Support Vector Machines (SVMs) classification learning is a powerful paradigm to investigate inverse input-output relationship of a specific problem according to some available and representative dataset. In particular, SVMs are able to identify even non-linear relationship by mapping non-linearly separable data into potentially linearly separable one through families of spatial transformation (kernel trick). With respect to this, several parameters (i.e., kernel function and its internal parameters) have to be tuned; however the optimal configuration is usually difficult to be defined a-priori.In this paper, a hyper-solution framework for SVM classification is presented. The main idea is to perform, simultaneously, three different SVM-based classification learning tasks: Model Selection, Multiple Kernel Learning and Ensemble Learning. The meta-heuristic known as Genetic Algorithms (GA) has been proposed to search for the most reliable final hyper-classifier (an SVM with a basic kernel, an SVM with a combination of kernel, or an ensemble of different SVMs, respectively), and the corresponding optimal configuration.We have applied the proposed framework on a critical and quite complex problem: the on-line assessment of structural health of aircraft fuselage panels, a crucial task both in military and civilian settings. In particular, the framework has been used to implement a diagnosis task, that is detecting a possible damage and identifying the structural component involved, according to the strain field measured through a monitoring sensor network deployed on the helicopter fuselage panels.Finite Elements (FE) simulation has been configured to simulate the response of a real panel to different damages. The resulting simulated strain fields have been used to build a dataset. Results obtained through 3 folds-cross validation proved the framework is reliable. Finally, when compared to results obtained by the authors in a previous work based on Artificial Neural Networks (ANN) classification learning paradigm, the proposed SVM framework proved to be more effective and reliable.

Human cytomegalovirus (HCMV) infection is associated with a series of direct and indirect effects following renal transplantation. However, the presence of HCMV in the kidney and its relationship with acute rejection and long‐term graft function remain to be fully elucidated. Sixty‐two biopsies derived from 30 renal transplant recipients with signs of clinical rejection were analyzed for HCMV using a sensitive in situ DNA hybridization method. Biopsies were also subjected to staining with anti‐C4d antibodies and an anti‐caspase 3 antibody to detect humoral rejection and apoptosis, respectively. In 21 patients, serial serum creatinine levels over 5 years of follow‐up were analyzed. HCMV DNA was detected in biopsies from 21/30 (70%) of the patients and 32/62 (52%) of the individual biopsies. HCMV DNA was detected early after transplant and was localized to renal tubule epithelial cells but not associated with apoptosis. HCMV DNAemia developed within 2 weeks of detecting HCMV DNA in the biopsy in 53% of patients. Ninety percent of patients experiencing HCMV disease had HCMV DNA in their biopsy. HCMV DNA was equally distributed between patients with or without histological evidence of acute rejection and was detected more frequently in patients with peritubular C4d deposits. Creatinine levels at 12 months post‐transplant were significantly higher in patients with HCMV DNA and remained elevated over the 5 years of follow‐up. HCMV DNA is frequently detected in renal tubular epithelial cells early after renal transplantation, precedes DNAemia and is associated with poor long‐term graft function. J. Med. Virol. 82:85–93, 2010. © 2009 Wiley‐Liss, Inc.

OBJECTIVETo determine the extent to which computer‐aided ultrasonography of the prostate (HistoScanningTM, Advanced Medical Diagnostics, Waterloo, Belgium) can identify tumour foci that correspond to a volume of ≥0.50 mL.PATIENTS AND METHODSBetween September 2004 and February 2006, 29 men were HistoScanned before scheduled radical prostatectomy. The three‐dimensional raw (grey‐scaled) data required for HistoScanning analysis were acquired by transrectal ultrasonography, and analysed using organ‐specific tissue‐characterization algorithms which form the core of the HistoScanning technology. The HistoScanning analysis results were compared with the histology of the whole‐mounted prostate, step‐sectioned sagittally at 5‐mm intervals, and each slide analysed by 5 × 5 mm grid analysis.RESULTSOf 29 patients, 13 had histology unknown to those evaluating the HistoScanning data. With 0.50 mL as the lower threshold for delineating and visualizing cancer volume, HistoScanning correctly predicted the presence of all 12 lesions that were subsequently confirmed to occupy ≥0.50 mL. In addition three lesions were predicted as being present and of ≥0.50 mL. These three lesions were subsequently confirmed to be present but were ≤0.50 mL on histopathological review. Thus, using the clinically accepted volume threshold of 0.50 mL, the sensitivity, specificity, positive and negative predictive value of HistoScanning were 12/12, 13/16 (82%), 12/15 (80%) and 12/12, respectively, for the cancer foci analysed.CONCLUSIONSIn this preliminary study, HistoScanning accurately detected cancer foci of ≥0.50 mL; these encouraging results will need to be verified in a larger group of patients.

We report a rare complication of cesarean section in a 46-year-old woman presenting with incontinence. The patient was noted at cystoscopy to have a lesion on the posterior wall of the bladder. Histologic examination of the biopsied lesion demonstrated endocervical tissue, and subsequent magnetic resonance imaging revealed a vesicocervical fistula. She was treated by open excision of the fistula and repair of the bladder and cervix with omental interposition. Only 16 cases of vesicocervical fistulas have been previously reported, and this is the first to demonstrate the finding on magnetic resonance imaging.