Automatic multi-resolution shape modeling of multi-organ structures.

Point Distribution Models (PDM) are among the most popular shape description techniques and their usefulness has been demonstrated in a wide variety of medical imaging applications. However, to adequately characterize the underlying modeled population it is essential to have a representative number of training samples, which is not always possible. This problem is especially relevant as the complexity of the modeled structure increases, being the modeling of ensembles of multiple 3D organs one of the most challenging cases. In this paper, we introduce a new GEneralized Multi-resolution PDM (GEM-PDM) in the context of multi-organ analysis able to efficiently characterize the different inter-object relations, as well as the particular locality of each object separately. Importantly, unlike previous approaches, the configuration of the algorithm is automated thanks to a new agglomerative landmark clustering method proposed here, which equally allows us to identify smaller anatomically significant regions within organs. The significant advantage of the GEM-PDM method over two previous approaches (PDM and hierarchical PDM) in terms of shape modeling accuracy and robustness to noise, has been successfully verified for two different databases of sets of multiple organs: six subcortical brain structures, and seven abdominal organs. Finally, we propose the integration of the new shape modeling framework into an active shape-model-based segmentation algorithm. The resulting algorithm, named GEMA, provides a better overall performance than the two classical approaches tested, ASM, and hierarchical ASM, when applied to the segmentation of 3D brain MRI.

Fully automatic GBM segmentation in the TCGA-GBM dataset: Prognosis and correlation with VASARI features.

Reproducible definition and quantification of imaging biomarkers is essential. We evaluated a fully automatic MR-based segmentation method by comparing it to manually defined sub-volumes by experienced radiologists in the TCGA-GBM dataset, in terms of sub-volume prognosis and association with VASARI features. MRI sets of 109 GBM patients were downloaded from the Cancer Imaging archive. GBM sub-compartments were defined manually and automatically using the Brain Tumor Image Analysis (BraTumIA). Spearman's correlation was used to evaluate the agreement with VASARI features. Prognostic significance was assessed using the C-index. Auto-segmented sub-volumes showed moderate to high agreement with manually delineated volumes (range (r): 0.4 - 0.86). Also, the auto and manual volumes showed similar correlation with VASARI features (auto r = 0.35, 0.43 and 0.36; manual r = 0.17, 0.67, 0.41, for contrast-enhancing, necrosis and edema, respectively). The auto-segmented contrast-enhancing volume and post-contrast abnormal volume showed the highest AUC (0.66, CI: 0.55-0.77 and 0.65, CI: 0.54-0.76), comparable to manually defined volumes (0.64, CI: 0.53-0.75 and 0.63, CI: 0.52-0.74, respectively). BraTumIA and manual tumor sub-compartments showed comparable performance in terms of prognosis and correlation with VASARI features. This method can enable more reproducible definition and quantification of imaging based biomarkers and has potential in high-throughput medical imaging research.

Cloud observations in Switzerland using hemispherical sky cameras

We present observations of total cloud cover and cloud type classification results from a sky camera network comprising four stations in Switzerland. In a comprehensive intercomparison study, records of total cloud cover from the sky camera, long-wave radiation observations, Meteosat, ceilometer, and visual observations were compared. Total cloud cover from the sky camera was in 65–85% of cases within ±1 okta with respect to the other methods. The sky camera overestimates cloudiness with respect to the other automatic techniques on average by up to 1.1 ± 2.8 oktas but underestimates it by 0.8 ± 1.9 oktas compared to the human observer. However, the bias depends on the cloudiness and therefore needs to be considered when records from various observational techniques are being homogenized. Cloud type classification was conducted using the k-Nearest Neighbor classifier in combination with a set of color and textural features. In addition, a radiative feature was introduced which improved the discrimination by up to 10%. The performance of the algorithm mainly depends on the atmospheric conditions, site-specific characteristics, the randomness of the selected images, and possible visual misclassifications: The mean success rate was 80–90% when the image only contained a single cloud class but dropped to 50–70% if the test images were completely randomly selected and multiple cloud classes occurred in the images.

MASCG: Multi-Atlas Segmentation Constrained Graph method for accurate segmentation of hip CT images

This paper addresses the issue of fully automatic segmentation of a hip CT image with the goal to preserve the joint structure for clinical applications in hip disease diagnosis and treatment. For this purpose, we propose a Multi-Atlas Segmentation Constrained Graph (MASCG) method. The MASCG method uses multi-atlas based mesh fusion results to initialize a bone sheetness based multi-label graph cut for an accurate hip CT segmentation which has the inherent advantage of automatic separation of the pelvic region from the bilateral proximal femoral regions. We then introduce a graph cut constrained graph search algorithm to further improve the segmentation accuracy around the bilateral hip joint regions. Taking manual segmentation as the ground truth, we evaluated the present approach on 30 hip CT images (60 hips) with a 15-fold cross validation. When the present approach was compared to manual segmentation, an average surface distance error of 0.30 mm, 0.29 mm, and 0.30 mm was found for the pelvis, the left proximal femur, and the right proximal femur, respectively. A further look at the bilateral hip joint regions demonstrated an average surface distance error of 0.16 mm, 0.21 mm and 0.20 mm for the acetabulum, the left femoral head, and the right femoral head, respectively.

