Tracking the invisible hand: Convergence of double auctions to competitive equilibrium

Economics is the science of want and scarcity. We show that want andscarcity, operating within a simple exchange institution (double auction),are sufficient for an economy consisting of multiple inter--related marketsto attain competitive equilibrium (CE). We generalize Gode and Sunder's(1993a, 1993b) single--market finding to multi--market economies, andexplore the role of the scarcity constraint in convergence of economies to CE.When the scarcity constraint is relaxed by allowing arbitrageurs in multiple markets to enter speculative trades, prices still converge to CE,but allocative efficiency of the economy drops. \\Optimization by individual agents, often used to derive competitive equilibria,are unnecessary for an actual economy to approximately attain such equilibria.From the failure of humans to optimize in complex tasks, one need not concludethat the equilibria derived from the competitive model are descriptivelyirrelevant. We show that even in complex economic systems, such equilibriacan be attained under a range of surprisingly weak assumptions about agentbehavior.

A data-dependent skeleton estimate and a scale-sensitive dimension for classification

The classical binary classification problem is investigatedwhen it is known in advance that the posterior probability function(or regression function) belongs to some class of functions. We introduceand analyze a method which effectively exploits this knowledge. The methodis based on minimizing the empirical risk over a carefully selected``skeleton'' of the class of regression functions. The skeleton is acovering of the class based on a data--dependent metric, especiallyfitted for classification. A new scale--sensitive dimension isintroduced which is more useful for the studied classification problemthan other, previously defined, dimension measures. This fact isdemonstrated by performance bounds for the skeleton estimate in termsof the new dimension.

Pattern recognition ecological niche models fit to presence-only and presence-absence data

1. Identifying the boundary of a species' niche from observational and environmental data is a common problem in ecology and conservation biology and a variety of techniques have been developed or applied to model niches and predict distributions. Here, we examine the performance of some pattern-recognition methods as ecological niche models (ENMs). Particularly, one-class pattern recognition is a flexible and seldom used methodology for modelling ecological niches and distributions from presence-only data. The development of one-class methods that perform comparably to two-class methods (for presence/absence data) would remove modelling decisions about sampling pseudo-absences or background data points when absence points are unavailable. 2. We studied nine methods for one-class classification and seven methods for two-class classification (five common to both), all primarily used in pattern recognition and therefore not common in species distribution and ecological niche modelling, across a set of 106 mountain plant species for which presence-absence data was available. We assessed accuracy using standard metrics and compared trade-offs in omission and commission errors between classification groups as well as effects of prevalence and spatial autocorrelation on accuracy. 3. One-class models fit to presence-only data were comparable to two-class models fit to presence-absence data when performance was evaluated with a measure weighting omission and commission errors equally. One-class models were superior for reducing omission errors (i.e. yielding higher sensitivity), and two-classes models were superior for reducing commission errors (i.e. yielding higher specificity). For these methods, spatial autocorrelation was only influential when prevalence was low. 4. These results differ from previous efforts to evaluate alternative modelling approaches to build ENM and are particularly noteworthy because data are from exhaustively sampled populations minimizing false absence records. Accurate, transferable models of species' ecological niches and distributions are needed to advance ecological research and are crucial for effective environmental planning and conservation; the pattern-recognition approaches studied here show good potential for future modelling studies. This study also provides an introduction to promising methods for ecological modelling inherited from the pattern-recognition discipline.

Class effect of pharmacotherapy in bipolar disorder: fact or misbelieff?

