector through a feedback loop, thus improving detection accuracy. The proposed solution has been tested with real sequences under several illumination conditions and in both urban areas and highways, achieving very high detection rates in challenging environments, including rapid motion and significant perspective distortion

Self-organizing cultured neural networks: Image analysis techniques for longitudinal tracking and modeling of the underlying network structure

Esta tesis estudia la evolución estructural de conjuntos de neuronas como la capacidad de auto-organización desde conjuntos de neuronas separadas hasta que forman una red (clusterizada) compleja. Esta tesis contribuye con el diseño e implementación de un algoritmo no supervisado de segmentación basado en grafos con un coste computacional muy bajo. Este algoritmo proporciona de forma automática la estructura completa de la red a partir de imágenes de cultivos neuronales tomadas con microscopios de fase con una resolución muy alta. La estructura de la red es representada mediante un objeto matemático (matriz) cuyos nodos representan a las neuronas o grupos de neuronas y los enlaces son las conexiones reconstruidas entre ellos. Este algoritmo extrae también otras medidas morfológicas importantes que caracterizan a las neuronas y a las neuritas. A diferencia de otros algoritmos hasta el momento, que necesitan de fluorescencia y técnicas inmunocitoquímicas, el algoritmo propuesto permite el estudio longitudinal de forma no invasiva posibilitando el estudio durante la formación de un cultivo. Además, esta tesis, estudia de forma sistemática un grupo de variables topológicas que garantizan la posibilidad de cuantificar e investigar la progresión de las características principales durante el proceso de auto-organización del cultivo. Nuestros resultados muestran la existencia de un estado concreto correspondiente a redes con configuracin small-world y la emergencia de propiedades a micro- y meso-escala de la estructura de la red. Finalmente, identificamos los procesos físicos principales que guían las transformaciones morfológicas de los cultivos y proponemos un modelo de crecimiento de red que reproduce el comportamiento cuantitativamente de las observaciones experimentales. ABSTRACT The thesis analyzes the morphological evolution of assemblies of living neurons, as they self-organize from collections of separated cells into elaborated, clustered, networks. In particular, it contributes with the design and implementation of a graph-based unsupervised segmentation algorithm, having an associated very low computational cost. The processing automatically retrieves the whole network structure from large scale phase-contrast images taken at high resolution throughout the entire life of a cultured neuronal network. The network structure is represented by a mathematical object (a matrix) in which nodes are identified neurons or neurons clusters, and links are the reconstructed connections between them. The algorithm is also able to extract any other relevant morphological information characterizing neurons and neurites. More importantly, and at variance with other segmentation methods that require fluorescence imaging from immunocyto- chemistry techniques, our measures are non invasive and entitle us to carry out a fully longitudinal analysis during the maturation of a single culture. In turn, a systematic statistical analysis of a group of topological observables grants us the possibility of quantifying and tracking the progression of the main networks characteristics during the self-organization process of the culture. Our results point to the existence of a particular state corresponding to a small-world network configuration, in which several relevant graphs micro- and meso-scale properties emerge. Finally, we identify the main physical processes taking place during the cultures morphological transformations, and embed them into a simplified growth model that quantitatively reproduces the overall set of experimental observations.

Self-organizing cultured neural networks: Image analysis techniques for longitudinal tracking and modeling of the underlying network structure (versión actualizada)

