Predicting prostate tumour location from multiparametric MRI using Gaussian kernel support vector machines: a preliminary study

The performance of a support vector machine (SVM) algorithm was investigated to predict prostate tumour location using multi-parametric MRI (mpMRI) data. The purpose was to obtain information of prostate tumour location for the implementation of bio-focused radiotherapy. In vivo mpMRI data were collected from 16 patients prior to radical prostatectomy. Sequences included T2-weighted imaging, diffusion-weighted imaging and dynamic contrast enhanced imaging. In vivo mpMRI was registered with ‘ground truth’ histology, using ex vivo MRI as an intermediate registration step to improve accuracy. Prostate contours were delineated by a radiation oncologist and tumours were annotated on histology by a pathologist. Five patients with minimal imaging artefacts were selected for this study. A Gaussian kernel SVM was trained and tested on different patient data subsets. Parameters were optimised using leave-oneout cross validation. Signal intensities of mpMRI were used as features and histology annotations as true labels. Prediction accuracy, as well as area under the curve (AUC) of the receiver operating characteristics (ROC) curve, were used to assess performance. Results demonstrated the prediction accuracy ranged from 70.4 to 87.1% and AUC of ROC ranged from 0.81 to 0.94. Additional investigations showed the apparent diffusion coefficient map from diffusion weighted imaging was the most important imaging modality for predicting tumour location. Future work will incorporate additional patient data into the framework to increase the sensitivity and specificity of the model, and will be extended to incorporate predictions of biological characteristics of the tumour which will be used in bio-focused radiotherapy optimisation.     

Simplified Scaling for Life Change Events

Abstract

A relatively simple interval scaling method for adjustment to life change events was compared to the original, more difficult, proportionate scaling method. Ranking of life events by both methods was extremely similar. Evidence also was found that today Americans scale several minor life change events as requiring greater adjustment than that estimated for these events a decade earlier.     

Isoarenarol,A New Protein Kinase Inhibitor from the Marine Sponge Dysidea arenaria

The novel sesquiterpene hydroquinone isoarenarol (1) and the known compound arenarol (2) were isolated from extracts of the marine sponge Dysidea arenaria Bergquist as part of a search for new protein kinase inhibitors. Both 1 and 2 showed potent and selective protein kinase inhibition in vitro.     

Microscopic and Spectroscopic Analyses of Chlorhexidine Tolerance in Delftia acidovorans Biofilms

The physicochemical responses of Delftia acidovorans biofilms exposed to the commonly used antimicrobial chlorhexidine (CHX) were examined in this study. A CHX-sensitive mutant (MIC, 1.0 μg ml⁻¹) was derived from a CHX-tolerant (MIC, 15.0 μg ml⁻¹) D. acidovorans parent strain using transposon mutagenesis. D. acidovorans mutant (MT51) and wild-type (WT15) strain biofilms were cultivated in flow cells and then treated with CHX at sub-MIC and inhibitory concentrations and examined by confocal laser scanning microscopy (CLSM), scanning transmission X-ray microscopy (STXM), and infrared (IR) spectroscopy. Specific morphological, structural, and chemical compositional differences between the CHX-treated and -untreated biofilms of both strains were observed. Apart from architectural differences, CLSM revealed a negative effect of CHX on biofilm thickness in the CHX-sensitive MT51 biofilms relative to those of the WT15 strain. STXM analyses showed that the WT15 biofilms contained two morphochemical cell variants, whereas only one type was detected in the MT51 biofilms. The cells in the MT51 biofilms bioaccumulated CHX to a similar extent as one of the cell types found in the WT15 biofilms, whereas the other cell type in the WT15 biofilms did not bioaccumulate CHX. STXM and IR spectral analyses revealed that CHX-sensitive MT51 cells accumulated the highest levels of CHX. Pretreating biofilms with EDTA promoted the accumulation of CHX in all cells. Thus, it is suggested that a subpopulation of cells that do not accumulate CHX appear to be responsible for greater CHX resistance in D. acidovorans WT15 biofilm in conjunction with the possible involvement of bacterial membrane stability.