Speeding up the EM algorithm for mixture model-based segmentation of magnetic resonance images

Mixture models implemented via the expectation-maximization (EM) algorithm are being increasingly used in a wide range of problems in pattern recognition such as image segmentation. However, the EM algorithm requires considerable computational time in its application to huge data sets such as a three-dimensional magnetic resonance (MR) image of over 10 million voxels. Recently, it was shown that a sparse, incremental version of the EM algorithm could improve its rate of convergence. In this paper, we show how this modified EM algorithm can be speeded up further by adopting a multiresolution kd-tree structure in performing the E-step. The proposed algorithm outperforms some other variants of the EM algorithm for segmenting MR images of the human brain. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

Conservative endodontic management of teeth associated with extensive periapical pathology: report of two cases

Traditionally, long-term calcium hydroxide dressings have been recommended for the conservative management of large periapical lesions. However, calcium hydroxide therapy has some disadvantages such as variability of treatment time, difficulties with patient follow-up and prolonged treatment periods that increase the risk of root canal contamination via microleakage and crown fractures. This paper reports the healing of large periapical lesions following conservative non-surgical treatment with calcium hydroxide dressings.

Erosive effects of common beverages on extracted premolar teeth

Background: Dental erosion is highly prevalent today, and acidic drinks are thought to be an important cause. The aim of the present investigation was to determine the erosive potential of a range of common beverages on extracted human teeth. Methods: The beverages were tested for their individual pHs using a pH meter. The clinical effects of the most erosive beverages were determined by the degree of etching and Vickers microhardness of enamel. Results: The results showed that many common beverages have pHs sufficiently low to cause enamel erosion. Lime juice concentrate (pH 2.1) had the lowest pH, followed by Coca-cola and Pepsi (both with pH 2.3) and Lucozade (pH 2.5). The erosive potential of these beverages was demonstrated by the deep etching of the enamel after five minutes. The Vickers Hardness of enamel was reduced by about 50 per cent is the case of lime juice (p < 0.001) and 24 per cent in the case of Coca-cola (p < 0.004). Addition of saliva to 50 per cent (v/v) of Coca-cola completely reversed the erosive effects on the enamel. Conclusion: Although only a few of the beverages with the lowest pHs were tested, the present study showed that the most acidic drinks had the greatest erosive effects on enamel. While saliva was protective against erosion, relatively large volumes were required to neutralize the acidity.

Temperature changes in dental pulp associated with use of power grinding equipment on equine teeth

Objective To quantify the temperature changes in the dental pulp associated with equine dental procedures using power grinding equipment. Design A matrix experimental design with replication on the same sample was followed to allow the following independent variables to be assessed: horse age (young or old), tooth type (premolar or molar), powered grinding instrument (rotating disc or die grinder), grinding time (15 or 20 seconds) and the presence or absence of water coolant. Procedure Sound premolar and molar teeth from a 6-year-old horse and a 15-year-old horse, which had been removed postmortem, were sectioned parallel to the occlusal plane to allow placement of a miniature thermocouple at the level of the dental pulp. The maximum temperature increase, the time taken to reach this maximum and the cooling time were measured (n=10 in each study). The teeth were placed in a vice and the instrument used on the tooth as per clinical situation. Results Significant differences were recorded for horse age (P < 0.001), instrument type (P < 0.001), grinding time (P < 0.001) and presence or absence of coolant (P < 0.001). There was no significant difference for tooth type. Conclusion Thermal insult to the dental pulp from the use of power instruments poses a significant risk to the tooth. This risk can be reduced or eliminated by appropriate selection of treatment time and by the use of water irrigation as a coolant. The increased dentine thickness in older horses appears to mitigate against thermal injury from frictional heat.

The use of unwrapped phase in MR image segmentation: A preliminary study

This paper considers the problem of tissue classification in 3D MRI. More specifically, a new set of texture features, based on phase information, is used to perform the segmentation of the bones of the knee. The phase information provides a very good discrimination between the bone and the surrounding tissues, but is usually not used due to phase unwrapping problems. We present a method to extract textural information from the phase that does not require phase unwrapping. The textural information extracted from the magnitude and the phase can be combined to perform tissue classification, and used to initialise an active shape model, leading to a more precise segmentation.

Degenerate dentition of the dugong (Dugong dugon), or why a grazer does not need teeth: morphology, occlusion and wear of mouthparts

The morphology and functional occlusion of the cheekteeth of 57 dugongs Dugong dugon of both sexes were examined using reflected light and scanning electron microscopy, radiography, hardness testing and skull manipulation. The functional morphology of the horny oral pads was also described. Mouthparts and body size allometry was examined for ontogenetic and gender-related trends. We found that the worn erupted cheekteeth of the dugong are simple flat pegs composed of soft degenerative dentine. During occlusion, the mandible moves in a mainly antero-lingual direction, with the possibility of mandibular retraction in some individuals. Anterior parts of the cheektooth row may become non-functional as a dugong ages. As a function of body size, dugong cheekteeth are extremely small compared with those of other mammalian herbivores, and with other hindgut fermenters in particular. The morphology, small size and occlusal variability of the cheekteeth suggest that there has not been strong selective pressure acting to maintain an effective dentition. In contrast, great development of the horny pads and associated skull parameters and their lower size variability suggest that the horny pads may have assumed the major role in food comminution.

A fuzzy approach to texture segmentation

The texture segmentation techniques are diversified by the existence of several approaches. In this paper, we propose fuzzy features for the segmentation of texture image. For this purpose, a membership function is constructed to represent the effect of the neighboring pixels on the current pixel in a window. Using these membership function values, we find a feature by weighted average method for the current pixel. This is repeated for all pixels in the window treating each time one pixel as the current pixel. Using these fuzzy based features, we derive three descriptors such as maximum, entropy, and energy for each window. To segment the texture image, the modified mountain clustering that is unsupervised and fuzzy c-means clustering have been used. The performance of the proposed features is compared with that of fractal features.

Automatic texture segmentation for texture-based image retrieval

Texture-segmentation is the crucial initial step for texture-based image retrieval. Texture is the main difficulty faced to a segmentation method. Many image segmentation algorithms either can’t handle texture properly or can’t obtain texture features directly during segmentation which can be used for retrieval purpose. This paper describes an automatic texture segmentation algorithm based on a set of features derived from wavelet domain, which are effective in texture description for retrieval purpose. Simulation results show that the proposed algorithm can efficiently capture the textured regions in arbitrary images, with the features of each region extracted as well. The features of each textured region can be directly used to index image database with applications as texture-based image retrieval.

Automatic initialisation of 3D deformable models for cartilage segmentation

Deformable models are a highly accurate and flexible approach to segmenting structures in medical images. The primary drawback of deformable models is that they are sensitive to initialisation, with accurate and robust results often requiring initialisation close to the true object in the image. Automatically obtaining a good initialisation is problematic for many structures in the body. The cartilages of the knee are a thin elastic material that cover the ends of the bone, absorbing shock and allowing smooth movement. The degeneration of these cartilages characterize the progression of osteoarthritis. The state of the art in the segmentation of the cartilage are 2D semi-automated algorithms. These algorithms require significant time and supervison by a clinical expert, so the development of an automatic segmentation algorithm for the cartilages is an important clinical goal. In this paper we present an approach towards this goal that allows us to automatically providing a good initialisation for deformable models of the patella cartilage, by utilising the strong spatial relationship of the cartilage to the underlying bone.