BACKGROUND: Anecdotal reports suggests that most clinicians treat medications as belonging to a class with regard to all therapeutic indications; this means that the whole 'class' of drugs is considered to possesses a specific therapeutic action. The present article explores the possible existence of a true 'class effect' for agents available for the treatment of bipolar disorder. METHODS: We reviewed the available treatment data from randomized controlled trials (RCTs) and explored 16 'agent class'/'treatment issue' cases for bipolar disorder. Four classes of agents were examined: first-generation antipsychotics (FGAs), second-generation antipsychotics (SGAs), antiepileptics and antidepressants, with respect to their efficacy on four treatment issues of bipolar disorder (BD) (acute mania, acute bipolar depression, maintenance against mania, maintenance against depression). RESULTS: From the 16 'agent class'/' treatment issue' cases, only 3 possible class effects were detected, and they all concerned acute mania and antipsychotics. Four effect cases have not been adequately studied (FGAs against acute bipolar depression and in maintenance protection from depression, and antidepressants against acute mania and protection from mania) and they all concern treatment cases with a high risk of switching to the opposite pole, thus research in these areas is poor. There is no 'class effect' at all concerning antiepileptics. CONCLUSIONS: The available data suggest that a 'class effect' is the exception rather than the rule in the treatment of BD. However, the possible presence of a 'class effect' concept discourages clinicians from continued scientific training and reading. Focused educational intervention might be necessary to change this attitude.

Taking on new challenges in multi-word unit processing for Machine Translation

This paper discusses the qualitativecomparative evaluation performed on theresults of two machine translation systemswith different approaches to the processing ofmulti-word units. It proposes a solution forovercoming the difficulties multi-word unitspresent to machine translation by adopting amethodology that combines the lexicongrammar approach with OpenLogos ontologyand semantico-syntactic rules. The paper alsodiscusses the importance of a qualitativeevaluation metrics to correctly evaluate theperformance of machine translation engineswith regards to multi-word units.

On the transcriptional role of NLRC5 and the function of NLRC5-driven MHC class I expression in the immune system

Major histocompatibility complex (MHC) molecules are of crucial importance for the immune system to recognize and defend the body against external attacks. Foreign antigens are presented by specialized cells, called antigen presenting cells, to T lymphocytes in the context of MHC molecules, thereby inducing T cell activation. In addition, MHC molecules are essential for Natural Killer (NK) cell biology, playing a role in NK cell education and activation. Recently, the NOD-like receptor (NLR) family member NLRC5 (NLR caspase recruitment domain containing protein 5) was found to act as transcriptional regulator of MHC class I, in particular in T and NK cells. Its role in MHC class I expression is however minor in dendritic cells (DCs). This raised the question of whether inflammatory conditions, which augment the levels of NLRC5 in DCs, could increase its contribution to MHC class I expression. Our work shows that MHC class I transcript and intracellular levels depend on NLRC5, while its role in MHC class I surface expression is instead negligible. We describe however a general salvage mechanism that enables cells with low intracellular MHC class I levels to nevertheless maintain relatively high MHC class I on the cell surface. In addition, we lack a thorough understanding of NLRC5 target gene specificity and mechanism of action. Our work delineates the unique consensus sequence in MHC class I promoters required for NLRC5 recruitment and pinpoints conserved features conferring its specificity. Furthermore, through genome-wide analyses, we confirm that NLRC5 regulates classical MHC class I genes and identify novel target genes all encoding non-classical MHC class I molecules exerting an array of functions in immunity and tolerance. We finally asked why a dedicated factor co-regulates MHC class I expression specifically in T and NK lymphocytes. We show that deregulated NLRC5 expression affects the education of NK cells and alters the crosstalk between T and NK cells, leading to NK cell-mediated killing of T lymphocytes. Altogether this thesis work brings insights into molecular and physiological aspects of NLRC5 function, which might help understand certain aspects of immune responses and disorders. -- Les molécules du complexe majeur d'histocompatibilité (CMH) sont essentielles au système immunitaire pour l'initiation de la réponse immunitaire. En effet, l'activation des lymphocytes T nécessite la reconnaissance d'un antigène étranger présenté par les cellules présentatrices d'antigènes sur une molécule du CMH. Les molécules du CMH ont également un rôle fondamental pour la fonction des cellules Natural Killer (NK) puisqu'elles sont nécessaires à leur processus d'éducation et d'activation. Récemment, NLRC5 (NLR caspase recruitment domain containing protein 5), un membre de la famille des récepteurs de type NOD (NLRs), a été décrit comme un facteur de transactivation de l'expression des gènes du CMH de classe I. A l'état basai, cette fonction transcriptionnelle est essentielle dans les lymphocytes T et NK, alors que ce rôle reste mineur pour l'expression des molécules du CMH de classe I dans les cellules dendritiques (DCs). Dans des conditions inflammatoires, l'expression de NLRC5 augmente dans les DCs. Notre travail démontre que, dans ces conditions, les transcrits et les niveaux intracellulaires des molécules du CMH de classe I augmentent aussi d'une façon dépendante de NLRC5. A contrario, le rôle de NLRC5 sur les niveaux de molécules de surface reste minoritaire. Cette observation nous a conduits à l'identification d'un mécanisme général de compensation qui permet aux cellules de maintenir des niveaux relativement élevés de molécules de CMH de class I à leur surface malgré de faibles niveaux intracellulaires. De plus, il semblait nécessaire de s'orienter vers une approche plus globale afin de déterminer l'étendue de la fonction transcriptionnelle de NLRC5. Par une approche du génome entier, nous avons pu décrire une séquence consensus conservée présente dans les promoteurs des gènes du CMH de classe I, sur laquelle NLRC5 est spécifiquement recruté. Nous avons pu également identifier de nouveaux gènes cibles codant pour des molécules de CMH de classe I non classiques impliqués dans l'immunité et la tolérance. Finalement, nous nous sommes demandé quel est l'intérêt d'avoir un facteur transcriptionnel, en l'occurrence NLRC5, qui orchestre l'expression du CMH de classe I dans les lymphocytes T et NK. Nous montrons que la dérégulation de l'expression de NLRC5 affecte l'éducation des cellules NK et conduit à la mort cellulaire des lymphocytes T médiée par les cellules NK. Dans l'ensemble ce travail de thèse contribue à la caractérisation du rôle de NLRC5, tant au niveau moléculaire que physiologique, ce qui présente un intérêt dans le cadre de la compréhension de certains aspects physiopathologique de la réponse immunitaire.

