Fully Automatic Segmentation of Brain Tumor Images using Support Vector Machine Classiffication in Combination with Hierarchical Conditional Random Field Regularization

Delineating brain tumor boundaries from magnetic resonance images is an essential task for the analysis of brain cancer. We propose a fully automatic method for brain tissue segmentation, which combines Support Vector Machine classification using multispectral intensities and textures with subsequent hierarchical regularization based on Conditional Random Fields. The CRF regularization introduces spatial constraints to the powerful SVM classification, which assumes voxels to be independent from their neighbors. The approach first separates healthy and tumor tissue before both regions are subclassified into cerebrospinal fluid, white matter, gray matter and necrotic, active, edema region respectively in a novel hierarchical way. The hierarchical approach adds robustness and speed by allowing to apply different levels of regularization at different stages. The method is fast and tailored to standard clinical acquisition protocols. It was assessed on 10 multispectral patient datasets with results outperforming previous methods in terms of segmentation detail and computation times.

The Trypanosoma brucei MitoCarta and its regulation and splicing pattern during development

It has long been known that trypanosomes regulate mitochondrial biogenesis during the life cycle of the parasite; however, the mitochondrial protein inventory (MitoCarta) and its regulation remain unknown. We present a novel computational method for genome-wide prediction of mitochondrial proteins using a support vector machine-based classifier with approximately 90% prediction accuracy. Using this method, we predicted the mitochondrial localization of 468 proteins with high confidence and have experimentally verified the localization of a subset of these proteins. We then applied a recently developed parallel sequencing technology to determine the expression profiles and the splicing patterns of a total of 1065 predicted MitoCarta transcripts during the development of the parasite, and showed that 435 of the transcripts significantly changed their expressions while 630 remain unchanged in any of the three life stages analyzed. Furthermore, we identified 298 alternatively splicing events, a small subset of which could lead to dual localization of the corresponding proteins.

Tumor classification of six common cancer types based on proteomic profiling by MALDI imaging

In clinical diagnostics, it is of outmost importance to correctly identify the source of a metastatic tumor, especially if no apparent primary tumor is present. Tissue-based proteomics might allow correct tumor classification. As a result, we performed MALDI imaging to generate proteomic signatures for different tumors. These signatures were used to classify common cancer types. At first, a cohort comprised of tissue samples from six adenocarcinoma entities located at different organ sites (esophagus, breast, colon, liver, stomach, thyroid gland, n = 171) was classified using two algorithms for a training and test set. For the test set, Support Vector Machine and Random Forest yielded overall accuracies of 82.74 and 81.18%, respectively. Then, colon cancer liver metastasis samples (n = 19) were introduced into the classification. The liver metastasis samples could be discriminated with high accuracy from primary tumors of colon cancer and hepatocellular carcinoma. Additionally, colon cancer liver metastasis samples could be successfully classified by using colon cancer primary tumor samples for the training of the classifier. These findings demonstrate that MALDI imaging-derived proteomic classifiers can discriminate between different tumor types at different organ sites and in the same site.

A Food Recognition System for Diabetic Patients based on an Optimized Bag of Features Model

Computer vision-based food recognition could be used to estimate a meal's carbohydrate content for diabetic patients. This study proposes a methodology for automatic food recognition, based on the Bag of Features (BoF) model. An extensive technical investigation was conducted for the identification and optimization of the best performing components involved in the BoF architecture, as well as the estimation of the corresponding parameters. For the design and evaluation of the prototype system, a visual dataset with nearly 5,000 food images was created and organized into 11 classes. The optimized system computes dense local features, using the scale-invariant feature transform on the HSV color space, builds a visual dictionary of 10,000 visual words by using the hierarchical k-means clustering and finally classifies the food images with a linear support vector machine classifier. The system achieved classification accuracy of the order of 78%, thus proving the feasibility of the proposed approach in a very challenging image dataset.

