A Hybrid Model for Multimodal Brain Tumor Segmentation

We present a fully automatic segmentation method for multi-modal brain tumor segmentation. The proposed generative-discriminative hybrid model generates initial tissue probabilities, which are used subsequently for enhancing the classi�cation and spatial regularization. The model has been evaluated on the BRATS2013 training set, which includes multimodal MRI images from patients with high- and low-grade gliomas. Our method is capable of segmenting the image into healthy (GM, WM, CSF) and pathological tissue (necrotic, enhancing and non-enhancing tumor, edema). We achieved state-of-the-art performance (Dice mean values of 0.69 and 0.8 for tumor subcompartments and complete tumor respectively) within a reasonable timeframe (4 to 15 minutes).

Cardiothoracic ratio in postmortem computed tomography: reliability and threshold for the diagnosis of cardiomegaly

The aim of this study was to evaluate the reliability of the cardiothoracic ratio (CTR) in postmortem computed tomography (PMCT) and to assess a CTR threshold for the diagnosis of cardiomegaly based on the weight of the heart at autopsy. PMCT data of 170 deceased human adults were retrospectively evaluated by two blinded radiologists. The CTR was measured on axial computed tomography images and the actual cardiac weight was weighed at autopsy. Inter-rater reliability, sensitivity, and specificity were calculated. Receiver operating characteristic curves were calculated to assess enlarged heart weight by CTR. The autopsy definition of cardiomegaly was based on normal values of the Zeek method (within a range of both, one or two SD) and the Smith method (within the given range). Intra-class correlation coefficients demonstrated excellent agreements (0.983) regarding CTR measurements. In 105/170 (62 %) cases the CTR in PMCT was >0.5, indicating enlarged heart weight, according to clinical references. The mean heart weight measured in autopsy was 405 ± 105 g. As a result, 114/170 (67 %) cases were interpreted as having enlarged heart weights according to the normal values of Zeek within one SD, while 97/170 (57 %) were within two SD. 100/170 (59 %) were assessed as enlarged according to Smith's normal values. The sensitivity/specificity of the 0.5 cut-off of the CTR for the diagnosis of enlarged heart weight was 78/71 % (Zeek one SD), 74/55 % (Zeek two SD), and 76/59 % (Smith), respectively. The discriminative power between normal heart weight and cardiomegaly was 79, 73, and 74 % for the Zeek (1SD/2SD) and Smith methods respectively. Changing the CTR threshold to 0.57 resulted in a minimum specificity of 95 % for all three definitions of cardiomegaly. With a CTR threshold of 0.57, cardiomegaly can be identified with a very high specificity. This may be useful if PMCT is used by forensic pathologists as a screening tool for medico-legal autopsies.

Eye movements discriminate fatigue due to chronotypical factors and time spent on task--a double dissociation

Systematic differences in circadian rhythmicity are thought to be a substantial factor determining inter-individual differences in fatigue and cognitive performance. The synchronicity effect (when time of testing coincides with the respective circadian peak period) seems to play an important role. Eye movements have been shown to be a reliable indicator of fatigue due to sleep deprivation or time spent on cognitive tasks. However, eye movements have not been used so far to investigate the circadian synchronicity effect and the resulting differences in fatigue. The aim of the present study was to assess how different oculomotor parameters in a free visual exploration task are influenced by: a) fatigue due to chronotypical factors (being a 'morning type' or an 'evening type'); b) fatigue due to the time spent on task. Eighteen healthy participants performed a free visual exploration task of naturalistic pictures while their eye movements were recorded. The task was performed twice, once at their optimal and once at their non-optimal time of the day. Moreover, participants rated their subjective fatigue. The non-optimal time of the day triggered a significant and stable increase in the mean visual fixation duration during the free visual exploration task for both chronotypes. The increase in the mean visual fixation duration correlated with the difference in subjectively perceived fatigue at optimal and non-optimal times of the day. Conversely, the mean saccadic speed significantly and progressively decreased throughout the duration of the task, but was not influenced by the optimal or non-optimal time of the day for both chronotypes. The results suggest that different oculomotor parameters are discriminative for fatigue due to different sources. A decrease in saccadic speed seems to reflect fatigue due to time spent on task, whereas an increase in mean fixation duration a lack of synchronicity between chronotype and time of the day.