Esta tesis estudia la evolución estructural de conjuntos de neuronas como la capacidad de auto-organización desde conjuntos de neuronas separadas hasta que forman una red (clusterizada) compleja. Esta tesis contribuye con el diseño e implementación de un algoritmo no supervisado de segmentación basado en grafos con un coste computacional muy bajo. Este algoritmo proporciona de forma automática la estructura completa de la red a partir de imágenes de cultivos neuronales tomadas con microscopios de fase con una resolución muy alta. La estructura de la red es representada mediante un objeto matemático (matriz) cuyos nodos representan a las neuronas o grupos de neuronas y los enlaces son las conexiones reconstruidas entre ellos. Este algoritmo extrae también otras medidas morfológicas importantes que caracterizan a las neuronas y a las neuritas. A diferencia de otros algoritmos hasta el momento, que necesitan de fluorescencia y técnicas inmunocitoquímicas, el algoritmo propuesto permite el estudio longitudinal de forma no invasiva posibilitando el estudio durante la formación de un cultivo. Además, esta tesis, estudia de forma sistemática un grupo de variables topológicas que garantizan la posibilidad de cuantificar e investigar la progresión de las características principales durante el proceso de auto-organización del cultivo. Nuestros resultados muestran la existencia de un estado concreto correspondiente a redes con configuracin small-world y la emergencia de propiedades a micro- y meso-escala de la estructura de la red. Finalmente, identificamos los procesos físicos principales que guían las transformaciones morfológicas de los cultivos y proponemos un modelo de crecimiento de red que reproduce el comportamiento cuantitativamente de las observaciones experimentales. ABSTRACT The thesis analyzes the morphological evolution of assemblies of living neurons, as they self-organize from collections of separated cells into elaborated, clustered, networks. In particular, it contributes with the design and implementation of a graph-based unsupervised segmentation algorithm, having an associated very low computational cost. The processing automatically retrieves the whole network structure from large scale phase-contrast images taken at high resolution throughout the entire life of a cultured neuronal network. The network structure is represented by a mathematical object (a matrix) in which nodes are identified neurons or neurons clusters, and links are the reconstructed connections between them. The algorithm is also able to extract any other relevant morphological information characterizing neurons and neurites. More importantly, and at variance with other segmentation methods that require fluorescence imaging from immunocyto- chemistry techniques, our measures are non invasive and entitle us to carry out a fully longitudinal analysis during the maturation of a single culture. In turn, a systematic statistical analysis of a group of topological observables grants us the possibility of quantifying and tracking the progression of the main networks characteristics during the self-organization process of the culture. Our results point to the existence of a particular state corresponding to a small-world network configuration, in which several relevant graphs micro- and meso-scale properties emerge. Finally, we identify the main physical processes taking place during the cultures morphological transformations, and embed them into a simplified growth model that quantitatively reproduces the overall set of experimental observations.

Numerical study of ultrasound induced non-linear shape and size bubble oscillations in viscoelastic media

The theoretical study of forced bubble oscillations is motivated by the importance of cavitation bubbles and oscillating encapsulated microbubbles (i.e. contrast agents) in medical sciences. In more details,theoretical studies on bubble dynamics addressing the sound-bubble interaction phenomenon provide the basis for understanding the dynamics of contrast agent microbubbles used in medical diagnosis and of non-linearly oscillating cavitation bubbles in the case of high-intensity ultrasound therapy. Moreover, the inclusion of viscoelasticity is of vital importance for an accurate theoretical analysis since most biological tissues and fluids exhibit non-Newtonian behavior.