Using digital RNA counting and flow cytometry to compare mRNA with protein expression in acute leukemias.

BACKGROUND: The diagnosis of malignant hematologic diseases has become increasingly complex during the last decade. It is based on the interpretation of results from different laboratory analyses, which range from microscopy to gene expression profiling. Recently, a method for the analysis of RNA phenotypes has been developed, the nCounter technology (Nanostring® Technologies), which allows for simultaneous quantification of hundreds of RNA molecules in biological samples. We evaluated this technique in a Swiss multi-center study on eighty-six samples from acute leukemia patients. METHODS: mRNA and protein profiles were established for normal peripheral blood and bone marrow samples. Signal intensities of the various tested antigens with surface expression were similar to those found in previously performed Affymetrix microarray analyses. Acute leukemia samples were analyzed for a set of twenty-two validated antigens and the Pearson Correlation Coefficient for nCounter and flow cytometry results was calculated. RESULTS: Highly significant values between 0.40 and 0.97 were found for the twenty-two antigens tested. A second correlation analysis performed on a per sample basis resulted in concordant results between flow cytometry and nCounter in 44-100% of the antigens tested (mean = 76%), depending on the number of blasts present in a sample, the homogeneity of the blast population, and the type of leukemia (AML or ALL). CONCLUSIONS: The nCounter technology allows for fast and easy depiction of a mRNA profile from hematologic samples. This technology has the potential to become a valuable tool for the diagnosis of acute leukemias, in addition to multi-color flow cytometry.

Genes outside The Hla Region affecting Susceptibility to Type 1 Diabetes - The Role of Iddm2 and Iddm9 in the Finnish Population

