Cluster-based active learning for compact image classification

In this paper, we consider active sampling to label pixels grouped with hierarchical clustering. The objective of the method is to match the data relationships discovered by the clustering algorithm with the user's desired class semantics. The first is represented as a complete tree to be pruned and the second is iteratively provided by the user. The active learning algorithm proposed searches the pruning of the tree that best matches the labels of the sampled points. By choosing the part of the tree to sample from according to current pruning's uncertainty, sampling is focused on most uncertain clusters. This way, large clusters for which the class membership is already fixed are no longer queried and sampling is focused on division of clusters showing mixed labels. The model is tested on a VHR image in a multiclass classification setting. The method clearly outperforms random sampling in a transductive setting, but cannot generalize to unseen data, since it aims at optimizing the classification of a given cluster structure.

Evidence-based provisional clinical classification criteria for autoinflammatory periodic fevers.

The objective of this work was to develop and validate a set of clinical criteria for the classification of patients affected by periodic fevers. Patients with inherited periodic fevers (familial Mediterranean fever (FMF); mevalonate kinase deficiency (MKD); tumour necrosis factor receptor-associated periodic fever syndrome (TRAPS); cryopyrin-associated periodic syndromes (CAPS)) enrolled in the Eurofever Registry up until March 2013 were evaluated. Patients with periodic fever, aphthosis, pharyngitis and adenitis (PFAPA) syndrome were used as negative controls. For each genetic disease, patients were considered to be 'gold standard' on the basis of the presence of a confirmatory genetic analysis. Clinical criteria were formulated on the basis of univariate and multivariate analysis in an initial group of patients (training set) and validated in an independent set of patients (validation set). A total of 1215 consecutive patients with periodic fevers were identified, and 518 gold standard patients (291 FMF, 74 MKD, 86 TRAPS, 67 CAPS) and 199 patients with PFAPA as disease controls were evaluated. The univariate and multivariate analyses identified a number of clinical variables that correlated independently with each disease, and four provisional classification scores were created. Cut-off values of the classification scores were chosen using receiver operating characteristic curve analysis as those giving the highest sensitivity and specificity. The classification scores were then tested in an independent set of patients (validation set) with an area under the curve of 0.98 for FMF, 0.95 for TRAPS, 0.96 for MKD, and 0.99 for CAPS. In conclusion, evidence-based provisional clinical criteria with high sensitivity and specificity for the clinical classification of patients with inherited periodic fevers have been developed.

Epidemiology of multiple congenital anomalies in Europe: a EUROCAT population-based registry study.

BACKGROUND: This study describes the prevalence, associated anomalies, and demographic characteristics of cases of multiple congenital anomalies (MCA) in 19 population-based European registries (EUROCAT) covering 959,446 births in 2004 and 2010. METHODS: EUROCAT implemented a computer algorithm for classification of congenital anomaly cases followed by manual review of potential MCA cases by geneticists. MCA cases are defined as cases with two or more major anomalies of different organ systems, excluding sequences, chromosomal and monogenic syndromes. RESULTS: The combination of an epidemiological and clinical approach for classification of cases has improved the quality and accuracy of the MCA data. Total prevalence of MCA cases was 15.8 per 10,000 births. Fetal deaths and termination of pregnancy were significantly more frequent in MCA cases compared with isolated cases (p < 0.001) and MCA cases were more frequently prenatally diagnosed (p < 0.001). Live born infants with MCA were more often born preterm (p < 0.01) and with birth weight < 2500 grams (p < 0.01). Respiratory and ear, face, and neck anomalies were the most likely to occur with other anomalies (34% and 32%) and congenital heart defects and limb anomalies were the least likely to occur with other anomalies (13%) (p < 0.01). However, due to their high prevalence, congenital heart defects were present in half of all MCA cases. Among males with MCA, the frequency of genital anomalies was significantly greater than the frequency of genital anomalies among females with MCA (p < 0.001). CONCLUSION: Although rare, MCA cases are an important public health issue, because of their severity. The EUROCAT database of MCA cases will allow future investigation on the epidemiology of these conditions and related clinical and diagnostic problems.

Automatic Mallampati Classification Using Active Appearance Models

Difficult tracheal intubation assessment is an important research topic in anesthesia as failed intubations are important causes of mortality in anesthetic practice. The modified Mallampati score is widely used, alone or in conjunction with other criteria, to predict the difficulty of intubation. This work presents an automatic method to assess the modified Mallampati score from an image of a patient with the mouth wide open. For this purpose we propose an active appearance models (AAM) based method and use linear support vector machines (SVM) to select a subset of relevant features obtained using the AAM. This feature selection step proves to be essential as it improves drastically the performance of classification, which is obtained using SVM with RBF kernel and majority voting. We test our method on images of 100 patients undergoing elective surgery and achieve 97.9% accuracy in the leave-one-out crossvalidation test and provide a key element to an automatic difficult intubation assessment system.