Object tracking using direct methods in RGB-D cameras

En esta tesis se presenta un análisis en profundidad de cómo se deben utilizar dos tipos de métodos directos, Lucas-Kanade e Inverse Compositional, en imágenes RGB-D y se analiza la capacidad y precisión de los mismos en una serie de experimentos sintéticos. Estos simulan imágenes RGB, imágenes de profundidad (D) e imágenes RGB-D para comprobar cómo se comportan en cada una de las combinaciones. Además, se analizan estos métodos sin ninguna técnica adicional que modifique el algoritmo original ni que lo apoye en su tarea de optimización tal y como sucede en la mayoría de los artículos encontrados en la literatura. Esto se hace con el fin de poder entender cuándo y por qué los métodos convergen o divergen para que así en el futuro cualquier interesado pueda aplicar los conocimientos adquiridos en esta tesis de forma práctica. Esta tesis debería ayudar al futuro interesado a decidir qué algoritmo conviene más en una determinada situación y debería también ayudarle a entender qué problemas le pueden dar estos algoritmos para poder poner el remedio más apropiado. Las técnicas adicionales que sirven de remedio para estos problemas quedan fuera de los contenidos que abarca esta tesis, sin embargo, sí se hace una revisión sobre ellas.---ABSTRACT---This thesis presents an in-depth analysis about how direct methods such as Lucas- Kanade and Inverse Compositional can be applied in RGB-D images. The capability and accuracy of these methods is also analyzed employing a series of synthetic experiments. These simulate the efects produced by RGB images, depth images and RGB-D images so that diferent combinations can be evaluated. Moreover, these methods are analyzed without using any additional technique that modifies the original algorithm or that aids the algorithm in its search for a global optima unlike most of the articles found in the literature. Our goal is to understand when and why do these methods converge or diverge so that in the future, the knowledge extracted from the results presented here can efectively help a potential implementer. After reading this thesis, the implementer should be able to decide which algorithm fits best for a particular task and should also know which are the problems that have to be addressed in each algorithm so that an appropriate correction is implemented using additional techniques. These additional techniques are outside the scope of this thesis, however, they are reviewed from the literature.

Robust Real-time Vision-based Aircraft Tracking From Unmanned Aerial Vehicles.

Aircraft tracking plays a key and important role in the Sense-and-Avoid system of Unmanned Aerial Vehicles (UAVs). This paper presents a novel robust visual tracking algorithm for UAVs in the midair to track an arbitrary aircraft at real-time frame rates, together with a unique evaluation system. This visual algorithm mainly consists of adaptive discriminative visual tracking method, Multiple-Instance (MI) learning approach, Multiple-Classifier (MC) voting mechanism and Multiple-Resolution (MR) representation strategy, that is called Adaptive M3 tracker, i.e. AM3. In this tracker, the importance of test sample has been integrated to improve the tracking stability, accuracy and real-time performances. The experimental results show that this algorithm is more robust, efficient and accurate against the existing state-of-art trackers, overcoming the problems generated by the challenging situations such as obvious appearance change, variant surrounding illumination, partial aircraft occlusion, blur motion, rapid pose variation and onboard mechanical vibration, low computation capacity and delayed information communication between UAVs and Ground Station (GS). To our best knowledge, this is the first work to present this tracker for solving online learning and tracking freewill aircraft/intruder in the UAVs.

Real-Time Adaptive Multi-Classifier Multi-Resolution Visual Tracking Framework for Unmanned Aerial Vehicles

This paper presents a novel robust visual tracking framework, based on discriminative method, for Unmanned Aerial Vehicles (UAVs) to track an arbitrary 2D/3D target at real-time frame rates, that is called the Adaptive Multi-Classifier Multi-Resolution (AMCMR) framework. In this framework, adaptive Multiple Classifiers (MC) are updated in the (k-1)th frame-based Multiple Resolutions (MR) structure with compressed positive and negative samples, and then applied them in the kth frame-based Multiple Resolutions (MR) structure to detect the current target. The sample importance has been integrated into this framework to improve the tracking stability and accuracy. The performance of this framework was evaluated with the Ground Truth (GT) in different types of public image databases and real flight-based aerial image datasets firstly, then the framework has been applied in the UAV to inspect the Offshore Floating Platform (OFP). The evaluation and application results show that this framework is more robust, efficient and accurate against the existing state-of-art trackers, overcoming the problems generated by the challenging situations such as obvious appearance change, variant illumination, partial/full target occlusion, blur motion, rapid pose variation and onboard mechanical vibration, among others. To our best knowledge, this is the first work to present this framework for solving the online learning and tracking freewill 2D/3D target problems, and applied it in the UAVs.

The influence of sensor placement on in-situ ultrasound wave velocity measurement.