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.

Improved Techniques for Acquisition and Analysis of Dynamic Contrast-Enhanced Magnetic Resonance Imaging for Detecting Vascular Permeability in the Central Nervous System

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a noninvasive technique for quantitative assessment of the integrity of blood-brain barrier and blood-spinal cord barrier (BSCB) in the presence of central nervous system pathologies. However, the results of DCE-MRI show substantial variability. The high variability can be caused by a number of factors including inaccurate T1 estimation, insufficient temporal resolution and poor contrast-to-noise ratio. My thesis work is to develop improved methods to reduce the variability of DCE-MRI results. To obtain fast and accurate T1 map, the Look-Locker acquisition technique was implemented with a novel and truly centric k-space segmentation scheme. In addition, an original multi-step curve fitting procedure was developed to increase the accuracy of T1 estimation. A view sharing acquisition method was implemented to increase temporal resolution, and a novel normalization method was introduced to reduce image artifacts. Finally, a new clustering algorithm was developed to reduce apparent noise in the DCE-MRI data. The performance of these proposed methods was verified by simulations and phantom studies. As part of this work, the proposed techniques were applied to an in vivo DCE-MRI study of experimental spinal cord injury (SCI). These methods have shown robust results and allow quantitative assessment of regions with very low vascular permeability. In conclusion, applications of the improved DCE-MRI acquisition and analysis methods developed in this thesis work can improve the accuracy of the DCE-MRI results.

Radiomics of NSCLC: Quantitative CT Image Feature Characterization and Tumor Shrinkage Prediction

Radiomics is the high-throughput extraction and analysis of quantitative image features. For non-small cell lung cancer (NSCLC) patients, radiomics can be applied to standard of care computed tomography (CT) images to improve tumor diagnosis, staging, and response assessment. The first objective of this work was to show that CT image features extracted from pre-treatment NSCLC tumors could be used to predict tumor shrinkage in response to therapy. This is important since tumor shrinkage is an important cancer treatment endpoint that is correlated with probability of disease progression and overall survival. Accurate prediction of tumor shrinkage could also lead to individually customized treatment plans. To accomplish this objective, 64 stage NSCLC patients with similar treatments were all imaged using the same CT scanner and protocol. Quantitative image features were extracted and principal component regression with simulated annealing subset selection was used to predict shrinkage. Cross validation and permutation tests were used to validate the results. The optimal model gave a strong correlation between the observed and predicted shrinkages with . The second objective of this work was to identify sets of NSCLC CT image features that are reproducible, non-redundant, and informative across multiple machines. Feature sets with these qualities are needed for NSCLC radiomics models to be robust to machine variation and spurious correlation. To accomplish this objective, test-retest CT image pairs were obtained from 56 NSCLC patients imaged on three CT machines from two institutions. For each machine, quantitative image features with concordance correlation coefficient values greater than 0.90 were considered reproducible. Multi-machine reproducible feature sets were created by taking the intersection of individual machine reproducible feature sets. Redundant features were removed through hierarchical clustering. The findings showed that image feature reproducibility and redundancy depended on both the CT machine and the CT image type (average cine 4D-CT imaging vs. end-exhale cine 4D-CT imaging vs. helical inspiratory breath-hold 3D CT). For each image type, a set of cross-machine reproducible, non-redundant, and informative image features was identified. Compared to end-exhale 4D-CT and breath-hold 3D-CT, average 4D-CT derived image features showed superior multi-machine reproducibility and are the best candidates for clinical correlation.