Reasons why emergency department providers do not rely on the pneumonia severity index to determine the initial site of treatment for patients with pneumonia.

BACKGROUND: Many emergency department (ED) providers do not follow guideline recommendations for the use of the pneumonia severity index (PSI) to determine the initial site of treatment for patients with community-acquired pneumonia (CAP). We identified the reasons why ED providers hospitalize low-risk patients or manage higher-risk patients as outpatients. METHODS: As a part of a trial to implement a PSI-based guideline for the initial site of treatment of patients with CAP, we analyzed data for patients managed at 12 EDs allocated to a high-intensity guideline implementation strategy study arm. The guideline recommended outpatient care for low-risk patients (nonhypoxemic patients with a PSI risk classification of I, II, or III) and hospitalization for higher-risk patients (hypoxemic patients or patients with a PSI risk classification of IV or V). We asked providers who made guideline-discordant decisions on site of treatment to detail the reasons for nonadherence to guideline recommendations. RESULTS: There were 1,306 patients with CAP (689 low-risk patients and 617 higher-risk patients). Among these patients, physicians admitted 258 (37.4%) of 689 low-risk patients and treated 20 (3.2%) of 617 higher-risk patients as outpatients. The most commonly reported reasons for admitting low-risk patients were the presence of a comorbid illness (178 [71.5%] of 249 patients); a laboratory value, vital sign, or symptom that precluded ED discharge (73 patients [29.3%]); or a recommendation from a primary care or a consulting physician (48 patients [19.3%]). Higher-risk patients were most often treated as outpatients because of a recommendation by a primary care or consulting physician (6 [40.0%] of 15 patients). CONCLUSION: ED providers hospitalize many low-risk patients with CAP, most frequently for a comorbid illness. Although higher-risk patients are infrequently treated as outpatients, this decision is often based on the request of an involved physician.

A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification

Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines. The complexity of the problem, the limited temporal and financial resources, as well as the high intraclass variance can make an algorithm fail if it is trained with a suboptimal dataset. Active learning aims at building efficient training sets by iteratively improving the model performance through sampling. A user-defined heuristic ranks the unlabeled pixels according to a function of the uncertainty of their class membership and then the user is asked to provide labels for the most uncertain pixels. This paper reviews and tests the main families of active learning algorithms: committee, large margin, and posterior probability-based. For each of them, the most recent advances in the remote sensing community are discussed and some heuristics are detailed and tested. Several challenging remote sensing scenarios are considered, including very high spatial resolution and hyperspectral image classification. Finally, guidelines for choosing the good architecture are provided for new and/or unexperienced user.

Robotic, fluoroscopic or EMG assisted pedicle screw insertion. A CT based comparative study

Introduction: In order to improve safety of pedicle screw placement several techniques have been developed. More recently robotically assisted pedicle insertion has been introduced aiming at increasing accuracy. The aim of this study was to compare this new technique with the two main pedicle insertion techniques in our unit namely fluoroscopically assisted vs EMG aided insertion. Material and methods: A total of 382 screws (78 thoracic,304 lumbar) were introduced in 64 patients (m/f = 1.37, equally distributed between insertion technique groups) by a single experienced spinal surgeon. From those, 64 (10 thoracic, 54 lumbar) were introduced in 11 patients using a miniature robotic device based on pre operative CT images under fluoroscopic control. 142 (4 thoracic, 138 lumbar) screws were introduced using lateral fluoroscopy in 27 patients while 176 (64 thoracic, 112 lumbar) screws in 26 patients were inserted using both fluoroscopy and EMG monitoring. There was no difference in the distribution of scoliotic spines between the 3 groups (n = 13). Screw position was assessed by an independent observer on CTs in axial, sagittal and coronal planes using the Rampersaud A to D classification. Data of lumbar and thoracic screws were processed separately as well as data obtained from axial, sagittal and coronal CT planes. Results: Intra- and interobserver reliability of the Rampersaud classification was moderate, (0.35 and 0.45 respectively) being the least good on axial plane. The total number of misplaced screws (C&D grades) was generally low (12 thoracic and 12 lumbar screws). Misplacement rates were same in straight and scoliotic spines. The only difference in misplacement rates was observed on axial and coronal images in the EMG assisted thoracic screw group with a higher proportion of C or D grades (p <0.05) in that group. Recorded compound muscle action potentials (CMAP) values of the inserted screws were 30.4 mA for the robot and 24.9mA for the freehand technique with a CI of 3.8 of the mean difference of 5.5 mA. Discussion: Robotic placement did improve the placement of thoracic screws but not that of lumbar screws possibly because our misplacement rates in general near that of published navigation series. Robotically assisted spine surgery might therefore enhance the safety of screw placement in particular in training settings were different users at various stages of their learning curve are involved in pedicle instrumentation.

