A Graph-Based Approach for Making Consensus-Based Decisions in Image Search and Person Re-Identification.

Image matching and retrieval is the underlying problem in various directions of computer vision research, such as image search, biometrics, and person re-identification. The problem involves searching for the closest match to a query image in a database of images. This work presents a method for generating a consensus amongst multiple algorithms for image matching and retrieval. The proposed algorithm, Shortest Hamiltonian Path Estimation (SHaPE), maps the process of ranking candidates based on a set of scores to a graph-theoretic problem. This mapping is extended to incorporate results from multiple sets of scores obtained from different matching algorithms. The problem of consensus-based decision-making is solved by searching for a suitable path in the graph under specified constraints using a two-step process. First, a greedy algorithm is employed to generate an approximate solution. In the second step, the graph is extended and the problem is solved by applying Ant Colony Optimization. Experiments are performed for image search and person re-identification to illustrate the efficiency of SHaPE in image matching and retrieval. Although SHaPE is presented in the context of image retrieval, it can be applied, in general, to any problem involving the ranking of candidates based on multiple sets of scores.

Identification of vascular disruptor compounds by analysis in zebrafish embryos and mouse embryonic endothelial cells.

To identify vascular disruptor compounds (VDCs), this study utilized an in vivo zebrafish embryo vascular model in conjunction with a mouse endothelial cell model to screen a subset of the U.S. Environmental Protection Agency (EPA) ToxCast Phase I chemical inventory. In zebrafish, 161 compounds were screened and 34 were identified by visual inspection as VDCs, of which 28 were confirmed as VDCs by quantitative image analysis. Testing of the zebrafish VDCs for their capacity to inhibit endothelial tube formation in the murine yolk-sac-derived endothelial cell line C166 identified 22 compounds that both disrupted zebrafish vascular development and murine endothelial in vitro tubulogenesis. Putative molecular targets for the VDCs were predicted using EPA's Toxicological Prioritization Index tool and a VDC signature based on a proposed adverse outcome pathway for developmental vascular toxicity. In conclusion, our screening approach identified 22 novel VDCs, some of which were active at nanomolar concentrations.

Inferior Breast-Chest Contour Detection in 3-D Images of the Female Torso.

Stereophotogrammetry is finding increased use in clinical breast surgery, both for breast reconstruction after oncological procedures and cosmetic augmentation and reduction. The ability to visualize and quantify morphological features of the breast facilitates pre-operative planning and post-operative outcome assessment. The contour outlining the lower half of the breast is important for the quantitative assessment of breast aesthetics. Based on this inferior breast contour, relevant morphological measures, such as breast symmetry, volume, and ptosis, can be determined. In this paper, we present an approach for automatically detecting the inferior contour of the breast in 3D images. Our approach employs surface curvature analysis and is able to detect the breast contour with high accuracy, achieving an average error of 1.64 mm and a dice coefficient in the range of 0.72-0.87 when compared with the manually annotated contour (ground truth). In addition, the detected contour is used to facilitate the detection of the lowest visible point on the breast, which is an important landmark for breast morphometric analysis.

Evaluation of a bovine 100% native collagen for the treatment of chronic wounds: a case series.

PURPOSE: The roles of debridement, infection control, and moisture balance in wound healing are familiar to wound care clinicians, but these measures may not be sufficient for wound closure in all patients. In these cases, adjuvant therapies such as collagen dressings may be needed. Collagen dressings are thought to encourage wound healing by laying down a provisional biomaterial matrix that captures wound exudates because of its absorbent nature, and thus creates an environment necessary for healing. This case series describes our experience with a bovine-derived, 100% native, type I collagen in patients with chronic and persistent wounds. CASES: This case series included 20 patients with 21 chronic wounds ranging from 0.6 to 101.4 cm(2) that had been recalcitrant to prior conservative treatment and/or the use of submucosal intestinal matrix, oxidized regenerated cellulose/collagen matrix, or skin substitute. In addition to the bovine-derived 100% native collagen, standard wound care included the use of any systemic or topical antimicrobial treatments needed to specifically address wound infections. The total duration of treatment with the bovine-derived 100% native collagen was up to 12 weeks. Complete wound healing was achieved for 15 of the patients in this series; wound healing times varied from 13 to 68 days. Two additional patients achieved wound healing, using a combination of the bovine-derived 100% native collagen and other therapies, at 114 days and 107 days, respectively, after starting the wound healing process with solely the bovine-derived 100% native collagen treatment. One patient did not respond to treatment. The collagen treatment was well tolerated by the patients, with 3 incidences of dermatitis that resolved after treatment with corticosteroids. CONCLUSION: Following a change in their chronic wound care regimen to include a bovine-derived, 100% native, type I collagen, we achieved an 83.3% (15 out of 18 patients) wound closure rate. Two patients were excluded from the data set analysis because they received additional intervention outside the parameters described in this multiple-case series.