Added value of dual-energy computed tomography versus single-energy computed tomography in assessing ferromagnetic properties of ballistic projectiles: implications for magnetic resonance imaging of gunshot victims.

OBJECTIVE The objective of this study was to assess the discriminative power of dual-energy computed tomography (DECT) versus single-energy CT (SECT) to distinguish between ferromagnetic and non-ferromagnetic ballistic projectiles to improve safety regarding magnetic resonance (MR) imaging studies in patients with retained projectiles. MATERIALS AND METHODS Twenty-seven ballistic projectiles including 25 bullets (diameter, 3-15 mm) and 2 shotgun pellets (2 mm each) were examined in an anthropomorphic chest phantom using 128-section dual-source CT. Data acquisition was performed with tube voltages set at 80, 100, 120, and 140 kV(p). Two readers independently assessed CT numbers of the projectile's core on images reconstructed with an extended CT scale. Dual-energy indices (DEIs) were calculated from both 80-/140-kV(p) and 100-/140-kV(p) pairs; receiver operating characteristics curves were fitted to assess ferromagnetic properties by means of CT numbers and DEI. RESULTS Nine (33%) of the projectiles were ferromagnetic; 18 were nonferromagnetic (67%). Interreader and intrareader correlations of CT number measurements were excellent (intraclass correlation coefficients, >0.906; P<0.001). The DEI calculated from both 80/140 and 100/140 kV(p) were significantly (P<0.05) different between the ferromagnetic and non-ferromagnetic projectiles. The area under the curve (AUC) was 0.75 and 0.8 for the tube voltage pairs of 80/140 and 100/140 kV(p) (P<0.05; 95% confidence interval, 0.57-0.94 and 0.62-0.97, respectively) to differentiate between the ferromagnetic and non-ferromagnetic ballistic projectiles; which increased to 0.83 and 0.85 when shotgun pellets were excluded from the analysis. The AUC for SECT was 0.69 and 0.73 (80 and 100 kV[p], respectively). CONCLUSIONS Measurements of DECT combined with an extended CT scale allow for the discrimination of projectiles with non-ferromagnetic from those with ferromagnetic properties in an anthropomorphic chest phantom with a higher AUC compared with SECT. This study indicates that DECT may have the potential to contribute to MR safety and allow for MR imaging of patients with retained projectiles. However, further studies are necessary before this concept may be used to triage clinical patients before MR.

Dementia in patients with atrial fibrillation and the value of the Hachinski ischemic score.

AIM To assess the prevalence of vascular dementia, mixed dementia and Alzheimer's disease in patients with atrial fibrillation, and to evaluate the accuracy of the Hachinski ischemic score for these subtypes of dementia. METHODS A nested case-control study was carried out. A total of 103 of 784 consecutive patients evaluated for cognitive status at the Ambulatory Geriatric Clinic had a diagnosis of atrial fibrillation. Controls without atrial fibrillation were randomly selected from the remaining 681 patients using a 1:2 matching for sex, age and education. RESULTS The prevalence of vascular dementia was twofold in patients with atrial fibrillation compared with controls (21.4% vs 10.7%, P = 0.024). Alzheimer's disease was also more frequent in the group with atrial fibrillation (12.6% vs 7.3%, P = 0.046), whereas mixed dementia had a similar distribution. The Hachinski ischemic score poorly discriminated between dementia subtypes, with misclassification rates between 46% (95% CI 28-66) and 70% (95% CI 55-83). In patients with atrial fibrillation, these rates ranged from 55% (95% CI 32-77) to 69% (95% CI 39-91%). In patients in whom the diagnosis of dementia was excluded, the Hachinski ischemic score suggested the presence of vascular dementia in 11% and mixed dementia in 30%. CONCLUSIONS Vascular dementia and Alzheimer's disease, but not mixed dementia, are more prevalent in patients with atrial fibrillation. The discriminative accuracy of the Hachinski ischemic score for dementia subtypes in atrial fibrillation is poor, with a significant proportion of misclassifications.