A web-based pilot study of inter-pathologist reproducibility using the ISHLT 2004 working formulation for biopsy diagnosis of cardiac allograft rejection: The European experience.

BACKGROUND: The aim of this study was to assess, at the European level and using digital technology, the inter-pathologist reproducibility of the ISHLT 2004 system and to compare it with the 1990 system We also assessed the reproducibility of the morphologic criteria for diagnosis of antibody-mediated rejection detailed in the 2004 grading system. METHODS: The hematoxylin-eosin-stained sections of 20 sets of endomyocardial biopsies were pre-selected and graded by two pathologists (A.A. and M.B.) and digitized using a telepathology digital pathology system (Aperio ImageScope System; for details refer to http://aperio.com/). Their diagnoses were considered the index diagnoses, which covered all grades of acute cellular rejection (ACR), early ischemic lesions, Quilty lesions, late ischemic lesions and (in the 2005 system) antibody-mediated rejection (AMR). Eighteen pathologists from 16 heart transplant centers in 7 European countries participated in the study. Inter-observer reproducibility was assessed using Fleiss's kappa and Krippendorff's alpha statistics. RESULTS: The combined kappa value of all grades diagnosed by all 18 pathologists was 0.31 for the 1990 grading system and 0.39 for the 2005 grading system, with alpha statistics at 0.57 and 0.55, respectively. Kappa values by grade for 1990/2005, respectively, were: 0 = 0.52/0.51; 1A/1R = 0.24/0.36; 1B = 0.15; 2 = 0.13; 3A/2R = 0.29/0.29; 3B/3R = 0.13/0.23; and 4 = 0.18. For the 2 cases of AMR, 6 of 18 pathologists correctly suspected AMR on the hematoxylin-eosin slides, whereas, in each of 17 of the 18 AMR-negative cases a small percentage of pathologists (range 5% to 33%) overinterpreted the findings as suggestive for AMR. CONCLUSIONS: Reproducibility studies of cardiac biopsies by pathologists in different centers at the international level were feasible using digitized slides rather than conventional histology glass slides. There was a small improvement in interobserver agreement between pathologists of different European centers when moving from the 1990 ISHLT classification to the "new" 2005 ISHLT classification. Morphologic suspicion of AMR in the 2004 system on hematoxylin-eosin-stained slides only was poor, highlighting the need for better standardization of morphologic criteria for AMR. Ongoing educational programs are needed to ensure standardization of diagnosis of both acute cellular and antibody-mediated rejection.

The use of classification and regression trees to predict the likelihood of seasonal influenza.

Background Individual signs and symptoms are of limited value for the diagnosis of influenza. Objective To develop a decision tree for the diagnosis of influenza based on a classification and regression tree (CART) analysis. Methods Data from two previous similar cohort studies were assembled into a single dataset. The data were randomly divided into a development set (70%) and a validation set (30%). We used CART analysis to develop three models that maximize the number of patients who do not require diagnostic testing prior to treatment decisions. The validation set was used to evaluate overfitting of the model to the training set. Results Model 1 has seven terminal nodes based on temperature, the onset of symptoms and the presence of chills, cough and myalgia. Model 2 was a simpler tree with only two splits based on temperature and the presence of chills. Model 3 was developed with temperature as a dichotomous variable (≥38°C) and had only two splits based on the presence of fever and myalgia. The area under the receiver operating characteristic curves (AUROCC) for the development and validation sets, respectively, were 0.82 and 0.80 for Model 1, 0.75 and 0.76 for Model 2 and 0.76 and 0.77 for Model 3. Model 2 classified 67% of patients in the validation group into a high- or low-risk group compared with only 38% for Model 1 and 54% for Model 3. Conclusions A simple decision tree (Model 2) classified two-thirds of patients as low or high risk and had an AUROCC of 0.76. After further validation in an independent population, this CART model could support clinical decision making regarding influenza, with low-risk patients requiring no further evaluation for influenza and high-risk patients being candidates for empiric symptomatic or drug therapy.