Segmentation and Recognition of Multi-Food Meal Images for Carbohydrate Counting

In this paper, we propose novel methodologies for the automatic segmentation and recognition of multi-food images. The proposed methods implement the first modules of a carbohydrate counting and insulin advisory system for type 1 diabetic patients. Initially the plate is segmented using pyramidal mean-shift filtering and a region growing algorithm. Then each of the resulted segments is described by both color and texture features and classified by a support vector machine into one of six different major food classes. Finally, a modified version of the Huang and Dom evaluation index was proposed, addressing the particular needs of the food segmentation problem. The experimental results prove the effectiveness of the proposed method achieving a segmentation accuracy of 88.5% and recognition rate equal to 87%

Evaluation of Three State-of-the-Art Classifiers for Recognition of Activities of Daily Living from Smart Home Ambient Data

Smart homes for the aging population have recently started attracting the attention of the research community. The "health state" of smart homes is comprised of many different levels; starting with the physical health of citizens, it also includes longer-term health norms and outcomes, as well as the arena of positive behavior changes. One of the problems of interest is to monitor the activities of daily living (ADL) of the elderly, aiming at their protection and well-being. For this purpose, we installed passive infrared (PIR) sensors to detect motion in a specific area inside a smart apartment and used them to collect a set of ADL. In a novel approach, we describe a technology that allows the ground truth collected in one smart home to train activity recognition systems for other smart homes. We asked the users to label all instances of all ADL only once and subsequently applied data mining techniques to cluster in-home sensor firings. Each cluster would therefore represent the instances of the same activity. Once the clusters were associated to their corresponding activities, our system was able to recognize future activities. To improve the activity recognition accuracy, our system preprocessed raw sensor data by identifying overlapping activities. To evaluate the recognition performance from a 200-day dataset, we implemented three different active learning classification algorithms and compared their performance: naive Bayesian (NB), support vector machine (SVM) and random forest (RF). Based on our results, the RF classifier recognized activities with an average specificity of 96.53%, a sensitivity of 68.49%, a precision of 74.41% and an F-measure of 71.33%, outperforming both the NB and SVM classifiers. Further clustering markedly improved the results of the RF classifier. An activity recognition system based on PIR sensors in conjunction with a clustering classification approach was able to detect ADL from datasets collected from different homes. Thus, our PIR-based smart home technology could improve care and provide valuable information to better understand the functioning of our societies, as well as to inform both individual and collective action in a smart city scenario.

Differentiation of Diabetic Macular Edema From Pseudophakic Cystoid Macular Edema by Spectral-Domain Optical Coherence Tomography.

PURPOSE: To differentiate diabetic macular edema (DME) from pseudophakic cystoid macular edema (PCME) based solely on spectral-domain optical coherence tomography (SD-OCT). METHODS: This cross-sectional study included 134 participants: 49 with PCME, 60 with DME, and 25 with diabetic retinopathy (DR) and ME after cataract surgery. First, two unmasked experts classified the 25 DR patients after cataract surgery as either DME, PCME, or mixed-pattern based on SD-OCT and color-fundus photography. Then all 134 patients were divided into two datasets and graded by two masked readers according to a standardized reading-protocol. Accuracy of the masked readers to differentiate the diseases based on SD-OCT parameters was tested. Parallel to the masked readers, a computer-based algorithm was established using support vector machine (SVM) classifiers to automatically differentiate disease entities. RESULTS: The masked readers assigned 92.5% SD-OCT images to the correct clinical diagnose. The classifier-accuracy trained and tested on dataset 1 was 95.8%. The classifier-accuracy trained on dataset 1 and tested on dataset 2 to differentiate PCME from DME was 90.2%. The classifier-accuracy trained and tested on dataset 2 to differentiate all three diseases was 85.5%. In particular, higher central-retinal thickness/retinal-volume ratio, absence of an epiretinal-membrane, and solely inner nuclear layer (INL)-cysts indicated PCME, whereas higher outer nuclear layer (ONL)/INL ratio, the absence of subretinal fluid, presence of hard exudates, microaneurysms, and ganglion cell layer and/or retinal nerve fiber layer cysts strongly favored DME in this model. CONCLUSIONS: Based on the evaluation of SD-OCT, PCME can be differentiated from DME by masked reader evaluation, and by automated analysis, even in DR patients with ME after cataract surgery. The automated classifier may help to independently differentiate these two disease entities and is made publicly available.

Body mass index, hormone replacement therapy, and endometrial cancer risk: a meta-analysis