El color en las aceitunas negras naturales de mesa : nueva técnica de mensura digitalizada para optimizar el método de oscurecimiento natural

Se aplicó un nuevo método para la evaluación objetiva del color en aceitunas de mesa, basado en el análisis de la intensidad de reflexión de cada uno de los colores primarios que componen la luz blanca (rojo, verde y azul), según las longitudes de onda del Sistema RGB. Se trabajó con programas informáticos para el análisis de imágenes digitales color tipo BMP de 24 bits. Este trabajo proporciona mayor información sobre el pardeamiento de las aceitunas naturales en salmuera, lo que sería muy útil para incrementar la efectividad del proceso. El método propuesto es rápido y no destructivo, prometiendo ser muy práctico ya que permite que una misma muestra pueda ser evaluada en el tiempo. Se investigaron los cambios de color en aceitunas elaboradas naturalmente, con diferentes grados de madurez (pintas, rojas y negras) y a diferentes valores de pH (3,6 - 4,0 - 4,5), expuestas al aire durante períodos crecientes de tiempo. Se cuantificó el grado de oscurecimiento a través de Índices de Intensidad de Reflexión. La evolución del índice de reflexión en función del tiempo generó una curva polinomial de 4° grado que reveló el comportamiento sigmoidal del fenómeno de pardeamiento enzimático, con la máxima correlación a las 8 horas de aireación. Esta función permitiría predecir el fenómeno de pardeamiento en las aceitunas negras y representa una medición objetiva del grado relativo de pardeamiento. La evolución del color rojo (λ = 700,0 nm) exhibió la mayor correlación con el proceso de pardeamiento. Las aceitunas rojas naturales a pH 4,5 presentaron óptimo pardeamiento. El espectro de reflexión para el color azul (λ = 435,8 nm) se sugiere como medida de la actividad de la enzima PPO (polifenoloxidasa).

Mensura digitalizada de la evolución del color en aceitunas según el grado de madurez del fruto

Se desarrolló un nuevo método para la valoración objetiva del color en las aceitunas, mediante el análisis de la intensidad de la reflexión de los colores primarios (rojo, verde y azul) que componen la luz blanca. Se trabajó con programas informáticos para el análisis de imágenes digitales color tipo BMP de 24 bits. Este método es rápido, objetivo, no destructivo y puede ser muy útil cuando se requiere una técnica eficiente para determinar el grado de madurez de las aceitunas o de otros alimentos.

Caracterización por contenido de β-carotenos de ocho cultivares de zanahoria (Daucus carota L.) y su relación con el color

El objetivo fue determinar, durante dos años, el contenido de β-caroteno y su relación con el Índice de Color (IC), de ocho cultivares comerciales del tipo 'Flakkee' cultivadas en el INTA La Consulta. El diseño experimental a campo utilizado fue en bloques al azar con 3 repeticiones. Se evaluó β-caroteno (espectrofotometría a 450 nm) y se calculó el IC, mediante captación de imagen digital con PC y escáner, midiendo L, a y b del Sistema CIELAB. Los datos fueron analizados por ACP (análisis de componentes principales), la visualización de la variabilidad, por cartografiado de datos, análisis de varianza, pruebas de diferencia de medias y correlaciones. Los contenidos de β-carotenos y el IC de los cultivares se mantuvieron constantes durante los dos años estudiados, resultando las cultivares Natasha, Flakesse y Colmar las de mayor valor nutricional en cuanto a aporte de β-carotenos. En el rango de valores menores de 18 mg%g de β-carotenos, se observó una correlación positiva significativa en las cultivares Supreme, Spring y Laval. No se encontró una correlación alta lineal entre el IC y el contenido de β-carotenos. El uso del IC resulta adecuado para predecir, en un intervalo de valores, el contenido de β-carotenos en cultivares de zanahoria.

Holocene sedimentation in the Strait of Otranto, Mediterranean Sea

An extensive radiograph study of 24 undisturbed, up to 206-cm long box and gravity cores from the western part of the Strait of Otranto revealed a great variety of primary bedding structures and secondary burrowing features. The regional distribution of the sediments according to their structural, textural, and compositional properties reflects the major morphologic subdivisions of the strait into shelf, slope, and trough bottom (e.g., the bottom of the northern end of the Corfu-Kephallinia Trough, which extends from the northeastern Ionian Sea into the Strait of Otranto): (1) The Apulian shelf (0 to -170m) is only partly covered by very poorly sorted, muddy sands without layering. These relict(?) sands are rich in organic carbonate debris and contain glauconite and reworked (?Pleistocene) ooids. (2) The slope sediments (-170 to -1,000 m) are poorly sorted, sandy muds with a high degree of burrowing. One core (OT 5) is laminated and shows slump structures. An origin of these slumped sediment masses from older deposits higher on the slope was inferred from their abnormal compaction, color, texture, organic content, and mineral composition. (3) Cores from the northern end of the Corfu-Kephallinia Trough (-980 to -1,060 m) display a few graded sand layers, 2-5 cm (maximum 30 cm) thick with parallel and ripple-cross-laminations, deposited by oceanic bottom or small-scale turbidity currents. They are intercalated with homogeneous lutite. (4) Hemipelagic sediments prevail in the more southerly part of the Corfu-Kephallinia Trough and on the "Apulian-Ionian Ridge", the southern submarine extension of the Apulian Peninsula. Below a core depth of 160 cm, these cores have a laminated ("varved") zone, representing an Early Holocene (Boreal-Atlanticum) "stagnation layer" (14C age approximately 9,000 years). The terrigenous components of the surface sediments as well as those of the deeper sand layers can be derived from the Apulian shelf and the Italian mainland (Cretaceous Apulian Plateau and Gargano Mountains, southern Apennines, volcanic province of the Monte Vulture). Indicated by the heavy mineral glaucophane, a minor proportion of the sedimentary material is probably of Alpine origin. If this portion is considered to be first-cycle clastic material it reaches the Strait of Otranto after a longitudinal transport of 700 km via the Adriatic Sea. The lack of phyllosilicates in the coarse- to medium-grained shelf samples might be explained by the activity of the "Apulian Current" (surface velocities up to 4 knots) which in the past possibly has affected the bottom almost down to depths of the shelf edge. The percentage of planktonic organisms, and also the plankton: benthos ratio in the sediments is a useful indicator for bathymetry (depth zonation).