Tyypin 1 diabeteksen perinnöllinen alttius Suomessa - HLA-alueen ulkopuolisten alttiuslokusten IDDM2 ja IDDM9 rooli taudin periytymisessä HLA-alue, joka sijaitsee kromosomissa 6p21.3, vastaa noin puolesta perinnöllisestä alttiudesta sairastua tyypin 1 diabetekseen. Myös HLA-alueen ulkopuolisten lokusten on todettu liittyvän sairausalttiuteen. Näistä kolmen lokuksen on varmistettu olevan todellisia alttiuslokuksia ja lisäksi useiden muiden, vielä varmistamattomien lokusten, on todettu liittyvän sairausalttiuteen. Tässä tutkimuksessa 12:n HLA-alueen ulkopuolisen alttiuslokuksen kytkentä tyypin 1 diabetekseen tutkittiin käyttäen 107:aa suomalaista multiplex-perhettä. Jatkotutkimuksessa analysoitiin IDDM9-alueen kytkentä ja assosiaatio sairauteen laajennetuissa perhemateriaaleissa sekä IDDM2-alueen mahdollinen interaktio HLA-alueen kanssa sairauden muodostumisessa. Lisäksi suoritettiin IDDM2-alueen suojaavien haplotyyppien alatyypitys tarkoituksena tutkia eri haplotyyppien käyttökelpoisuutta sairastumisriskin tarkempaa ennustamista varten. Ensimmäisessä kytkentätutkimuksessa ei löytynyt koko genomin tasolla merkitsevää tai viitteellistä kytkentää tutkituista HLA-alueen ulkopuolisista lokuksista. Voimakkain havaittu nimellisen merkitsevyyden tavoittava kytkentä nähtiin IDDM9-alueen markkerilla D3S3576 (MLS=1.05). Tutkimuksessa ei kyetty varmistamaan tai sulkemaan pois aiempia kytkentähavaintoja tutkituilla lokuksilla, mutta IDDM9-alueen jatkotutkimuksessa havaittu voimakas kytkentä (MLS=3.4) ja merkitsevä assosiaatio (TDT p=0.0002) viittaa vahvasti siihen, että 3q21-alueella sijaitsee todellinen tyypin 1 diabeteksen alttiusgeeni, jolloin alueen kattava assosiaatiotutkimus olisi perusteltu jatkotoimenpide. Sairauteen altistava IDDM2-alueen MspI-2221 genotyyppi CC oli nimellisesti yleisempi matalan tai kohtalaisen HLA-sairastumisriskin diabeetikoilla, verrattuna korkean HLA-riskin potilaisiin (p=0.05). Myös genotyyppijakauman vertailu osoitti merkitsevää eroa ryhmien välillä (p=0.01). VNTR-haplotyyppitutkimus osoitti, että IIIA/IIIA-homotsygootin sairaudelta suojaava vaikutus on merkitsevästi voimakkaampi kuin muiden luokka III:n genotyypeillä. Nämä tulokset viittaavat IDDM2-HLA -vuorovaikutukseen sekä siihen että IDDM2-alueen haplotyyppien välillä esiintyy etiologista heterogeniaa. Tämän johdosta IDDM2-alueen haplotyyppien tarkempi määrittäminen voisi tehostaa tyypin 1 diabeteksen riskiarviointia.

Differential evolution based classification with pool of distances and aggregation operators

