Improved fault diagnosis in multivariate systems using regression-based reconstruction

Subspace monitoring has recently been proposed as a condition monitoring tool that requires considerably fewer variables to be analysed compared to dynamic principal component analysis (PCA). This paper analyses subspace monitoring in identifying and isolating fault conditions, which reveals that the existing work suffers from inherent limitations if complex fault senarios arise. Based on the assumption that the fault signature is deterministic while the monitored variables are stochastic, the paper introduces a regression-based reconstruction technique to overcome these limitations. The utility of the proposed fault identification and isolation method is shown using a simulation example and the analysis of experimental data from an industrial reactive distillation unit.

The classification and diagnosis of erythrocytosis

An absolute erythrocytosis is present when the red cell mass is raised and the haematocrit is elevated above prescribed limits. Causes of an absolute erythrocytosis can be primary where there is an intrinsic problem in the bone marrow and secondary where there an event outside the bone marrow driving erythropoiesis. This can further be divided into congenital and acquired causes. There remain an unexplained group idiopathic erythrocytosis. Investigation commencing with thorough history taking and examination and then investigation depending on initial features is required. Clear simple criteria for polycythaemia vera are now defined. Those who do not fulfil these criteria require further investigation depending on the clinical scenario and initial results. The erythropoietin level provides some guidance as to the direction in which to proceed and the order and extent of investigation necessary in an individual patient. It should thus be possible to make an accurate diagnosis in the majority of patients.

Microbiologic Diagnosis of Prosthetic Shoulder Infection by Use of Implant Sonication

We recently described a sonication technique for the diagnosis of prosthetic knee and hip infections. We compared periprosthetic tissue culture to implant sonication followed by sonicate fluid culture for the diagnosis of prosthetic shoulder infection. One hundred thirty-six patients undergoing arthroplasty revision or resection were studied; 33 had definite prosthetic shoulder infections and 2 had probable prosthetic shoulder infections. Sonicate fluid culture was more sensitive than periprosthetic tissue culture for the detection of definite prosthetic shoulder infection (66.7 and 54.5%, respectively; P = 0.046). The specificities were similar (98.0% and 95.1%, respectively; P = 0.26). Propionibacterium acnes was the commonest species detected among culture-positive definite prosthetic shoulder infection cases by periprosthetic tissue culture (38.9%) and sonicate fluid culture (40.9%). All subjects from whom P. acnes was isolated from sonicate fluid were male. We conclude that sonicate fluid culture is useful for the diagnosis of prosthetic shoulder infection.

Ex vivo diagnosis of lung cancer using a Raman miniprobe.

Lung cancer is the most common cause of cancer death. The conventional method of confirming the diagnosis is bronchoscopy, inspecting the airways of the patient with a fiber optic endoscope. A number of studies have shown that Raman spectroscopy can diagnose lung cancer in vitro. In this study, Raman spectra were obtained from ex vivo normal and malignant lung tissue using a minifiber optic Raman probe suitable for insertion into the working channel of a bronchoscope. Shifted subtracted Raman spectroscopy was used to reduce the fluorescence from the lung tissue. Using principal component analysis with a leave-one-out analysis, the tissues were classified accurately. This novel technique has the potential to obtain Raman spectra from tumors from patients with lung cancer in vivo.

Assisted Diagnosis of Cervical Intraepithelial Neoplasia (CIN)

This paper introduces an automated computer- assisted system for the diagnosis of cervical intraepithelial neoplasia (CIN) using ultra-large cervical histological digital slides. The system contains two parts: the segmentation of squamous epithelium and the diagnosis of CIN. For the segmentation, to reduce processing time, a multiresolution method is developed. The squamous epithelium layer is first segmented at a low (2X) resolution. The boundaries are further fine tuned at a higher (20X) resolution. The block-based segmentation method uses robust texture feature vectors in combination with support vector machines (SVMs) to perform classification. Medical rules are finally applied. In testing, segmentation using 31 digital slides achieves 94.25% accuracy. For the diagnosis of CIN, changes in nuclei structure and morphology along lines perpendicular to the main axis of the squamous epithelium are quantified and classified. Using multi-category SVM, perpendicular lines are classified into Normal, CIN I, CIN II, and CIN III. The robustness of the system in term of regional diagnosis is measured against pathologists' diagnoses and inter-observer variability between two pathologists is considered. Initial results suggest that the system has potential as a tool both to assist in pathologists' diagnoses, and in training.