Predicting 3-year mortality after percutaneous coronary intervention: updated logistic clinical SYNTAX score based on patient-level data from 7 contemporary stent trials

OBJECTIVES This study aimed to update the Logistic Clinical SYNTAX score to predict 3-year survival after percutaneous coronary intervention (PCI) and compare the performance with the SYNTAX score alone. BACKGROUND The SYNTAX score is a well-established angiographic tool to predict long-term outcomes after PCI. The Logistic Clinical SYNTAX score, developed by combining clinical variables with the anatomic SYNTAX score, has been shown to perform better than the SYNTAX score alone in predicting 1-year outcomes after PCI. However, the ability of this score to predict long-term survival is unknown. METHODS Patient-level data (N = 6,304, 399 deaths within 3 years) from 7 contemporary PCI trials were analyzed. We revised the overall risk and the predictor effects in the core model (SYNTAX score, age, creatinine clearance, and left ventricular ejection fraction) using Cox regression analysis to predict mortality at 3 years. We also updated the extended model by combining the core model with additional independent predictors of 3-year mortality (i.e., diabetes mellitus, peripheral vascular disease, and body mass index). RESULTS The revised Logistic Clinical SYNTAX models showed better discriminative ability than the anatomic SYNTAX score for the prediction of 3-year mortality after PCI (c-index: SYNTAX score, 0.61; core model, 0.71; and extended model, 0.73 in a cross-validation procedure). The extended model in particular performed better in differentiating low- and intermediate-risk groups. CONCLUSIONS Risk scores combining clinical characteristics with the anatomic SYNTAX score substantially better predict 3-year mortality than the SYNTAX score alone and should be used for long-term risk stratification of patients undergoing PCI.

A clinical prediction model to identify patients at high risk of death in the emergency department.

PURPOSE Rapid assessment and intervention is important for the prognosis of acutely ill patients admitted to the emergency department (ED). The aim of this study was to prospectively develop and validate a model predicting the risk of in-hospital death based on all available information available at the time of ED admission and to compare its discriminative performance with a non-systematic risk estimate by the triaging first health-care provider. METHODS Prospective cohort analysis based on a multivariable logistic regression for the probability of death. RESULTS A total of 8,607 consecutive admissions of 7,680 patients admitted to the ED of a tertiary care hospital were analysed. Most frequent APACHE II diagnostic categories at the time of admission were neurological (2,052, 24 %), trauma (1,522, 18 %), infection categories [1,328, 15 %; including sepsis (357, 4.1 %), severe sepsis (249, 2.9 %), septic shock (27, 0.3 %)], cardiovascular (1,022, 12 %), gastrointestinal (848, 10 %) and respiratory (449, 5 %). The predictors of the final model were age, prolonged capillary refill time, blood pressure, mechanical ventilation, oxygen saturation index, Glasgow coma score and APACHE II diagnostic category. The model showed good discriminative ability, with an area under the receiver operating characteristic curve of 0.92 and good internal validity. The model performed significantly better than non-systematic triaging of the patient. CONCLUSIONS The use of the prediction model can facilitate the identification of ED patients with higher mortality risk. The model performs better than a non-systematic assessment and may facilitate more rapid identification and commencement of treatment of patients at risk of an unfavourable outcome.