The objective of this thesis is to develop and generalize further the differential evolution based data classification method. For many years, evolutionary algorithms have been successfully applied to many classification tasks. Evolution algorithms are population based, stochastic search algorithms that mimic natural selection and genetics. Differential evolution is an evolutionary algorithm that has gained popularity because of its simplicity and good observed performance. In this thesis a differential evolution classifier with pool of distances is proposed, demonstrated and initially evaluated. The differential evolution classifier is a nearest prototype vector based classifier that applies a global optimization algorithm, differential evolution, to determine the optimal values for all free parameters of the classifier model during the training phase of the classifier. The differential evolution classifier applies the individually optimized distance measure for each new data set to be classified is generalized to cover a pool of distances. Instead of optimizing a single distance measure for the given data set, the selection of the optimal distance measure from a predefined pool of alternative measures is attempted systematically and automatically. Furthermore, instead of only selecting the optimal distance measure from a set of alternatives, an attempt is made to optimize the values of the possible control parameters related with the selected distance measure. Specifically, a pool of alternative distance measures is first created and then the differential evolution algorithm is applied to select the optimal distance measure that yields the highest classification accuracy with the current data. After determining the optimal distance measures for the given data set together with their optimal parameters, all determined distance measures are aggregated to form a single total distance measure. The total distance measure is applied to the final classification decisions. The actual classification process is still based on the nearest prototype vector principle; a sample belongs to the class represented by the nearest prototype vector when measured with the optimized total distance measure. During the training process the differential evolution algorithm determines the optimal class vectors, selects optimal distance metrics, and determines the optimal values for the free parameters of each selected distance measure. The results obtained with the above method confirm that the choice of distance measure is one of the most crucial factors for obtaining higher classification accuracy. The results also demonstrate that it is possible to build a classifier that is able to select the optimal distance measure for the given data set automatically and systematically. After finding optimal distance measures together with optimal parameters from the particular distance measure results are then aggregated to form a total distance, which will be used to form the deviation between the class vectors and samples and thus classify the samples. This thesis also discusses two types of aggregation operators, namely, ordered weighted averaging (OWA) based multi-distances and generalized ordered weighted averaging (GOWA). These aggregation operators were applied in this work to the aggregation of the normalized distance values. The results demonstrate that a proper combination of aggregation operator and weight generation scheme play an important role in obtaining good classification accuracy. The main outcomes of the work are the six new generalized versions of previous method called differential evolution classifier. All these DE classifier demonstrated good results in the classification tasks.

Dynamic ecosystems under anthropogenic stress : how does macrotidal sandy fauna respond to green tides?

Highly dynamic systems, often considered as resilient systems, are characterised by abiotic and biotic processes under continuous and strong changes in space and time. Because of this variability, the detection of overlapping anthropogenic stress is challenging. Coastal areas harbour dynamic ecosystems in the form of open sandy beaches, which cover the vast majority of the world’s ice-free coastline. These ecosystems are currently threatened by increasing human-induced pressure, among which mass-development of opportunistic macroalgae (mainly composed of Chlorophyta, so called green tides), resulting from the eutrophication of coastal waters. The ecological impact of opportunistic macroalgal blooms (green tides, and blooms formed by other opportunistic taxa), has long been evaluated within sheltered and non-tidal ecosystems. Little is known, however, on how more dynamic ecosystems, such as open macrotidal sandy beaches, respond to such stress. This thesis assesses the effects of anthropogenic stress on the structure and the functioning of highly dynamic ecosystems using sandy beaches impacted by green tides as a study case. The thesis is based on four field studies, which analyse natural sandy sediment benthic community dynamics over several temporal (from month to multi-year) and spatial (from local to regional) scales. In this thesis, I report long-lasting responses of sandy beach benthic invertebrate communities to green tides, across thousands of kilometres and over seven years; and highlight more pronounced responses of zoobenthos living in exposed sandy beaches compared to semi-exposed sands. Within exposed sandy sediments, and across a vertical scale (from inshore to nearshore sandy habitats), I also demonstrate that the effects of the presence of algal mats on intertidal benthic invertebrate communities is more pronounced than that on subtidal benthic invertebrate assemblages, but also than on flatfish communities. Focussing on small-scale variations in the most affected faunal group (i.e. benthic invertebrates living at low shore), this thesis reveals a decrease in overall beta-diversity along a eutrophication-gradient manifested in the form of green tides, as well as the increasing importance of biological variables in explaining ecological variability of sandy beach macrobenthic assemblages along the same gradient. To illustrate the processes associated with the structural shifts observed where green tides occurred, I investigated the effects of high biomasses of opportunistic macroalgae (Ulva spp.) on the trophic structure and functioning of sandy beaches. This work reveals a progressive simplification of sandy beach food web structure and a modification of energy pathways over time, through direct and indirect effects of Ulva mats on several trophic levels. Through this thesis I demonstrate that highly dynamic systems respond differently (e.g. shift in δ13C, not in δ15N) and more subtly (e.g. no mass-mortality in benthos was found) to anthropogenic stress compared to what has been previously shown within more sheltered and non-tidal systems. Obtaining these results would not have been possible without the approach used through this work; I thus present a framework coupling field investigations with analytical approaches to describe shifts in highly variable ecosystems under human-induced stress.