Ultrasound wave velocity was measured in 30 pieces of Spanish Scots pine (Pinus sylvestris L.), 90 x 140 mm in cross-section and 4 m long. Five different sensor placement arrangements were used: end to end (V0), face to opposite face, edge to opposite edge, face to same face and edge to same edge. The pieces were successively shortened to 3, 2 and 1 m, in order to obtain these velocities and their ratios to reference value V0 for different lengths and angles with respect to the piece axis for the crossed measurements. The velocity obtained in crossed measurements is lower than V0. A correction coefficient for crossed velocities is proposed, depending on the angle, to adjust them to the V0 benchmark. The velocities measured on a surface, are also lower than V0, and their ratio with respect to V0 is close to 0.97 for distances equal to or greater than 18 times the depth of the beam.

Sustained correction of bleeding disorder in hemophilia B mice by gene therapy

Mice generated by disrupting the clotting factor IX gene exhibit severe bleeding disorder and closely resemble the phenotype seen in hemophilia B patients. Here we demonstrate that a single intraportal injection of a recombinant adeno-associated virus (AAV) vector encoding canine factor IX cDNA under the control of a liver-specific enhancer/promoter leads to a long-term and complete correction of the bleeding disorder. High level expression of up to 15–20 μg/ml of canine factor IX was detected in the plasma of mice injected with 5.6 × 1011 particles of an AAV vector for >5 months. The activated partial thromboplastin time of the treated mice was fully corrected to higher than normal levels. Liver-specific expression of canine factor IX was confirmed by immunofluorescence staining, and secreted factor IX protein was identified in the mouse plasma by Western blotting. All treated mice survived the tail clip test without difficulty. Thus, a single intraportal injection of a recombinant adeno-associated virus vector expressing factor IX successfully cured the bleeding disorder of hemophilia B mice, proving the feasibility of using AAV-based vectors for liver-targeted gene therapy of genetic diseases.

Administration of helper-dependent adenoviral vectors and sequential delivery of different vector serotype for long-term liver-directed gene transfer in baboons

The efficiency of first-generation adenoviral vectors as gene delivery tools is often limited by the short duration of transgene expression, which can be related to immune responses and to toxic effects of viral proteins. In addition, readministration is usually ineffective unless the animals are immunocompromised or a different adenovirus serotype is used. Recently, adenoviral vectors devoid of all viral coding sequences (helper-dependent or gutless vectors) have been developed to avoid expression of viral proteins. In mice, liver-directed gene transfer with AdSTK109, a helper-dependent adenoviral (Ad) vector containing the human α1-antitrypsin (hAAT) gene, resulted in sustained expression for longer than 10 months with negligible toxicity to the liver. In the present report, we have examined the duration of expression of AdSTK109 in the liver of baboons and compared it to first-generation vectors expressing hAAT. Transgene expression was limited to approximately 3–5 months with the first-generation vectors. In contrast, administration of AdSTK109 resulted in transgene expression for longer than a year in two of three baboons. We have also investigated the feasibility of circumventing the humoral response to the virus by sequential administration of vectors of different serotypes. We found that the ineffectiveness of readministration due to the humoral response to an Ad5 first-generation vector was overcome by use of an Ad2-based vector expressing hAAT. These data suggest that long-term expression of transgenes should be possible by combining the reduced immunogenicity and toxicity of helper-dependent vectors with sequential delivery of vectors of different serotypes.

Calpain is a mediator of preservation-reperfusion injury in rat liver transplantation

