Improving Clustering Algorithms for Image Segmentation using Contour and Region Information

In image segmentation, clustering algorithms are very popular because they are intuitive and, some of them, easy to implement. For instance, the k-means is one of the most used in the literature, and many authors successfully compare their new proposal with the results achieved by the k-means. However, it is well known that clustering image segmentation has many problems. For instance, the number of regions of the image has to be known a priori, as well as different initial seed placement (initial clusters) could produce different segmentation results. Most of these algorithms could be slightly improved by considering the coordinates of the image as features in the clustering process (to take spatial region information into account). In this paper we propose a significant improvement of clustering algorithms for image segmentation. The method is qualitatively and quantitative evaluated over a set of synthetic and real images, and compared with classical clustering approaches. Results demonstrate the validity of this new approach

Dense Deformation Field Estimation for Atlas Registration using the Active Contour Framework

In this paper, we propose a new paradigm to carry outthe registration task with a dense deformation fieldderived from the optical flow model and the activecontour method. The proposed framework merges differenttasks such as segmentation, regularization, incorporationof prior knowledge and registration into a singleframework. The active contour model is at the core of ourframework even if it is used in a different way than thestandard approaches. Indeed, active contours are awell-known technique for image segmentation. Thistechnique consists in finding the curve which minimizesan energy functional designed to be minimal when thecurve has reached the object contours. That way, we getaccurate and smooth segmentation results. So far, theactive contour model has been used to segment objectslying in images from boundary-based, region-based orshape-based information. Our registration technique willprofit of all these families of active contours todetermine a dense deformation field defined on the wholeimage. A well-suited application of our model is theatlas registration in medical imaging which consists inautomatically delineating anatomical structures. Wepresent results on 2D synthetic images to show theperformances of our non rigid deformation field based ona natural registration term. We also present registrationresults on real 3D medical data with a large spaceoccupying tumor substantially deforming surroundingstructures, which constitutes a high challenging problem.

Profound impact of uncomplicated pregnancy on diastolic, but not systolic pulse contour of aortic pressure

RESUME: L'objectif de cette étude était de déterminer l'impact de la grossesse non compliquée sur l'onde de pouls de la pression aortique centrale. Méthode 66 femmes au total avec une grossesse simple ont été réparties en trois groupes selon le stade de leur gestation: premier trimestre (T1, n=22), deuxième trimestre (T2, n=20) et troisième trimestre (T3, n=24). Le groupe contrôle (C, n=21) était constitué de femmes non enceintes, en bonne santé habituelle, prenant une contraception oestroprogestative. La tonométrie d'aplanation a été utilisée pour l'acquisition des ondes de pouls centrale un appareil disponible dans le commerce (SphygmoCor) permet l'enregistrement de l'onde de pouls périphérique avec un tonomètre d'aplanation de l'artère radiale au niveau du poignet, puis effectue sa transformation en sa forme centrale, grâce à une analyse de Fourrier et une fonction de transfert. L'influence des ondes réfléchies sur l'onde de pouls a été déterminée non seulement pendant la systole (augmentation systolique), comme on procède habituellement dans l'analyse de l'onde de pouls, mais aussi pendant la diastole (augmentation diastolique). Résultats Au cours de la grossesse, les pressions centrales systolique et diastolique sont restées inchangées et comparables aux valeurs mesurées chez les femmes qui ne sont pas enceintes. Dans le groupe contrôle, l'augmentation systolique s'élevait à 8.1±7.5% de la pression de pouls ; il n'y avait pas de différence statistiquement significative avec les valeurs obtenues chez les femmes enceintes, et ce, à n'importe quel stade de la grossesse (T1 : 4.6±11.4%, T2: 5.0±9.3%, T3 : 4.7±8.1%). Par contre, l'amplitude de l'augmentation diastolique diminuait avec la progression de la grossesse (C 6.5±2.4%, T1 : 5.2±3.1%, T2 : 3.8±2.6%; P=0.002 versus C; T3 : 2.3±2.0%; P<0.0001 versus C et P=0.004 versus T 1). Conclusion La grossesse ne modifie pas la forme de l'onde de pouls systolique centrale, ce qui implique de la part du système cardiovasculaire une adaptation fine à la demande croissante de flux sanguin, et ce, à tous les stades de la grossesse. Par contre, l'amplitude de l'onde de réflexion atteignant l'aorte pendant la diastole diminue progressivement au cours de la grossesse. Perspectives De récentes études montrent qu'une valeur anormalement haute de l'augmentation systolique de la pression centrale, comme on peut la déterminer avec la tonométrie d'aplanation, pourrait être un indice de trouble hypertensif de la grossesse débutant. Cette technique simple pourrait être d'autant plus facile à mettre en oeuvre si les valeurs normales pour l'augmentation systolique étaient indépendantes du stade de la grossesse, comme le suggèrent nos résultats, du moins pour les mesures prises en position assise.