Deviations of Governance In IT Multi-Sourcing: A Case Study

IT outsourcing (ITO) refers to the shift of IT/IS activities from internal to external of an organization. In prior research, the governance of ITO is recognized with persistent strategic importance for practice, because it is tightly related to ITO success. Under the rapid transformation of global market, the evolving practice of ITO requires updated knowledge on effective governance. However, research on ITO governance is still under developed due to the lack of integrated theoretical frameworks and the variety of empirical settings besides dyadic client-vendor relationships. Especially, as multi-sourcing has become an increasingly common practice in ITO, its new governance challenges must be attended by both ITO researchers and practitioners. To address this research gap, this study aims to understand multi-sourcing governance with an integrated theoretical framework incorporating both governance structure and governance mechanisms. The focus is on the emerging deviations among formal, perceived and practiced governance. With an interpretive perspective, a single case study is conducted with mixed methods of Social Network Analysis (SNA) and qualitative inquiries. The empirical setting embraces one client firm and its two IT suppliers for IT infrastructure services. The empirical material is analyzed at three levels: within one supplier firm, between the client and one supplier, and among all three firms. Empirical evidences, at all levels, illustrate various deviations in governance mechanisms, with which emerging governance structures are shaped. This dissertation contributes to the understanding of ITO governance in three domains: the governance of ITO in general, the governance of multi-sourcing in particular, and research methodology. For ITO governance in general, this study has identified two research strands of governance structure and governance mechanisms, and integrated both concepts under a unified framework. The composition of four research papers contributes to multi-sourcing research by illustrating the benefits of zooming in and out across the multilateral relationships with different aspects and scopes. Methodologically, the viability and benefit of mixed-method is illustrated and confirmed for both researchers and practitioners.

The evaluation of a predialysis class on client knowledge and attitude toward compliant behaviours

In this quasi-experimental study, the theory of reasoned action was used as a conceptual framework to assess the outcome effect of a predialysis class. A pretest, posttest design was used to determine changes in client knowledge about their condition and its treatment, and their intention, attitudes and social norm towards compliant behaviours. The related compliant behaviours were following a low-salt diet and taking medications as proscribed. Thirty-eight End Stage Renal Diseases (ESRD) clients were self-selected into the treatment or control groups. Both groups received the standard predialysis education from members of the multidisciplinary renal team. In addition, the treatment group also attended the predialysis class. Subjects' health locus of control, anxiety and demographic variables were measured as possible extraneous variables. Study subjects from both groups demonstrated a high internal and powerful others health locus of control and a normal range of anxiety. Although not statistically significant ill = .64), the experimental group demonstrated higher knowledge level and greater intention to follow a low salt diet UL= .73). They developed more significantly positive attitudes towards following a low salt diet and increased subjective norm influence after attending the predialysis class. Attending the predialysis class did not have an effect on subjects' intentions, attitudes or subjective norm towards taking medications as prescribed. Conclusion: The predialysis class was only marginally effective in increasing client knowledge, but influenced clients' attitudes towards following a low-salt diet. Based on the results, recommendations for improvements to the class have been suggested.

A crisis of social democracy : organized labour and the NDP in an era of neoliberalism