Road environment modeling using robust perspective analysis and recursive Bayesian segmentation

Recently, vision-based advanced driver-assistance systems (ADAS) have received a new increased interest to enhance driving safety. In particular, due to its high performance–cost ratio, mono-camera systems are arising as the main focus of this field of work. In this paper we present a novel on-board road modeling and vehicle detection system, which is a part of the result of the European I-WAY project. The system relies on a robust estimation of the perspective of the scene, which adapts to the dynamics of the vehicle and generates a stabilized rectified image of the road plane. This rectified plane is used by a recursive Bayesian classi- fier, which classifies pixels as belonging to different classes corresponding to the elements of interest of the scenario. This stage works as an intermediate layer that isolates subsequent modules since it absorbs the inherent variability of the scene. The system has been tested on-road, in different scenarios, including varied illumination and adverse weather conditions, and the results have been proved to be remarkable even for such complex scenarios.

Improved ore processing assessed by digital image análisis of the ores: a key to the sustainable development of the Iberian Pyrite Belt

Mining in the Iberian Pyrite Belt (IPB), the biggest VMS metallogenetic province known in the world to date, has to face a deep crisis in spite of the huge reserves still known after ≈5 000 years of production. This is due to several factors, as the difficult processing of complex Cu-Pb-Zn-Ag- Au ores, the exhaustion of the oxidation zone orebodies (the richest for gold, in gossan), the scarce demand for sulphuric acid in the world market, and harder environmental regulations. Of these factors, only the first and the last mentioned can be addressed by local ore geologists. A reactivation of mining can therefore only be achieved by an improved and more efficient ore processing, under the constraint of strict environmental controls. Digital image analysis of the ores, coupled to reflected light microscopy, provides a quantified and reliable mineralogical and textural characterization of the ores. The automation of the procedure for the first time furnishes the process engineers with real-time information, to improve the process and to preclude or control pollution; it can be applied to metallurgical tailings as well. This is shown by some examples of the IPB.

MRI texture analysis as means for addressing rehydration and milk diffusion of cereals

Cereals microstructure is one of the primary quality attributes of cereals. Cereals rehydration and milk diffusion depends on such microstructure and thus, the crispiness and the texture, which will make it more palatable for the final consumer. Magnetic Resonance Imaging (MRI) is a very powerful topographic tool since acquisition parameter leads to a wide possibility for identifying textures, structures and liquids mobility. It is suited for non-invasive imaging of water and fats. Rehydration and diffusion cereals processes were measured by MRI at different times and using two different kinds of milk, varying their fat level. Several images were obtained. A combination of textural analysis (based on the analysis of histograms) and segmentation methods (in order to understand the rehydration level of each variety of cereals) were performed. According to the rehydration level, no advisable clustering behavior was found. Nevertheless, some differences were noticeable between the coating, the type of milk and the variety of cereals

Multiscale object-based classification of satellite images merging multispectral information with panchromatic textural features

Once admitted the advantages of object-based classification compared to pixel-based classification; the need of simple and affordable methods to define and characterize objects to be classified, appears. This paper presents a new methodology for the identification and characterization of objects at different scales, through the integration of spectral information provided by the multispectral image, and textural information from the corresponding panchromatic image. In this way, it has defined a set of objects that yields a simplified representation of the information contained in the two source images. These objects can be characterized by different attributes that allow discriminating between different spectral&textural patterns. This methodology facilitates information processing, from a conceptual and computational point of view. Thus the vectors of attributes defined can be used directly as training pattern input for certain classifiers, as for example artificial neural networks. Growing Cell Structures have been used to classify the merged information.