The Initial Slope of the Variogram, Foundation of the Trabecular Bone Score, Is Not or Poorly Associated With Vertebral Strength

Trabecular bone score (TBS) rests on the textural analysis of DXA to reflect the decay in trabecular structure characterising osteoporosis. Yet, its discriminative power in fracture studies remains incomprehensible as prior biomechanical tests found no correlation with vertebral strength. To verify this result possibly due to an unrealistic set-up and to cover a wide range of loading scenarios, the data from three previous biomechanical studies using different experimental settings was used. They involved the compressive failure of 62 human lumbar vertebrae loaded 1) via intervertebral discs to mimic the in vivo situation (“full vertebra”), 2) via the classical endplate embedding (“vertebral body”) or 3) via a ball joint to induce anterior wedge failure (“vertebral section”). HR-pQCT scans acquired prior testing were used to simulate anterior-posterior DXA from which areal bone mineral density (aBMD) and the initial slope of the variogram (ISV), the early definition of TBS, were evaluated. Finally, the relation of aBMD and ISV with failure load (Fexp) and apparent failure stress (σexp) was assessed and their relative contribution to a multi-linear model was quantified via ANOVA. We found that, unlike aBMD, ISV did not significantly correlate with Fexp and σexp, except for the “vertebral body” case (r2 = 0.396, p = 0.028). Aside from the “vertebra section” set-up where it explained only 6.4% of σexp (p = 0.037), it brought no significant improvement to aBMD. These results indicate that ISV, a replica of TBS, is a poor surrogate for vertebral strength no matter the testing set-up, which supports the prior observations and raises a fortiori the question of the deterministic factors underlying the statistical relationship between TBS and vertebral fracture risk.

Genetic variants in SLC22A17 and SLC22A7 are associated with anthracycline-induced cardiotoxicity in children

AIM To identify novel variants associated with anthracycline-induced cardiotoxicity and to assess these in a genotype-guided risk prediction model. PATIENTS & METHODS Two cohorts treated for childhood cancer (n = 344 and 218, respectively) were genotyped for 4578 SNPs in drug ADME and toxicity genes. RESULTS Significant associations were identified in SLC22A17 (rs4982753; p = 0.0078) and SLC22A7 (rs4149178; p = 0.0034), with replication in the second cohort (p = 0.0071 and 0.047, respectively). Additional evidence was found for SULT2B1 and several genes related to oxidative stress. Adding the SLC22 variants to the prediction model improved its discriminative ability (AUC 0.78 vs 0.75 [p = 0.029]). CONCLUSION Two novel variants in SLC22A17 and SLC22A7 were significantly associated with anthracycline-induced cardiotoxicity and improved a genotype-guided risk prediction model, which could improve patient risk stratification.

External validation of the Hospital-patient One-year Mortality Risk (HOMR) model for predicting death within 1 year after hospital admission

BACKGROUND Predicting long-term survival after admission to hospital is helpful for clinical, administrative and research purposes. The Hospital-patient One-year Mortality Risk (HOMR) model was derived and internally validated to predict the risk of death within 1 year after admission. We conducted an external validation of the model in a large multicentre study. METHODS We used administrative data for all nonpsychiatric admissions of adult patients to hospitals in the provinces of Ontario (2003-2010) and Alberta (2011-2012), and to the Brigham and Women's Hospital in Boston (2010-2012) to calculate each patient's HOMR score at admission. The HOMR score is based on a set of parameters that captures patient demographics, health burden and severity of acute illness. We determined patient status (alive or dead) 1 year after admission using population-based registries. RESULTS The 3 validation cohorts (n = 2,862,996 in Ontario, 210 595 in Alberta and 66,683 in Boston) were distinct from each other and from the derivation cohort. The overall risk of death within 1 year after admission was 8.7% (95% confidence interval [CI] 8.7% to 8.8%). The HOMR score was strongly and significantly associated with risk of death in all populations and was highly discriminative, with a C statistic ranging from 0.89 (95% CI 0.87 to 0.91) to 0.92 (95% CI 0.91 to 0.92). Observed and expected outcome risks were similar (median absolute difference in percent dying in 1 yr 0.3%, interquartile range 0.05%-2.5%). INTERPRETATION The HOMR score, calculated using routinely collected administrative data, accurately predicted the risk of death among adult patients within 1 year after admission to hospital for nonpsychiatric indications. Similar performance was seen when the score was used in geographically and temporally diverse populations. The HOMR model can be used for risk adjustment in analyses of health administrative data to predict long-term survival among hospital patients.

