3D Intervertebral disc localization and segmentation from MR images by data-driven regression and classification

In this paper we propose a new fully-automatic method for localizing and segmenting 3D intervertebral discs from MR images, where the two problems are solved in a unified data-driven regression and classification framework. We estimate the output (image displacements for localization, or fg/bg labels for segmentation) of image points by exploiting both training data and geometric constraints simultaneously. The problem is formulated in a unified objective function which is then solved globally and efficiently. We validate our method on MR images of 25 patients. Taking manually labeled data as the ground truth, our method achieves a mean localization error of 1.3 mm, a mean Dice metric of 87%, and a mean surface distance of 1.3 mm. Our method can be applied to other localization and segmentation tasks.

Fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images via a learning-based method

In this paper, we address the problems of fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images. We propose a learning-based, unified random forest regression and classification framework to tackle these two problems. More specifically, in the first stage, the localization of 3D vertebral bodies is solved with random forest regression where we aggregate the votes from a set of randomly sampled image patches to get a probability map of the center of a target vertebral body in a given image. The resultant probability map is then further regularized by Hidden Markov Model (HMM) to eliminate potential ambiguity caused by the neighboring vertebral bodies. The output from the first stage allows us to define a region of interest (ROI) for the segmentation step, where we use random forest classification to estimate the likelihood of a voxel in the ROI being foreground or background. The estimated likelihood is combined with the prior probability, which is learned from a set of training data, to get the posterior probability of the voxel. The segmentation of the target vertebral body is then done by a binary thresholding of the estimated probability. We evaluated the present approach on two openly available datasets: 1) 3D T2-weighted spine MR images from 23 patients and 2) 3D spine CT images from 10 patients. Taking manual segmentation as the ground truth (each MR image contains at least 7 vertebral bodies from T11 to L5 and each CT image contains 5 vertebral bodies from L1 to L5), we evaluated the present approach with leave-one-out experiments. Specifically, for the T2-weighted MR images, we achieved for localization a mean error of 1.6 mm, and for segmentation a mean Dice metric of 88.7% and a mean surface distance of 1.5 mm, respectively. For the CT images we achieved for localization a mean error of 1.9 mm, and for segmentation a mean Dice metric of 91.0% and a mean surface distance of 0.9 mm, respectively.

Reverberation and the parodic: an invitation to the spaces of sound

Jacques Rancière in The Politics of Aesthetics speaks of artistic practices ‘as ways of ‘doing and making’ that intervene in the general distribution of ways of doing and making’ (2013: 8). ‘Reverberation’ in the various dimensions explored by this paper is the compelling and parodic force, which signals the transformative potential of the spaces of music, word and sound collaborations. This paper will present the mixed impulse of parody as repetition with difference in Deleuze’s sense, or ironic ‘trans-contextualisation’ (Hutcheon 2000: 32), contextualised by Foucault’s heterotopic thought, Steve Reich’s minimalist music, and Brian Eno’s recognition of ambient sound in 1975 (Howard 2004: 91). Also explored is Hutcheon’s investigation of the etymology of parody as ‘counter-song’, which suggests intimacy and accord. The latter understanding of parody will be of particular importance in a discussion of New York-based band, The National.

Evaluation and comparison of 3D intervertebral disc localization and segmentation methods for 3D T2 MR data: A grand challenge.

The evaluation of changes in Intervertebral Discs (IVDs) with 3D Magnetic Resonance (MR) Imaging (MRI) can be of interest for many clinical applications. This paper presents the evaluation of both IVD localization and IVD segmentation methods submitted to the Automatic 3D MRI IVD Localization and Segmentation challenge, held at the 2015 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2015) with an on-site competition. With the construction of a manually annotated reference data set composed of 25 3D T2-weighted MR images acquired from two different studies and the establishment of a standard validation framework, quantitative evaluation was performed to compare the results of methods submitted to the challenge. Experimental results show that overall the best localization method achieves a mean localization distance of 0.8 mm and the best segmentation method achieves a mean Dice of 91.8%, a mean average absolute distance of 1.1 mm and a mean Hausdorff distance of 4.3 mm, respectively. The strengths and drawbacks of each method are discussed, which provides insights into the performance of different IVD localization and segmentation methods.

