An automated machine vision system for the histological grading of cervical intraepithelial neoplasia (CIN)

The histological grading of cervical intraepithelial neoplasia (CIN) remains subjective, resulting in inter- and intra-observer variation and poor reproducibility in the grading of cervical lesions. This study has attempted to develop an objective grading system using automated machine vision. The architectural features of cervical squamous epithelium are quantitatively analysed using a combination of computerized digital image processing and Delaunay triangulation analysis; 230 images digitally captured from cases previously classified by a gynaecological pathologist included normal cervical squamous epithelium (n = 30), koilocytosis (n = 46), CIN 1 (n = 52), CIN 2 (n = 56), and CIN 3 (n=46). Intra- and inter-observer variation had kappa values of 0.502 and 0.415, respectively. A machine vision system was developed in KS400 macro programming language to segment and mark the centres of all nuclei within the epithelium. By object-oriented analysis of image components, the positional information of nuclei was used to construct a Delaunay triangulation mesh. Each mesh was analysed to compute triangle dimensions including the mean triangle area, the mean triangle edge length, and the number of triangles per unit area, giving an individual quantitative profile of measurements for each case. Discriminant analysis of the geometric data revealed the significant discriminatory variables from which a classification score was derived. The scoring system distinguished between normal and CIN 3 in 98.7% of cases and between koilocytosis and CIN 1 in 76.5% of cases, but only 62.3% of the CIN cases were classified into the correct group, with the CIN 2 group showing the highest rate of misclassification. Graphical plots of triangulation data demonstrated the continuum of morphological change from normal squamous epithelium to the highest grade of CIN, with overlapping of the groups originally defined by the pathologists. This study shows that automated location of nuclei in cervical biopsies using computerized image analysis is possible. Analysis of positional information enables quantitative evaluation of architectural features in CIN using Delaunay triangulation meshes, which is effective in the objective classification of CIN. This demonstrates the future potential of automated machine vision systems in diagnostic histopathology. Copyright (C) 2000 John Wiley and Sons, Ltd.

The Voice as Transcursive Inscriber: The Relation of Body and Instrument Understood through the Workings of a Machine

This article examines the relationship of the body with a musical instrument; specifically it looks at the vital threshold conditions that occur during the interplay of voice and instrument. By examining the work ‘IKAS’ (1982) for solo saxophone by German composer Hans-Joachim Hespos, the unusual timbral relationships created between vocal and instrumental sounds are exposed. I argue that this particular work highlights the performer/instrument relation as one marked by Gilles Deleuze’s notion of the workings of a machine and a machine’s relation to a ‘flow’, in particular a machine’s function with view to the break in the flow. By turning towards Deleuze’s concept of the machine, this article offers a slightly different vocabulary for music analysis, one that more easily encompasses certain works of the twentieth century, specifically those that are more timbre- than pitch-based.

Epidermal Langerhans Cells are Dispensable for Humoral and Cell-Mediated Immunity Elicited by Gene Gun Immunization.

Gene gun immunization, i.e., bombardment of skin with DNA-coated particles, is an efficient method for the administration of DNA vaccines. Direct transfection of APC or cross-presentation of exogenous Ag acquired from transfected nonimmune cells enables MHC-I-restricted activation of CD8(+) T cells. Additionally, MHC-II-restricted presentation of exogenous Ag activates CD4(+) Th cells. Being the principal APC in the epidermis, Langerhans cells (LC) seem ideal candidates to accomplish these functions. However, the dependence on LC of gene gun-induced immune reactions has not yet been demonstrated directly. This was primarily hampered by difficulties to discriminate the contributions of LC from those of other dermal dendritic cells. To address this problem, we have used Langerin-diphtheria toxin receptor knockin mice that allow for selective inducible ablation of LC. LC deficiency, even over the entire duration of experiments, did not affect any of the gene gun-induced immune functions examined, including proliferation of CD4(+) and CD8(+) T cells, IFN-gamma secretion by spleen cells, Ab production, CTL activity, and development of protective antitumor immunity.

Reconfiguring Older Bodies in the Prison Time Machine

It is by mapping an area that the geographer comes to understand the contours and formations of a place. The “place” in this case is the prison world. This article serves to map moments in prison demonstrating how “old” female bodies are performed under the prison gaze. In this article I will illustrate how older women subvert, negotiate, or invoke discourse as a means of reinscribing the normalizing discourses that serve to confine and define older women's experiences in prison. Female elders in prison become defined and confined by regimes of femininity and ageism. They have to endure symbolic and actual intrusions of physical privacy, which serve to remind them of what they were, where they are, and what they have become. This article will critically explore the complexity and contradictions of time use in prison and how they impact on embodied identities. By incorporating the voices of elders, I hope to draw out the contradictions and dilemmas which they experience, thereby illustrating the relationship between time, their involvement in doing time, and the performance of time in a total institution (see Goffman, 1961), and the relationship between temporality and existence. The stories of the women show how their identities are caught within the movement and motion of time and space, both in terms of the time of “the real” on the outside and within prison time. This is the in-between space of carceral time within which women live and which they negotiate. It is by being caught in this network of carceral time that they are constantly being “remade” as their body/performance of identities alters within it. While only a small percentage of the female prison population in the United Kingdom are in later life, one has to question why criminological and gerontological literature fail to address the needs of a growing significant minority.

Support vector machine classification for large data sets via minimum enclosing ball clustering

Support vector machine (SVM) is a powerful technique for data classification. Despite of its good theoretic foundations and high classification accuracy, normal SVM is not suitable for classification of large data sets, because the training complexity of SVM is highly dependent on the size of data set. This paper presents a novel SVM classification approach for large data sets by using minimum enclosing ball clustering. After the training data are partitioned by the proposed clustering method, the centers of the clusters are used for the first time SVM classification. Then we use the clusters whose centers are support vectors or those clusters which have different classes to perform the second time SVM classification. In this stage most data are removed. Several experimental results show that the approach proposed in this paper has good classification accuracy compared with classic SVM while the training is significantly faster than several other SVM classifiers.

A hierarchical multiclass support vector machine incorporated with holistic triple learning units

This paper proposes a new hierarchical learning structure, namely the holistic triple learning (HTL), for extending the binary support vector machine (SVM) to multi-classification problems. For an N-class problem, a HTL constructs a decision tree up to a depth of A leaf node of the decision tree is allowed to be placed with a holistic triple learning unit whose generalisation abilities are assessed and approved. Meanwhile, the remaining nodes in the decision tree each accommodate a standard binary SVM classifier. The holistic triple classifier is a regression model trained on three classes, whose training algorithm is originated from a recently proposed implementation technique, namely the least-squares support vector machine (LS-SVM). A major novelty with the holistic triple classifier is the reduced number of support vectors in the solution. For the resultant HTL-SVM, an upper bound of the generalisation error can be obtained. The time complexity of training the HTL-SVM is analysed, and is shown to be comparable to that of training the one-versus-one (1-vs.-1) SVM, particularly on small-scale datasets. Empirical studies show that the proposed HTL-SVM achieves competitive classification accuracy with a reduced number of support vectors compared to the popular 1-vs-1 alternative.