Minimizing illumination differences for 3D to 2D face recognition using lighting maps.

Asymmetric 3D to 2D face recognition has gained attention from the research community since the real-world application of 3D to 3D recognition is limited by the unavailability of inexpensive 3D data acquisition equipment. A 3D to 2D face recognition system explicitly relies on 3D facial data to account for uncontrolled image conditions related to head pose or illumination. We build upon such a system, which matches relit gallery textures with pose-normalized probe images, using the gallery facial meshes. The relighting process, however, is based on an assumption of indoor lighting conditions and limits recognition performance on outdoor images. In this paper, we propose a novel method for minimizing illumination difference by unlighting a 3D face texture via albedo estimation using lighting maps. The algorithm is evaluated on challenging databases (UHDB30, UHDB11, FRGC v2.0) with drastic lighting and pose variations. The experimental results demonstrate the robustness of our method for estimating the albedo from both indoor and outdoor captured images, and the effectiveness and efficiency for illumination normalization in face recognition.

Embryonic exposure to sodium arsenite perturbs vascular development in zebrafish.

Exposure to arsenic in its inorganic form, arsenite, causes adverse effects to many different organs and tissues. Here, we have investigated arsenite-induced adverse effects on vascular tissues in the model organism zebrafish, Danio rerio. Zebrafish embryos were exposed to arsenite at different exposure windows and the susceptibility to vascular tissue damage was recorded at 72hours post fertilization (hpf). Intersegmental vessel sprouting and growth was most perturbed by exposure to arsenite during the 24-48hpf window, while disruption in the condensation of the caudal vein plexus was more often observed at the 48-72hpf exposure window, reflecting when these structures develop during normal embryogenesis. The vascular growth rate was decreased by arsenite exposure, and deviated from that of control embryos at around 24-26.5hpf. We further mapped changes in expression of key regulators of angiogenesis and vasculogenesis. Downregulation of vascular endothelial growth factor receptor 1/fms-related tyrosine kinase 1 (vegfr1/flt1) expression was evident already at 24hpf, coinciding with the decreased vascular growth rate. At later time points, matrix metalloproteinase 9 (mmp9) expression was upregulated, suggesting that arsenite affects the composition of the extracellular matrix. In total, the expression of eight key factors involved in different aspects of vascularization was significantly altered by arsenic exposure. In conclusion, our results show that arsenite is a potent vascular disruptor in the developing zebrafish embryo, a finding that calls for an evaluation of arsenite as a developmental vascular toxicant in mammalian model systems.

Automated analysis of zebrafish images for screening toxicants.

An important factor facilitating the application of zebrafish in biomedical research is high throughput screening of vertebrate animal models. For example, being able to model the growth of blood vessel in the vasculature system is interesting for understanding both the circulatory system in humans, and for facilitating large scale screening of the influence of various chemicals on vascular development. Compared to other models, the zebrafish embryo is an attractive alternative for environmental risk assessment of chemicals since it offers the possibility to perform high-throughput analyses in vivo. However the lack of an automated image analysis framework restricts high throughput screening. In this paper, we provide a method for quantitative measurements of zebrafish blood vessel morphology since it is difficult to assess changes in vessel structure by visual inspection. The method presented is generalized, i.e. it is not restricted to any specific chemically treated zebrafish, and can be used with wide variety of chemicals.

Modeling novelty habituation during exploratory activity in Drosophila.