Proteases as well as alterations in intracellular calcium have important roles in hepatic preservation-reperfusion injury, and increased calpain activity recently has been demonstrated in liver allografts. Experiments were designed to evaluate (i) hepatic cytosolic calpain activity during different periods of cold ischemia (CI), rewarming, or reperfusion, and (ii) effects of inhibition of calpain on liver graft function using the isolated perfused rat liver and arterialized orthotopic liver transplantation models. Calpain activity was assayed using the fluorogenic substrate Suc-Leu-Leu-Val-Tyr-7-amino-4-methyl coumarin (AMC) and expressed as mean ± SD pmol AMC released/min per mg of cytosolic protein. Calpain activity rose significantly after 24 hr of CI in University of Wisconsin solution and further increased with longer preservation. Activity also increased within 30 min of rewarming, peaking at 120 min. Increased durations of CI preceding rewarming resulted in significantly higher activity (P < 0.01). Calpain activity increased rapidly upon reperfusion and was significantly enhanced by previous CI (P < 0.01). Calpain inhibition with Cbz-Val-Phe methyl ester significantly decreased aspartate aminotransferase released in the isolated perfused rat liver perfusate (P < 0.05). Duration of survival after orthotopic liver transplantation using livers cold-preserved for 40 hr was also significantly increased (P < 0.05) with calpain inhibitor. In conclusion, calpain proteases are activated during each phase of transplantation and are likely to play an important role in the mechanisms of preservation-reperfusion injury.

A substance P (neurokinin-1) receptor mutant carboxyl-terminally truncated to resemble a naturally occurring receptor isoform displays enhanced responsiveness and resistance to desensitization

Two isoforms of the substance P (SP) receptor, differing in the length of the cytoplasmic carboxyl-terminus by ≈8 kDa, have been detected previously in rat salivary glands and other tissues. The binding and functional properties of these two isoforms have been investigated using full-length (407 amino acids) and carboxyl-terminally truncated (324 amino acids) rat SP receptors transfected stably into Chinese hamster ovary cells. Both the full-length and the truncated receptor bound radiolabeled SP with a similar Kd (≈0.1 nM). The average number of high affinity SP binding sites per cell was 1.0 × 105 and 0.3 × 105 for the full-length and the truncated SP receptor, respectively. In both cell lines, SP induced a rapid but transient increase in cytosolic calcium concentration ([Ca2+]i), which consisted of the release of Ca2+ from intracellular stores and the influx of extracellular Ca2+. Both components are dependent on phospholipase C activation. Although the full-length and the truncated receptor utilize the same calcium pathways, they differ in their EC50 values (0.28 nM for the full-length; 0.07 nM for the truncated). These differences in responsiveness may be related to the observed differences in receptor desensitization. The truncated receptor, in contrast to the full-length receptor, does not undergo rapid and long-lasting desensitization. Cells possessing the short isoform of the SP receptor would thus be expected to exhibit a prolonged responsiveness.

Short-term correction of factor VIII deficiency in a murine model of hemophilia A after delivery of adenovirus murine factor VIII in utero

Development of in utero gene transfer approaches may provide therapies for genetic disorders with perinatal morbidity. In hemophilia A, prenatal and postnatal bleeding may be catastrophic, and modest increments in factor VIII (FVIII) activity are therapeutic. We performed transuterine i.p. gene transfer at day 15 of gestation in a murine model of hemophilia A. Normal, carrier (XHX), and FVIII-deficient (XHY and XHXH) fetuses injected with adenoviral vectors carrying luciferase or β-galactosidase reporter genes showed high-level gene expression with 91% fetal survival. The live-born rates of normal and FVIII-deficient animals injected in utero with adenovirus murine FVIII (3.3 × 105 plaque-forming units) was 87%. FVIII activity in plasma was 50.7 ± 10.5% of normal levels at day 2 of life, 7.2 ± 2.2% by day 15 of life, and no longer detectable at day 21 of life in hemophilic animals. Injection of higher doses of murine FVIII adenovirus at embryonic day 15 produced supranormal levels of FVIII activity in the neonatal period. PCR analysis identified viral genomes primarily in the liver, intestine, and spleen, although adenoviral DNA was detected in distal tissues when higher doses of adenovirus were administered. These studies show that transuterine i.p. injection of adenoviral vectors produces therapeutic levels of circulating FVIII throughout the neonatal period. The future development of efficient and persisting vectors that produce long-term gene expression may allow for in utero correction of genetic diseases originating in the fetal liver, hematopoietic stem cells, as well as other tissues.