Applied Graph Theory in Computer Vision and Pattern Recognition

This book will serve as a foundation for a variety of useful applications of graph theory to computer vision, pattern recognition, and related areas. It covers a representative set of novel graph-theoretic methods for complex computer vision and pattern recognition tasks. The first part of the book presents the application of graph theory to low-level processing of digital images such as a new method for partitioning a given image into a hierarchy of homogeneous areas using graph pyramids, or a study of the relationship between graph theory and digital topology. Part II presents graph-theoretic learning algorithms for high-level computer vision and pattern recognition applications, including a survey of graph based methodologies for pattern recognition and computer vision, a presentation of a series of computationally efficient algorithms for testing graph isomorphism and related graph matching tasks in pattern recognition and a new graph distance measure to be used for solving graph matching problems. Finally, Part III provides detailed descriptions of several applications of graph-based methods to real-world pattern recognition tasks. It includes a critical review of the main graph-based and structural methods for fingerprint classification, a new method to visualize time series of graphs, and potential applications in computer network monitoring and abnormal event detection.

Crystalloids versus colloids for goal-directed fluid therapy in major surgery

INTRODUCTION: Perioperative hypovolemia arises frequently and contributes to intestinal hypoperfusion and subsequent postoperative complications. Goal-directed fluid therapy might reduce these complications. The aim of this study was to compare the effects of goal-directed administration of crystalloids and colloids on the distribution of systemic, hepatosplanchnic, and microcirculatory (small intestine) blood flow after major abdominal surgery in a clinically relevant pig model. METHODS: Twenty-seven pigs were anesthetized and mechanically ventilated and underwent open laparotomy. They were randomly assigned to one of three treatment groups: the restricted Ringer lactate (R-RL) group (n = 9) received 3 mL/kg per hour of RL, the goal-directed RL (GD-RL) group (n = 9) received 3 mL/kg per hour of RL and intermittent boluses of 250 mL of RL, and the goal-directed colloid (GD-C) group (n = 9) received 3 mL/kg per hour of RL and boluses of 250 mL of 6% hydroxyethyl starch (130/0.4). The latter two groups received a bolus infusion when mixed venous oxygen saturation was below 60% ('lockout' time of 30 minutes). Regional blood flow was measured in the superior mesenteric artery and the celiac trunk. In the small bowel, microcirculatory blood flow was measured using laser Doppler flowmetry. Intestinal tissue oxygen tension was measured with intramural Clark-type electrodes. RESULTS: After 4 hours of treatment, arterial blood pressure, cardiac output, mesenteric artery flow, and mixed oxygen saturation were significantly higher in the GD-C and GD-RL groups than in the R-RL group. Microcirculatory flow in the intestinal mucosa increased by 50% in the GD-C group but remained unchanged in the other two groups. Likewise, tissue oxygen tension in the intestine increased by 30% in the GD-C group but remained unchanged in the GD-RL group and decreased by 18% in the R-RL group. Mesenteric venous glucose concentrations were higher and lactate levels were lower in the GD-C group compared with the two crystalloid groups. CONCLUSIONS: Goal-directed colloid administration markedly increased microcirculatory blood flow in the small intestine and intestinal tissue oxygen tension after abdominal surgery. In contrast, goal-directed crystalloid and restricted crystalloid administrations had no such effects. Additionally, mesenteric venous glucose and lactate concentrations suggest that intestinal cellular substrate levels were higher in the colloid-treated than in the crystalloid-treated animals. These results support the notion that perioperative goal-directed therapy with colloids might be beneficial during major abdominal surgery.

Goal-directed colloid administration improves the microcirculation of healthy and perianastomotic colon

BACKGROUND: The aim of this study was to compare the effects of goal-directed colloid fluid therapy with goal-directed crystalloid and restricted crystalloid fluid therapy on healthy and perianastomotic colon tissue in a pig model of colon anastomosis surgery. METHODS: Pigs (n = 27, 9 per group) were anesthetized and mechanically ventilated. A hand-sewn colon anastomosis was performed. The animals were subsequently randomized to one of the following treatments: R-RL group, 3 ml x kg(-1) x h(-1) Ringer lactate (RL); GD-RL group, 3 ml x kg(-1) x h(-1) RL + bolus 250 ml of RL; GD-C group, 3 ml x kg(-1) x h(-1) RL + bolus 250 ml of hydroxyethyl starch (HES 6%, 130/0.4). A fluid bolus was administered when mixed venous oxygen saturation dropped below 60%. Intestinal tissue oxygen tension and microcirculatory blood flow were measured continuously. RESULTS: After 4 h of treatment, tissue oxygen tension in healthy colon increased to 150 +/- 31% in group GD-C versus 123 +/- 40% in group GD-RL versus 94 +/- 23% in group R-RL (percent of postoperative baseline values, mean +/- SD; P < 0.01). Similarly perianastomotic tissue oxygen tension increased to 245 +/- 93% in the GD-C group versus 147 +/- 58% in the GD-RL group and 116 +/- 22% in the R-RL group (P < 0.01). Microcirculatory flow was higher in group GD-C in healthy colon. CONCLUSIONS: Goal-directed colloid fluid therapy significantly increased microcirculatory blood flow and tissue oxygen tension in healthy and injured colon compared to goal-directed or restricted crystalloid fluid therapy.

Cyclic automorphic graph decompositions

Chapter 1 introduces the tools and mechanics necessary for this report. Basic definitions and topics of graph theory which pertain to the report and discussion of automorphic decompositions will be covered in brief detail. An automorphic decomposition D of a graph H by a graph G is a G-decomposition of H such that the intersection of graph (D) @H. H is called the automorhpic host, and G is the automorphic divisor. We seek to find classes of graphs that are automorphic divisors, specifically ones generated cyclically. Chapter 2 discusses the previous work done mainly by Beeler. It also discusses and gives in more detail examples of automorphic decompositions of graphs. Chapter 2 also discusses labelings and their direct relation to cyclic automorphic decompositions. We show basic classes of graphs, such as cycles, that are known to have certain labelings, and show that they also are automorphic divisors. In Chapter 3, we are concerned with 2-regular graphs, in particular rCm, r copies of the m-cycle. We seek to show that rCm has a ρ-labeling, and thus is an automorphic divisor for all r and m. we discuss methods including Skolem type difference sets to create cycle systems and their correlation to automorphic decompositions. In the Appendix, we give classes of graphs known to be graceful and our java code to generate ρ-labelings on rCm.