Background: Body mass index (BMI) is a risk factor for endometrial cancer. We quantified the risk and investigated whether the association differed by use of hormone replacement therapy (HRT), menopausal status, and histologic type. Methods: We searched MEDLINE and EMBASE (1966 to December 2009) to identify prospective studies of BMI and incident endometrial cancer. We did random-effects meta-analyses, meta-regressions, and generalized least square regressions for trend estimations assuming linear, and piecewise linear, relationships. Results: Twenty-four studies (17,710 cases) were analyzed; 9 studies contributed to analyses by HRT, menopausal status, or histologic type, all published since 2003. In the linear model, the overall risk ratio (RR) per 5 kg/m2 increase in BMI was 1.60 (95% CI, 1.52–1.68), P < 0.0001. In the piecewise model, RRs compared with a normal BMI were 1.22 (1.19–1.24), 2.09 (1.94–2.26), 4.36 (3.75–5.10), and 9.11 (7.26–11.51) for BMIs of 27, 32, 37, and 42 kg/m2, respectively. The association was stronger in never HRT users than in ever users: RRs were 1.90 (1.57–2.31) and 1.18 (95% CI, 1.06–1.31) with P for interaction ¼ 0.003. In the piecewise model, the RR in never users was 20.70 (8.28–51.84) at BMI 42 kg/m2, compared with never users at normal BMI. The association was not affected by menopausal status (P ¼ 0.34) or histologic type (P ¼ 0.26). Conclusions: HRT use modifies the BMI-endometrial cancer risk association. Impact: These findings support the hypothesis that hyperestrogenia is an important mechanism underlying the BMI-endometrial cancer association, whilst the presence of residual risk in HRT users points to the role of additional systems. Cancer Epidemiol Biomarkers Prev; 19(12); 3119–30.

Application and comparison of classification algorithms for recognition of Alzheimer's disease in electrical brain activity (EEG)

The early detection of subjects with probable Alzheimer's disease (AD) is crucial for effective appliance of treatment strategies. Here we explored the ability of a multitude of linear and non-linear classification algorithms to discriminate between the electroencephalograms (EEGs) of patients with varying degree of AD and their age-matched control subjects. Absolute and relative spectral power, distribution of spectral power, and measures of spatial synchronization were calculated from recordings of resting eyes-closed continuous EEGs of 45 healthy controls, 116 patients with mild AD and 81 patients with moderate AD, recruited in two different centers (Stockholm, New York). The applied classification algorithms were: principal component linear discriminant analysis (PC LDA), partial least squares LDA (PLS LDA), principal component logistic regression (PC LR), partial least squares logistic regression (PLS LR), bagging, random forest, support vector machines (SVM) and feed-forward neural network. Based on 10-fold cross-validation runs it could be demonstrated that even tough modern computer-intensive classification algorithms such as random forests, SVM and neural networks show a slight superiority, more classical classification algorithms performed nearly equally well. Using random forests classification a considerable sensitivity of up to 85% and a specificity of 78%, respectively for the test of even only mild AD patients has been reached, whereas for the comparison of moderate AD vs. controls, using SVM and neural networks, values of 89% and 88% for sensitivity and specificity were achieved. Such a remarkable performance proves the value of these classification algorithms for clinical diagnostics.

Comparison of partial least squares regression and principal component regression for pelvic shape prediction.

This paper studied two different regression techniques for pelvic shape prediction, i.e., the partial least square regression (PLSR) and the principal component regression (PCR). Three different predictors such as surface landmarks, morphological parameters, or surface models of neighboring structures were used in a cross-validation study to predict the pelvic shape. Results obtained from applying these two different regression techniques were compared to the population mean model. In almost all the prediction experiments, both regression techniques unanimously generated better results than the population mean model, while the difference on prediction accuracy between these two regression methods is not statistically significant (α=0.01).

Stereoselective pharmacokinetics of ketamine and norketamine after racemic ketamine or S-ketamine administration in Shetland ponies sedated with xylazine

The pharmacokinetics of ketamine and norketamine enantiomers after administration of intravenous (IV) racemic ketamine (R-/S-ketamine; 2.2mg/kg) or S-ketamine (1.1mg/kg) to five ponies sedated with IV xylazine (1.1mg/kg) were compared. The time intervals to assume sternal and standing positions were recorded. Arterial blood samples were collected before and 1, 2, 4, 6, 8 and 13min after ketamine administration. Arterial blood gases were evaluated 5min after ketamine injection. Plasma concentrations of ketamine and norketamine enantiomers were determined by capillary electrophoresis and were evaluated by non-linear least square regression analysis applying a monocompartmental model. The first-order elimination rate constant was significantly higher and elimination half-life and mean residence time were lower for S-ketamine after S-ketamine compared to R-/S-ketamine administration. The maximum concentration of S-norketamine was higher after S-ketamine administration. Time to standing position was significantly diminished after S-ketamine compared to R-/S-ketamine. Blood gases showed low-degree hypoxaemia and hypercarbia.