Towards a resolution of conflicting models of illusory contour processing in humans.

Despite myriad studies, neurophysiologic mechanisms mediating illusory contour (IC) sensitivity remain controversial. Among the competing models one favors feed-forward effects within lower-tier cortices (V1/V2). Another situates IC sensitivity first within higher-tier cortices, principally lateral-occipital cortices (LOC), with later feedback effects in V1/V2. Still others postulate that LOC are sensitive to salient regions demarcated by the inducing stimuli, whereas V1/V2 effects specifically support IC sensitivity. We resolved these discordances by using misaligned line gratings, oriented either horizontally or vertically, to induce ICs. Line orientation provides an established assay of V1/V2 modulations independently of IC presence, and gratings lack salient regions. Electrical neuroimaging analyses of visual evoked potentials (VEPs) disambiguated the relative timing and localization of IC sensitivity with respect to that for grating orientation. Millisecond-by-millisecond analyses of VEPs and distributed source estimations revealed a main effect of grating orientation beginning at 65 ms post-stimulus onset within the calcarine sulcus that was followed by a main effect of IC presence beginning at 85 ms post-stimulus onset within the LOC. There was no evidence for differential processing of ICs as a function of the orientation of the grating. These results support models wherein IC sensitivity occurs first within the LOC.

Water erosion in no-tillage monoculture and intercropped systems along contour lines

Water erosion is the major cause of soil and water losses and the main factor of degradation of agricultural areas. The objective of this work was to quantify pluvial water erosion from an untilled soil with crop rows along the contour, in 2009 and 2010, on a Humic Dystrupept, with the following treatments: a) maize monoculture; b) soybean monoculture; c) common bean monoculture; d) intercropped maize and bean, exposed to four simulated rainfall tests of on hour at controlled intensity (64 mm h-1). The first test was applied 18 days after sowing and the others; 39, 75 and 120 days after the first test. The crop type influenced soil loss through water erosion in the simulated rainfall tests 3 and 4; soybean was most effective in erosion control in test 3, however, in test 4, maize was more effective. Water loss was influenced by the crop type in test 3 only, where maize and soybean were equally effective, with less runoff than from the other crops. The soil loss rate varied during the runoff sampling period in different ways, demonstrating a positive linear relationship between soil and water loss, in the different rainfall tests.

Multi-Atlas based Segmentation of Head and Neck CT Images using Active Contour

This paper presents the segmentation of bilateral parotid glands in the Head and Neck (H&N) CT images using an active contour based atlas registration. We compare segmentation results from three atlas selection strategies: (i) selection of "single-most-similar" atlas for each image to be segmented, (ii) fusion of segmentation results from multiple atlases using STAPLE, and (iii) fusion of segmentation results using majority voting. Among these three approaches, fusion using majority voting provided the best results. Finally, we present a detailed evaluation on a dataset of eight images (provided as a part of H&N auto segmentation challenge conducted in conjunction with MICCAI-2010 conference) using majority voting strategy.

An active contour-based atlas registration model applied to automatic subthalamic nucleus targeting on MRI: method and validation.

This paper presents a new non parametric atlas registration framework, derived from the optical flow model and the active contour theory, applied to automatic subthalamic nucleus (STN) targeting in deep brain stimulation (DBS) surgery. In a previous work, we demonstrated that the STN position can be predicted based on the position of surrounding visible structures, namely the lateral and third ventricles. A STN targeting process can thus be obtained by registering these structures of interest between a brain atlas and the patient image. Here we aim to improve the results of the state of the art targeting methods and at the same time to reduce the computational time. Our simultaneous segmentation and registration model shows mean STN localization errors statistically similar to the most performing registration algorithms tested so far and to the targeting expert's variability. Moreover, the computational time of our registration method is much lower, which is a worthwhile improvement from a clinical point of view.