Habituation is a common form of non-associative learning in which the organism gradually decreases its response to repeated stimuli. The decrease in exploratory activity of many animal species during exposure to a novel open field arena is a widely studied habituation paradigm. However, a theoretical framework to quantify how the novelty of the arena is learned during habituation is currently missing. Drosophila melanogaster display a high mean absolute activity and a high probability for directional persistence when first introduced to a novel arena. Both measures decrease during habituation to the arena. Here, we propose a phenomenological model of habituation for Drosophila exploration based on two principles: Drosophila form a spatial representation of the arena edge as a set of connected local patches, and repeated exposure to these patches is essential for the habituation of the novelty. The level of exposure depends on the number of visitations and is quantified by a variable referred to as "coverage". This model was tested by comparing predictions against the experimentally measured behavior of wild type Drosophila. The novelty habituation of wild type Canton-S depends on coverage and is specifically independent of the arena radius. Our model describes the time dependent locomotor activity, ΔD, of Canton-S using an experimentally established stochastic process Pn(ΔD), which depends on the coverage. The quantitative measures of exploration and habituation were further applied to three mutant genotypes. Consistent with a requirement for vision in novelty habituation, blind no receptor potential A(7) mutants display a failure in the decay of probability for directional persistence and mean absolute activity. The rutabaga(2080) habituation mutant also shows defects in these measures. The kurtz(1) non-visual arrestin mutant demonstrates a rapid decay in these measures, implying reduced motivation. The model and the habituation measures offer a powerful framework for understanding mechanisms associated with open field habituation.

3D Face Discriminant Analysis Using Gauss-Markov Posterior Marginals.

We present a Markov Random Field model for the analysis of lattices (e.g., images or 3D meshes) in terms of the discriminative information of their vertices. The proposed method provides a measure field that estimates the probability of each vertex being "discriminative" or "nondiscriminative" for a given classification task. To illustrate the applicability and generality of our framework, we use the estimated probabilities as feature scoring to define compact signatures for three different classification tasks: 1) 3D Face Recognition, 2) 3D Facial Expression Recognition, and 3) Ethnicity-based Subject Retrieval, obtaining very competitive results. The main contribution of this work lies in the development of a novel framework for feature selection in scenaria in which the most discriminative information is smoothly distributed along a lattice.

Total oesophagectomy for squamous cell carcinoma with or without standard two field node dissection - a prospective study.

Cancer of the esophagus and gastroesophageal junction (GEJ) is notorious for its advanced stage at the time of diagnosis with transmural invasion and early lymphatic spread in the majority of the patients. R0 resection is the aim of surgery with curative intent. Regarding the role of lymphadenectomy, as in any other solid organ cancer, there are opposing views. Some surgeons argue that the presence of lymph node involvement equals systemic disease and that survival remains unchanged despite removal of these lymph nodes. For others the presence of lymph node involvement, even at a distance from the primary tumor, justifies an aggressive approach with radical esophagectomy combined with lymphadenectomy. The purpose of this article is to compare standard two field lymph node dissection versus non formal lymph node dissection in carcinoma esophagus. The conclusions are based on the experience with 60 cases of carcinoma esophagus over 2 years. In our opinion total esophagectomy with 2-field lymphadenectomy is the standard surgery for resectable squamous cell carcinoma of esophagus. It improves the lymphnode yield thereby ensuring adequate staging of the disease. It can be performed with acceptable morbidity and mortality as the nonformal lymphadenectomy procedure. Locoregional recurrence following 2 field lymphadenectomy is significantly low as compared to nonformal lymphadenectomy procedure though the distant recurrence rate is same. 2 year disease free survival in this study shows advantage of 2 field lymphadenectomy compared to non formal lymphadenectomy procedure.

Modeling Drosophila positional preferences in open field arenas with directional persistence and wall attraction.

In open field arenas, Drosophila adults exhibit a preference for arena boundaries over internal walls and open regions. Herein, we investigate the nature of this preference using phenomenological modeling of locomotion to determine whether local arena features and constraints on movement alone are sufficient to drive positional preferences within open field arenas of different shapes and with different internal features. Our model has two components: directional persistence and local wall force. In regions far away from walls, the trajectory is entirely characterized by a directional persistence probability, P(r,θ), for each movement defined by the step size, r, and the turn angle, θ. In close proximity to walls, motion is computed from P(r,θ), and a local attractive force which depends on the distance between the fly and points on the walls. The directional persistence probability was obtained experimentally from trajectories of wild type Drosophila in a circular open field arena and the wall force was computed to minimize the difference between the radial distributions from the model and Drosophila in the same circular arena. The two-component model for fly movement was challenged by comparing the positional preferences from the two-component model to wild type Drosophila in a variety of open field arenas. In most arenas there was a strong concordance between the two-component model and Drosophila. In more complex arenas, the model exhibits similar trends, but some significant differences were found. These differences suggest that there are emergent features within these complex arenas that have significance for the fly, such as potential shelter. Hence, the two-component model is an important step in defining how Drosophila interact with their environment.