Constraints, segmentation, services, satisfaction and loyalty relating to park visitation.

Nature parks provide substantial recreation opportunities for the community. Improved park use through better knowledge of visits and what constrains people from visiting parks was the focus of this research. Certain park services affect different market segments’ experience; the experience and economic benefits in turn affect the loyalty of visitors.

Age related motivational segmentation of wine consumption in a hospitality setting

The wine industry is a multi-billion product value category worldwide with a significant part being sales through hospitality service providers. Although wine sales add considerably to the profitability of many restaurants, hotels, bars and other hospitality establishments, few studies have been conducted into wine purchasing behaviour within hospitality settings. This study identifies the factors that influence consumers to purchase wine and attempts to demonstrate how the basic demographic characteristic of age is a useful variable for segmentation purposes. The study reveals that there are six dominant factors that influence wine purchasing behaviour and that significant differences in purchase motivation exist between three age segments, 18 to 25 years, 26 to 34 years and 34+years. The results of this research have significant implications for hospitality operators who, with a basic knowledge of the demographic characteristics of their guests, can develop marketing strategies to maximise the sale of wine and wine products

Australians' organic food beliefs, demographics and values

Purpose – To examine consumers' beliefs about organic foods and their relationship with socio-demographics and self-transcendence (universal, benevolence) personal values.

Design/methodology/approach – A random questionnaire-based mail survey of 500 Australian (Victorian) adults (58 per cent response) was used. The questionnaire included items on organic food beliefs, the importance of self-transcendence values as guiding principles in life, and socio-demographics. Statistical analyses included cross-tabulations of organic food beliefs by socio-demographics and multiple regression analyses of positive organic food beliefs with personal value and socio-demographic items as the independent variables.

Findings – The majority of participants believed organic food to be healthier, tastier and better for the environment than conventional food. However, expense and lack of availability were strong barriers to the purchasing of organic foods. Generally, women were more positive about organic food than men (e.g. women were more likely to agree that organic food has more vitamins/minerals than conventional food). The personal value factor related to nature, environment and equality was the dominant predictor of positive organic food beliefs, followed by sex. These predictors accounted for 11 per cent of the variance.

Research limitations/implications – A survey response bias needs to be taken into account. However, the response rate was adequate for reporting and differences in age and education between participants and the Victorian population were taken into account in data presentation. Future understanding of consumers' use of organic foods will require the inclusion of a fairly extensive set of potential influences.

Practical implications – Communication appeals based on psychographics may be a more effective way to alter consumers' beliefs about organic foods than those based on demographic segmentation.

Originality/value – To the best of one's knowledge, this is the first study to examine the relationship between personal values, socio-demographics and organic food beliefs in a random population sample. This study is relevant to producers, processors and retailers of organic food and those involved with food and agricultural policy.

Cultural sustainability of the arts through cross cultural market segmentation

The cultural characteristics attributed to individuals in their country of birth are likely to change through immigration and acculturation processes taking place in the host country. Immigrants are likely to develop their own unique cultural styles through a blending of their old culture and the host culture. With slightly less than half of the population born overseas or with at least one parent born overseas, and with some 200 languages Australia has one of the most cosmopolitan populations in the world, with a relatively small population of 20 million. This paper considers the cross cultural nature of the Australian population and the sustainability of culture through the Arts. This paper also considers the marketing of the arts from a cross cultural segmentation perspective. In so doing the paper identifies segmentation issues associated with cross cultural segmentation.

Allocative and informational pricing roles in MBA program choice

This paper reports on a study of how prospective and current MBA students (n = 699) made tradeoffs between tuition price and other variables in choosing a university program in the Australian market. Two price segments were identified: price-negative and price-positive. The price-positive segment constituted 13 per cent of the sample. The behaviour of the two price segments is interpreted in relation to the allocative and informational roles of price. Price-positive respondents were found to be more concerned with the reputational characteristics of universities and programs in making their choice. Age, enrolment mode, and residential state were found to be associated with segment membership. The results suggest that an MBA by distance education can be regarded as a prestige product for some market segments.