Stereoselective pharmacokinetics of ketamine and norketamine after racemic ketamine or S-ketamine administration during isoflurane anaesthesia in Shetland ponies

BACKGROUND: The arterial pharmacokinetics of ketamine and norketamine enantiomers after racemic ketamine or S-ketamine i.v. administration were evaluated in seven gelding ponies in a crossover study (2-month interval). METHODS: Anaesthesia was induced with isoflurane in oxygen via a face-mask and then maintained at each pony's individual MAC. Racemic ketamine (2.2 mg kg(-1)) or S-ketamine (1.1 mg kg(-1)) was injected in the right jugular vein. Blood samples were collected from the right carotid artery before and at 1, 2, 4, 8, 16, 32, 64, and 128 min after ketamine administration. Ketamine and norketamine enantiomer plasma concentrations were determined by capillary electrophoresis. Individual R-ketamine and S-ketamine concentration vs time curves were analysed by non-linear least square regression two-compartment model analysis using PCNonlin. Plasma disposition curves for R-norketamine and S-norketamine were described by estimating AUC, C(max), and T(max). Pulse rate (PR), respiratory rate (R(f)), tidal volume (V(T)), minute volume ventilation (V(E)), end-tidal partial pressure of carbon dioxide (PE'(CO(2))), and mean arterial blood pressure (MAP) were also evaluated. RESULTS: The pharmacokinetic parameters of S- and R-ketamine administered in the racemic mixture or S-ketamine administered separately did not differ significantly. Statistically significant higher AUC and C(max) were found for S-norketamine compared with R-norketamine in the racemic group. Overall, R(f), V(E), PE'(CO(2)), and MAP were significantly higher in the racemic group, whereas PR was higher in the S-ketamine group. CONCLUSIONS: Norketamine enantiomers showed different pharmacokinetic profiles after single i.v. administration of racemic ketamine in ponies anaesthetised with isoflurane in oxygen (1 MAC). Cardiopulmonary variables require further investigation.

The influence of muscle strength on the gait profile score (GPS) across different patients

BACKGROUND Muscle strength greatly influences gait kinematics. The question was whether this association is similar in different diseases. METHODS Data from instrumented gait analysis of 716 patients were retrospectively assessed. The effect of muscle strength on gait deviations, namely the gait profile score (GPS) was evaluated by means of generalised least square models. This was executed for seven different patient groups. The groups were formed according to the type of disease: orthopaedic/neurologic, uni-/bilateral affection, and flaccid/spastic muscles. RESULTS Muscle strength had a negative effect on GPS values, which did not significantly differ amongst the different patient groups. However, an offset of the GPS regression line was found, which was mostly dependent on the basic disease. Surprisingly, spastic patients, who have reduced strength and additionally spasticity in clinical examination, and flaccid neurologic patients showed the same offset. Patients with additional lack of trunk control (Tetraplegia) showed the largest offset. CONCLUSION Gait kinematics grossly depend on muscle strength. This was seen in patients with very different pathologies. Nevertheless, optimal correction of biomechanics and muscle strength may still not lead to a normal gait, especially in that of neurologic patients. The basic disease itself has an additional effect on gait deviations expressed as a GPS-offset of the linear regression line.

Prediction of soil organic carbon for Ethiopian highlands using soil spectroscopy

Soil spectroscopy was applied for predicting soil organic carbon (SOC) in the highlands of Ethiopia. Soil samples were acquired from Ethiopia’s National Soil Testing Centre and direct field sampling. The reflectance of samples was measured using a FieldSpec 3 diffuse reflectance spectrometer. Outliers and sample relation were evaluated using principal component analysis (PCA) and models were developed through partial least square regression (PLSR). For nine watersheds sampled, 20% of the samples were set aside to test prediction and 80% were used to develop calibration models. Depending on the number of samples per watershed, cross validation or independent validation were used.The stability of models was evaluated using coefficient of determination (R2), root mean square error (RMSE), and the ratio performance deviation (RPD). The R2 (%), RMSE (%), and RPD, respectively, for validation were Anjeni (88, 0.44, 3.05), Bale (86, 0.52, 2.7), Basketo (89, 0.57, 3.0), Benishangul (91, 0.30, 3.4), Kersa (82, 0.44, 2.4), Kola tembien (75, 0.44, 1.9),Maybar (84. 0.57, 2.5),Megech (85, 0.15, 2.6), andWondoGenet (86, 0.52, 2.7) indicating that themodels were stable. Models performed better for areas with high SOC values than areas with lower SOC values. Overall, soil spectroscopy performance ranged from very good to good.