Embedding topic discovery in conditional random fields model for segmenting nuclei using multispectral data.

Segmentation of cells/nuclei is a challenging problem in 2-D histological and cytological images. Although a large number of algorithms have been proposed, newer efforts continue to be devoted to investigate robust models that could have high level of adaptability with regard to considerable amount of image variability. In this paper, we propose a multiclassification conditional random fields (CRFs) model using a combination of low-level cues (bottom-up) and high-level contextual information (top-down) for separating nuclei from the background. In our approach, the contextual information is extracted by an unsupervised topic discovery process, which efficiently helps to suppress segmentation errors caused by intensity inhomogeneity and variable chromatin texture. In addition, we propose a multilayer CRF, an extension of the traditional single-layer CRF, to handle high-dimensional dataset obtained through spectral microscopy, which provides combined benefits of spectroscopy and imaging microscopy, resulting in the ability to acquire spectral images of microscopic specimen. The approach is evaluated with color images, as well as spectral images. The overall accuracy of the proposed segmentation algorithm reaches 95% when applying multilayer CRF model to the spectral microscopy dataset. Experiments also show that our method outperforms seeded watershed, a widely used algorithm for cell segmentation.

[Not Available].

A total contact cast (TCC) is considered the gold standard for healing diabetic foot ulcers (DFU). Numerous studies have demonstrated the excellent healing success of a TCC; however, its adoption in routine clinical use does not match its success rate. This lack of implementation is due to several factors: Medicare's payment structure, lack of clinical training, and a variety of patient factors. These factors have reduced clinicians' use of TCC to approximately 25% of DFU. The aim of this review was to analyze and demonstrate common scenarios for outpatient wound centers where a TCC may be beneficial to both patients and hospital systems, and to expand its usage to more closely reflect its healing success rate. .

Assessment of the adequacy of closed reduction in fractures of the zygomatic arch using "C"-arm image intensifier.

Major problems in closed reduction of isolated, minimally displaced, and depressed zygomatic arch fractures are blind nature of the technique, reliability on digital palpation, reduction click, and step deformity between fragments. The purpose of this study was to objectively confirm the adequacy of closed reduction intraoperatively and the usefulness of the "C"-arm image intensifier. A total of 12 patients with 1- to 8-day-old unilateral isolated and depressed zygomatic arch fracture underwent closed reduction under "C"-arm image intensifier. Of these patients, 9 were men and 3 were women, with age ranging from 18 to 32 years. Intraoperative prereduction and postreduction images were obtained using the "C"-arm image intensifier. Criteria for adequate reduction were the following: intrafragmentary gap less than 0.5 mm, no overriding of fragments, no depression of fragments, and no step deformity. After being clinically satisfied about the reduction, images on "C"-arm showed no intrafragmentary gap. In 3 patients, there were residual overriding and minimal rotation around the anteroposterior axis of the posterior fragment. In 1 patient, rotation and step deformity remained. In this patient, additional stabilization was provided. The "C"-arm image intensifier shows some poorly reduced or unstable isolated depressed zygomatic arch fractures that remain unidentified even after careful palpation. Thus, it plays a recognizable role to avoid the trouble of second intervention.

Horizontal flip pedicled genioplasty for correction of asymmetric chin in adult unilateral temperomandibular joint ankylosis.

It has been the desire and a great challenge to clinicians treating maxillofacial deformities to bring about symmetry in asymmetric faces. As one understands, it is very difficult to reproduce nature, that is, the normal side out of abnormal side, and it is easier to manage bilateral symmetrical deformities. Temporomandibular joint (TMJ) ankylosis, when it occurs in early childhood, will have devastating effects on the future growth and development of the jaws and teeth with obvious facial deformity including the chin, which worsens with advancing age and the time elapsed between the onset of ankylosis and the treatment instituted. We have been treating these chin deformities in adult unilateral TMJ ankylosis cases for over more than a decade with horizontal flip pedicled genioplasty, which has a mathematical basis of turning a scalene triangle to an isosceles triangle and thereby achieving symmetry. Fixation of the genial segment in an overriding position not only adds to the length of mandible but also overcomes the obstructive sleep apnea many times associated with TMJ ankylosis. We have successfully treated 15 patients using horizontal flip pedicled genioplasty during last 14 years. This instantaneous corrective and unique technique requiring minimal patient compliance is put forward with refinements developed during a period of years.