The NDP was founded out of the ashes of the Co-Operative Commonwealth Federation to cooperate with the Canadian Labour Congress to become the 'political arm of organized labour' in Canada. The NDP has long claimed they are the party which represents the policy goals of organized labour in Canada: that the NDP alone will fight for trade union rights, and will fight for Canadian workers. Divergent Paths is an examination of the links between the labour movement and the ND P in an era ofneo-liberalism. Provincial NDP governments have become increasingly neoliberal in their ideological orientation, and have often proved to be no friend to the labour movement when they hold office. The Federal party has never held power, nor have they ever formed the Official Opposition. This thesis charts the progress of the federal NDP as they become more neoliberal from 1988 to 2006, and shows how this trend effects the links between the NDP and labour. Divergent Paths studies each federal election from 1988 to 2006, looking at the interactions between Labour and the NDP during these elections. Elections provide critical junctions to study discourse - party platforms, speeches, and other official documents can be used to examine discourse. Extensive newspaper searches were used to follow campaign events and policy speeches. Studying the party's discourse can be used to determine the ideological orientation of the party itself: the fact that the party's discourse has become neoliberal is a sure sign that the party itself is neoliberal. The NDP continues to drive towards the centre of the political spectrum in an attempt to gain multi-class support. The NDP seems more interested in gaining seats at any cost, rather then promoting the agenda of Labour. As the party attempts to open up to more multi-class support, Labour becomes increasingly marginalised in the party. A rift which arguably started well before the 1988 election was exacerbated during that election; labour encouraged the NDP to campaign solely on the issue of Free Trade, and the NDP did not. The 1993 election saw the rift between the two grow even further as the Federal NDP suffered major blowbacks from the actions of the Ontario NDP. The 1997 and 2000 elections saw the NDP make a deliberate move to the centre of the political spectrum which increasingly marginalised labour. In the 2004 election, Jack Layton made no attempt to move the party back to the left; and in 2006 the link between labour and the NDP was perhaps irreparably damaged when the CAW endorsed the Liberal party in a strategic voting strategy, and the CLC did not endorse the NDP. The NDP is no longer a reliable ally of organized labour. The Canadian labour movement must decide wether the NDP can be 'salvaged' or if the labour movement should end their alliance with the NDP and engage in a new political project.

Scoliosis curve type classification from 3D trunk image

Adolescent idiopathic scoliosis (AIS) is a deformity of the spine manifested by asymmetry and deformities of the external surface of the trunk. Classification of scoliosis deformities according to curve type is used to plan management of scoliosis patients. Currently, scoliosis curve type is determined based on X-ray exam. However, cumulative exposure to X-rays radiation significantly increases the risk for certain cancer. In this paper, we propose a robust system that can classify the scoliosis curve type from non invasive acquisition of 3D trunk surface of the patients. The 3D image of the trunk is divided into patches and local geometric descriptors characterizing the surface of the back are computed from each patch and forming the features. We perform the reduction of the dimensionality by using Principal Component Analysis and 53 components were retained. In this work a multi-class classifier is built with Least-squares support vector machine (LS-SVM) which is a kernel classifier. For this study, a new kernel was designed in order to achieve a robust classifier in comparison with polynomial and Gaussian kernel. The proposed system was validated using data of 103 patients with different scoliosis curve types diagnosed and classified by an orthopedic surgeon from the X-ray images. The average rate of successful classification was 93.3% with a better rate of prediction for the major thoracic and lumbar/thoracolumbar types.

Non invasive classification system of scoliosis curve types using least-squares support vector machines

Objective To determine scoliosis curve types using non invasive surface acquisition, without prior knowledge from X-ray data. Methods Classification of scoliosis deformities according to curve type is used in the clinical management of scoliotic patients. In this work, we propose a robust system that can determine the scoliosis curve type from non invasive acquisition of the 3D back surface of the patients. The 3D image of the surface of the trunk is divided into patches and local geometric descriptors characterizing the back surface are computed from each patch and constitute the features. We reduce the dimensionality by using principal component analysis and retain 53 components using an overlap criterion combined with the total variance in the observed variables. In this work, a multi-class classifier is built with least-squares support vector machines (LS-SVM). The original LS-SVM formulation was modified by weighting the positive and negative samples differently and a new kernel was designed in order to achieve a robust classifier. The proposed system is validated using data from 165 patients with different scoliosis curve types. The results of our non invasive classification were compared with those obtained by an expert using X-ray images. Results The average rate of successful classification was computed using a leave-one-out cross-validation procedure. The overall accuracy of the system was 95%. As for the correct classification rates per class, we obtained 96%, 84% and 97% for the thoracic, double major and lumbar/thoracolumbar curve types, respectively. Conclusion This study shows that it is possible to find a relationship between the internal deformity and the back surface deformity in scoliosis with machine learning methods. The proposed system uses non invasive surface acquisition, which is safe for the patient as it involves no radiation. Also, the design of a specific kernel improved classification performance.