Bayesian classification criterion for forensic multivariate data

This study presents a classification criteria for two-class Cannabis seedlings. As the cultivation of drug type cannabis is forbidden in Switzerland, law enforcement authorities regularly ask laboratories to determine cannabis plant's chemotype from seized material in order to ascertain that the plantation is legal or not. In this study, the classification analysis is based on data obtained from the relative proportion of three major leaf compounds measured by gas-chromatography interfaced with mass spectrometry (GC-MS). The aim is to discriminate between drug type (illegal) and fiber type (legal) cannabis at an early stage of the growth. A Bayesian procedure is proposed: a Bayes factor is computed and classification is performed on the basis of the decision maker specifications (i.e. prior probability distributions on cannabis type and consequences of classification measured by losses). Classification rates are computed with two statistical models and results are compared. Sensitivity analysis is then performed to analyze the robustness of classification criteria.

Lipid composition of fingermark residue and donor classification using GC/MS

Lipids available in fingermark residue represent important targets for enhancement and dating techniques. While it is well known that lipid composition varies among fingermarks of the same donor (intra-variability) and between fingermarks of different donors (inter-variability), the extent of this variability remains uncharacterised. Thus, this worked aimed at studying qualitatively and quantitatively the initial lipid composition of fingermark residue of 25 different donors. Among the 104 detected lipids, 43 were reported for the first time in the literature. Furthermore, palmitic acid, squalene, cholesterol, myristyl myristate and myristyl myristoleate were quantified and their correlation within fingermark residue was highlighted. Ten compounds were then selected and further studied as potential targets for dating or enhancement techniques. It was shown that their relative standard deviation was significantly lower for the intra-variability than for the inter-variability. Moreover, the use of data pretreatments could significantly reduce this variability. Based on these observations, an objective donor classification model was proposed. Hierarchical cluster analysis was conducted on the pre-treated data and the fingermarks of the 25 donors were classified into two main groups, corresponding to "poor" and "rich" lipid donors. The robustness of this classification was tested using fingermark replicates of selected donors. 86% of these replicates were correctly classified, showing the potential of such a donor classification model for research purposes in order to select representative donors based on compounds of interest.

Structured output SVM for remote sensing image classification

In the recent years, kernel methods have revealed very powerful tools in many application domains in general and in remote sensing image classification in particular. The special characteristics of remote sensing images (high dimension, few labeled samples and different noise sources) are efficiently dealt with kernel machines. In this paper, we propose the use of structured output learning to improve remote sensing image classification based on kernels. Structured output learning is concerned with the design of machine learning algorithms that not only implement input-output mapping, but also take into account the relations between output labels, thus generalizing unstructured kernel methods. We analyze the framework and introduce it to the remote sensing community. Output similarity is here encoded into SVM classifiers by modifying the model loss function and the kernel function either independently or jointly. Experiments on a very high resolution (VHR) image classification problem shows promising results and opens a wide field of research with structured output kernel methods.

Rehabilitation needs assessment in persons with spinal cord injury following the 2010 earthquake in Haiti: a pilot study using an ICF-based tool.

OBJECTIVE: The aim of this pilot study was to describe problems in functioning and associated rehabilitation needs in persons with spinal cord injury after the 2010 earthquake in Haiti by applying a newly developed tool based on the International Classification of Functioning, Disability and Health (ICF). DESIGN: Pilot study. SUBJECTS: Eighteen persons with spinal cord injury (11 women, 7 men) participated in the needs assessment. Eleven patients had complete lesions (American Spinal Injury Association Impairment Scale; AIS A), one patient had tetraplegia. METHODS: Data collection included information from the International Spinal Cord Injury Core Data Set and a newly developed needs assessment tool based on ICF Core Sets. This tool assesses the level of functioning, the corresponding rehabilitation need, and required health professional. Data were summarized using descriptive statistics. RESULTS: In body functions and body structures, patients showed typical problems following spinal cord injury. Nearly all patients showed limitations and restrictions in their activities and participation related to mobility, self-care and aspects of social integration. Several environmental factors presented barriers to these limitations and restrictions. However, the availability of products and social support were identified as facilitators. Rehabilitation needs were identified in nearly all aspects of functioning. To address these needs, a multidisciplinary approach would be needed. CONCLUSION: This ICF-based needs assessment provided useful information for rehabilitation planning in the context of natural disaster. Future studies are required to test and, if necessary, adapt the assessment.