Incremental Value of the CRUSADE, ACUITY, and HAS-BLED Risk Scores for the Prediction of Hemorrhagic Events After Coronary Stent Implantation in Patients Undergoing Long or Short Duration of Dual Antiplatelet Therapy

BACKGROUND Multiple scores have been proposed to stratify bleeding risk, but their value to guide dual antiplatelet therapy duration has never been appraised. We compared the performance of the CRUSADE (Can Rapid Risk Stratification of Unstable Angina Patients Suppress Adverse Outcomes With Early Implementation of the ACC/AHA Guidelines), ACUITY (Acute Catheterization and Urgent Intervention Triage Strategy), and HAS-BLED (Hypertension, Abnormal Renal/Liver Function, Stroke, Bleeding History or Predisposition, Labile INR, Elderly, Drugs/Alcohol Concomitantly) scores in 1946 patients recruited in the Prolonging Dual Antiplatelet Treatment After Grading Stent-Induced Intimal Hyperplasia Study (PRODIGY) and assessed hemorrhagic and ischemic events in the 24- and 6-month dual antiplatelet therapy groups. METHODS AND RESULTS Bleeding score performance was assessed with a Cox regression model and C statistics. Discriminative and reclassification power was assessed with net reclassification improvement and integrated discrimination improvement. The C statistic was similar between the CRUSADE score (area under the curve 0.71) and ACUITY (area under the curve 0.68), and higher than HAS-BLED (area under the curve 0.63). CRUSADE, but not ACUITY, improved reclassification (net reclassification index 0.39, P=0.005) and discrimination (integrated discrimination improvement index 0.0083, P=0.021) of major bleeding compared with HAS-BLED. Major bleeding and transfusions were higher in the 24- versus 6-month dual antiplatelet therapy groups in patients with a CRUSADE score >40 (hazard ratio for bleeding 2.69, P=0.035; hazard ratio for transfusions 4.65, P=0.009) but not in those with CRUSADE score ≤40 (hazard ratio for bleeding 1.50, P=0.25; hazard ratio for transfusions 1.37, P=0.44), with positive interaction (Pint=0.05 and Pint=0.01, respectively). The number of patients with high CRUSADE scores needed to treat for harm for major bleeding and transfusion were 17 and 15, respectively, with 24-month rather than 6-month dual antiplatelet therapy; corresponding figures in the overall population were 67 and 71, respectively. CONCLUSIONS Our analysis suggests that the CRUSADE score predicts major bleeding similarly to ACUITY and better than HAS BLED in an all-comer population with percutaneous coronary intervention and potentially identifies patients at higher risk of hemorrhagic complications when treated with a long-term dual antiplatelet therapy regimen. CLINICAL TRIAL REGISTRATION URL: http://clinicaltrials.gov. Unique identifier: NCT00611286.

A novel colourimetric technique to assess chewing function using two-coloured specimens: Validation and application

OBJECTIVES Chewing efficiency may be evaluated using cohesive specimen, especially in elderly or dysphagic patients. The aim of this study was to evaluate three two-coloured chewing gums for a colour-mixing ability test and to validate a new purpose built software (ViewGum©). METHODS Dentate participants (dentate-group) and edentulous patients with mandibular two-implant overdentures (IOD-group) were recruited. First, the dentate-group chewed three different types of two-coloured gum (gum1-gum3) for 5, 10, 20, 30 and 50 chewing cycles. Subsequently the number of chewing cycles with the highest intra- and inter-rater agreement was determined visually by applying a scale (SA) and opto-electronically (ViewGum©, Bland-Altman analysis). The ViewGum© software determines semi-automatically the variance of hue (VOH); inadequate mixing presents with larger VOH than complete mixing. Secondly, the dentate-group and the IOD-group were compared. RESULTS The dentate-group comprised 20 participants (10 female, 30.3±6.7 years); the IOD-group 15 participants (10 female, 74.6±8.3 years). Intra-rater and inter-rater agreement (SA) was very high at 20 chewing cycles (95.00-98.75%). Gums 1-3 showed different colour-mixing characteristics as a function of chewing cycles, gum1 showed a logarithmic association; gum2 and gum3 demonstrated more linear behaviours. However, the number of chewing cycles could be predicted in all specimens from VOH (all p<0.0001, mixed linear regression models). Both analyses proved discriminative to the dental state. CONCLUSION ViewGum© proved to be a reliable and discriminative tool to opto-electronically assess chewing efficiency, given an elastic specimen is chewed for 20 cycles and could be recommended for the evaluation of chewing efficiency in a clinical and research setting. CLINICAL SIGNIFICANCE Chewing is a complex function of the oro-facial structures and the central nervous system. The application of the proposed assessments of the chewing function in geriatrics or special care dentistry could help visualising oro-functional or dental comorbidities in dysphagic patients or those suffering from protein-energy malnutrition.