Active Contour-Based Segmentation of Head and Neck with Adaptive Atlas Selection

This paper presents automated segmentation of structuresin the Head and Neck (H\&N) region, using an activecontour-based joint registration and segmentation model.A new atlas selection strategy is also used. Segmentationis performed based on the dense deformation fieldcomputed from the registration of selected structures inthe atlas image that have distinct boundaries, onto thepatient's image. This approach results in robustsegmentation of the structures of interest, even in thepresence of tumors, or anatomical differences between theatlas and the patient image. For each patient, an atlasimage is selected from the available atlas-database,based on the similarity metric value, computed afterperforming an affine registration between each image inthe atlas-database and the patient's image. Unlike manyof the previous approaches in the literature, thesimilarity metric is not computed over the entire imageregion; rather, it is computed only in the regions ofsoft tissue structures to be segmented. Qualitative andquantitative evaluation of the results is presented.

Segmentation of Head and Neck Lymph Node Regions for Radiotherapy Planning Using Active Contour-Based Atlas Registration

In this paper, we present the segmentation of the headand neck lymph node regions using a new active contourbased atlas registration model. We propose to segment thelymph node regions without directly including them in theatlas registration process; instead, they are segmentedusing the dense deformation field computed from theregistration of the atlas structures with distinctboundaries. This approach results in robust and accuratesegmentation of the lymph node regions even in thepresence of significant anatomical variations between theatlas-image and the patient's image to be segmented. Wealso present a quantitative evaluation of lymph noderegions segmentation using various statistical as well asgeometrical metrics: sensitivity, specificity, dicesimilarity coefficient and Hausdorff distance. Acomparison of the proposed method with two other state ofthe art methods is presented. The robustness of theproposed method to the atlas selection, in segmenting thelymph node regions, is also evaluated.

Active deformation fields: dense deformation field estimation for atlas-based segmentation using the active contour framework.

This paper presents a new and original variational framework for atlas-based segmentation. The proposed framework integrates both the active contour framework, and the dense deformation fields of optical flow framework. This framework is quite general and encompasses many of the state-of-the-art atlas-based segmentation methods. It also allows to perform the registration of atlas and target images based on only selected structures of interest. The versatility and potentiality of the proposed framework are demonstrated by presenting three diverse applications: In the first application, we show how the proposed framework can be used to simulate the growth of inconsistent structures like a tumor in an atlas. In the second application, we estimate the position of nonvisible brain structures based on the surrounding structures and validate the results by comparing with other methods. In the final application, we present the segmentation of lymph nodes in the Head and Neck CT images, and demonstrate how multiple registration forces can be used in this framework in an hierarchical manner.

Pin guidance of reconstruction plate contour: an expanded role of external fixation

This article presents a modification of intraoperative external fixation for mandibular reconstruction with free tissue flaps. This technique is indicated when preregistration of the reconstruction plate is not possible due to transmandibular tumor extension. Once standard external fixation has been carried out and prior to segmental mandibulectomy, additional pins are fixed to the connecting rod that delineate the mandibular contour in three-dimensional (3D) space. Following mandibulectomy, these pins allow accurate contouring of the reconstruction plate and improved restoration of mandibular contour, projection, and dental occlusion. A step-by-step description of the technique using models and intraoperative photos is presented. This method of mandibular reconstruction is a simple and time-effective alternative to intraoperative computer navigation and 3D modeling in select cases of oral carcinoma where tumor infiltration of the outer mandibular cortex precludes prebending of the reconstruction plates.

Body taping for contour surgery.

BACKGROUND: Preoperative marking is of primary importance in body contouring and when precise simulation of skin excisions is difficult. Because the "cut as you go" principle can be delicate, especially in patients after massive weight loss, a simple and quick method is needed for preoperative planning. We suggest an approach that helps visualize the optimal skin incision lines and simulates the postoperative result by body taping. METHODS: Twelve patients who underwent abdominal contouring, including classic and vertical abdominoplasties as well as dog ear and scar revision, were prospectively analyzed. The skin to be excised was preoperatively folded, taped, and then marked. The area marked was measured and compared with the actual intraoperatively resected area and the postoperative result was evaluated after 1 year by the patients and three surgeons. RESULTS: With body taping, an 83% congruence between the preoperative planning and the surgery was obtained and only two patients had additional skin resected. No wound dehiscence and flap necrosis occurred and patients as well as surgeons scored the final body contour positively. CONCLUSION: Body taping is a simple, quick, and economic method for planning contour surgery with high accuracy as demonstrated by the low rate of intraoperative changes of the planned resection and low complication rate.