Who are "innovators" and do they matter?: A critical review of the evidence supporting the targeting of “innovative” consumers

Purpose – This paper aims to bring together and evaluate the reasons that have historically been advanced to justify the heavy emphasis on innovative consumers within the general context of the adoption of products and services, and to assess the strategic benefits to be gained from targeting such market segments.

Design/methodology/approach – The approach is critical review and analysis of the published
literature.

Findings – This paper finds that, although the benefits of identifying innovative early adopters are not as strong and clear-cut as is often claimed, they are still sufficient to warrant further research into methods that will accurately identify them and predict their purchasing behaviour.

Practical implications – Targeting strategies should distinguish carefully between truly innovative consumers and other early adopters. The costs of identifying them in a particular market need to be weighed against the potential benefits.

Originality/value – Although many studies have attempted to address the question of what drives individual adoption behaviour, the rationale for that focus has not been well established and is rarely critiqued. In clarifying the situation, this paper should provide guidance for academic researchers and marketing planners.

Trends in consumer segmentation

This paper reviews academic and practitioner literature to identify some of the emerging trends in consumer segmentation. Our review suggests that a number of specialised segmentations have recently emerged, each utilising different techniques, methodologies and data inputs relevant to their respective strategic intent.

Choosing ICT? A segmentation analysis of students' preferences for hybrid study mode

Students’ acceptance and use of ICT-based learning needs to be understood in terms of their preferences for alternatives such as face-to-face (FtF) or print-based learning. This paper reports on an investigation of students’ preferences for hybrid study modes. Cluster analysis was used to identify segments of students that had distinctive preferences for combinations of FtF, print and web-based study modes. Five segments were identified. These segments were distinguishable on some demographic and situational characteristics. The size and nature of the segments have implications for the hybrid modes offered by universities and the extent to which students’ may embrace the ICT-based innovations designed by educators.

Tourism and recreation in natural environments : an empirical analysis of visitor satisfaction

A trend in tourism patterns is the desire by tourists to spend more time enjoying unspoilt, natural environments. Leisure experiences in parks can provide many benefits which include promoting positive emotional, intellectual and social experiences which result in high levels of wellness in communities with long-term benefits. However, the resultant growing number of national park visitors has created a need for effective and efficient decision suppOli tools to assist park managers to administer resources, assess planning decisions, cater for an increased range of users, avoid user conflicts and minimise negative impacts on the environment. The aim of this paper is to determine the extent to which manageable variables predict park visitor satisfaction, and in so doing develop a better understanding of park visitors and their leisure experiences in parks. This study is based on a sample of 11,387 face to face interviews at 34 major parks in Victoria, Australia. The study uses cluster analysis, factor analysis and structural equation modelling to develop a segmentation approach to model and analyse visitor satisfaction. Seven well differentiated segments have been developed; constructs relating to park visitation have also been produced. The study highlights that different combinations of park facilities and resources are important in determining the satisfaction of park visitors from different segments.

Empirical evaluation of segmentation algorithms for lung modelling

Lung modelling has emerged as a useful method for diagnosing lung diseases. Image segmentation is an important part of lung modelling systems. The ill-defined nature of image segmentation makes automated lung modelling difficult. Also, low resolution of lung images further increases the difficulty of the lung image segmentation. It is therefore important to identify a suitable segmentation algorithm that can enhance lung modelling accuracies. This paper investigates six image segmentation algorithms, used in medical imaging, and also their application to lung modelling. The algorithms are: normalised cuts, graph, region growing, watershed, Markov random field, and mean shift. The performance of the six segmentation algorithms is determined through a set of experiments on realistic 2D CT lung images. An experimental procedure is devised to measure the performance of the tested algorithms. The measured segmentation accuracies as well as execution times of the six algorithms are then compared and discussed.