Contextual classification of full waveform lidar data in the Wadden Sea

The classification of airborne lidar data is a relevant task in different disciplines. The information about the geometry and the full waveform can be used in order to classify the 3D point cloud. In Wadden Sea areas the classification of lidar data is of main interest for the scientific monitoring of coastal morphology and habitats, but it becomes a challenging task due to flat areas with hardly any discriminative objects. For the classification we combine a Conditional Random Fields framework with a Random Forests approach. By classifying in this way, we benefit from the consideration of context on the one hand and from the opportunity to utilise a high number of classification features on the other hand. We investigate the relevance of different features for the lidar points in coastal areas as well as for the interaction of neighbouring points.

Optimizing Functional Network Representation of Multivariate Time Series

By combining complex network theory and data mining techniques, we provide objective criteria for optimization of the functional network representation of generic multivariate time series. In particular, we propose a method for the principled selection of the threshold value for functional network reconstruction from raw data, and for proper identification of the network's indicators that unveil the most discriminative information on the system for classification purposes. We illustrate our method by analysing networks of functional brain activity of healthy subjects, and patients suffering from Mild Cognitive Impairment, an intermediate stage between the expected cognitive decline of normal aging and the more pronounced decline of dementia. We discuss extensions of the scope of the proposed methodology to network engineering purposes, and to other data mining tasks.

Adaptive neuro-fuzzy inference systems (ANFIS) for supervised classification of competence in MIS based on psychomotor skills

INTRODUCTION: Objective assessment of motor skills has become an important challenge in minimally invasive surgery (MIS) training.Currently, there is no gold standard defining and determining the residents' surgical competence.To aid in the decision process, we analyze the validity of a supervised classifier to determine the degree of MIS competence based on assessment of psychomotor skills METHODOLOGY: The ANFIS is trained to classify performance in a box trainer peg transfer task performed by two groups (expert/non expert). There were 42 participants included in the study: the non-expert group consisted of 16 medical students and 8 residents (< 10 MIS procedures performed), whereas the expert group consisted of 14 residents (> 10 MIS procedures performed) and 4 experienced surgeons. Instrument movements were captured by means of the Endoscopic Video Analysis (EVA) tracking system. Nine motion analysis parameters (MAPs) were analyzed, including time, path length, depth, average speed, average acceleration, economy of area, economy of volume, idle time and motion smoothness. Data reduction was performed by means of principal component analysis, and then used to train the ANFIS net. Performance was measured by leave one out cross validation. RESULTS: The ANFIS presented an accuracy of 80.95%, where 13 experts and 21 non-experts were correctly classified. Total root mean square error was 0.88, while the area under the classifiers' ROC curve (AUC) was measured at 0.81. DISCUSSION: We have shown the usefulness of ANFIS for classification of MIS competence in a simple box trainer exercise. The main advantage of using ANFIS resides in its continuous output, which allows fine discrimination of surgical competence. There are, however, challenges that must be taken into account when considering use of ANFIS (e.g. training time, architecture modeling). Despite this, we have shown discriminative power of ANFIS for a low-difficulty box trainer task, regardless of the individual significances between MAPs. Future studies are required to confirm the findings, inclusion of new tasks, conditions and sample population.