Evaluating retraining rules for semi-supervised learning in neural network based cursive word recognition

Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, including the generation of the ground truth, is tedious and costly. One way of reducing the high cost of labeled training data acquisition is to exploit unlabeled data, which can be gathered easily. Making use of both labeled and unlabeled data is known as semi-supervised learning. One of the most general versions of semi-supervised learning is self-training, where a recognizer iteratively retrains itself on its own output on new, unlabeled data. In this paper we propose to apply semi-supervised learning, and in particular self-training, to the problem of cursive, handwritten word recognition. The special focus of the paper is on retraining rules that define what data are actually being used in the retraining phase. In a series of experiments it is shown that the performance of a neural network based recognizer can be significantly improved through the use of unlabeled data and self-training if appropriate retraining rules are applied.

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).

Quality control for retinal OCT in multiple sclerosis: validation of the OSCAR-IB criteria.

BACKGROUND Retinal optical coherence tomography (OCT) permits quantification of retinal layer atrophy relevant to assessment of neurodegeneration in multiple sclerosis (MS). Measurement artefacts may limit the use of OCT to MS research. OBJECTIVE An expert task force convened with the aim to provide guidance on the use of validated quality control (QC) criteria for the use of OCT in MS research and clinical trials. METHODS A prospective multi-centre (n = 13) study. Peripapillary ring scan QC rating of an OCT training set (n = 50) was followed by a test set (n = 50). Inter-rater agreement was calculated using kappa statistics. Results were discussed at a round table after the assessment had taken place. RESULTS The inter-rater QC agreement was substantial (kappa = 0.7). Disagreement was found highest for judging signal strength (kappa = 0.40). Future steps to resolve these issues were discussed. CONCLUSION Substantial agreement for QC assessment was achieved with aid of the OSCAR-IB criteria. The task force has developed a website for free online training and QC certification. The criteria may prove useful for future research and trials in MS using OCT as a secondary outcome measure in a multi-centre setting.

Noninvasive Urinary Metabolomic Profiling Identifies Diagnostic and Prognostic Markers in Lung Cancer

Lung cancer remains the most common cause of cancer deaths worldwide, yet there is currently a lack of diagnostic noninvasive biomarkers that could guide treatment decisions. Small molecules (<1,500 Da) were measured in urine collected from 469 patients with lung cancer and 536 population controls using unbiased liquid chromatography/mass spectrometry. Clinical putative diagnostic and prognostic biomarkers were validated by quantitation and normalized to creatinine levels at two different time points and further confirmed in an independent sample set, which comprises 80 cases and 78 population controls, with similar demographic and clinical characteristics when compared with the training set. Creatine riboside (IUPAC name: 2-{2-[(2R,3R,4S,5R)-3,4-dihydroxy-5-(hydroxymethyl)-oxolan-2-yl]-1-methylcarbamimidamido}acetic acid), a novel molecule identified in this study, and N-acetylneuraminic acid (NANA) were each significantly (P < 0.00001) elevated in non-small cell lung cancer and associated with worse prognosis [HR = 1.81 (P = 0.0002), and 1.54 (P = 0.025), respectively]. Creatine riboside was the strongest classifier of lung cancer status in all and stage I-II cases, important for early detection, and also associated with worse prognosis in stage I-II lung cancer (HR = 1.71, P = 0.048). All measurements were highly reproducible with intraclass correlation coefficients ranging from 0.82 to 0.99. Both metabolites were significantly (P < 0.03) enriched in tumor tissue compared with adjacent nontumor tissue (N = 48), thus revealing their direct association with tumor metabolism. Creatine riboside and NANA may be robust urinary clinical metabolomic markers that are elevated in tumor tissue and associated with early lung cancer diagnosis and worse prognosis.

Articulated Statistical Shape Model-Based 2D-3D Reconstruction of a Hip Joint

In this paper, reconstruction of three-dimensional (3D) patient-specific models of a hip joint from two-dimensional (2D) calibrated X-ray images is addressed. Existing 2D-3D reconstruction techniques usually reconstruct a patient-specific model of a single anatomical structure without considering the relationship to its neighboring structures. Thus, when those techniques would be applied to reconstruction of patient-specific models of a hip joint, the reconstructed models may penetrate each other due to narrowness of the hip joint space and hence do not represent a true hip joint of the patient. To address this problem we propose a novel 2D-3D reconstruction framework using an articulated statistical shape model (aSSM). Different from previous work on constructing an aSSM, where the joint posture is modeled as articulation in a training set via statistical analysis, here it is modeled as a parametrized rotation of the femur around the joint center. The exact rotation of the hip joint as well as the patient-specific models of the joint structures, i.e., the proximal femur and the pelvis, are then estimated by optimally fitting the aSSM to a limited number of calibrated X-ray images. Taking models segmented from CT data as the ground truth, we conducted validation experiments on both plastic and cadaveric bones. Qualitatively, the experimental results demonstrated that the proposed 2D-3D reconstruction framework preserved the hip joint structure and no model penetration was found. Quantitatively, average reconstruction errors of 1.9 mm and 1.1 mm were found for the pelvis and the proximal femur, respectively.

A multilingual audiometer simulator software for training purposes

A set of algorithms, which allows a computer to determine the answers of simulated patients during pure tone and speech audiometry, is presented. Based on these algorithms, a computer program for training in audiometry was written and found to be useful for teaching purposes.

Practical sources of error in measuring pulmonary artery occlusion pressure: a study in participants of a special intensivist training program of The Scandinavian Society of Anaesthesiology and Intensive Care Medicine (SSAI)

BACKGROUND: Physiological data obtained with the pulmonary artery catheter (PAC) are susceptible to errors in measurement and interpretation. Little attention has been paid to the relevance of errors in hemodynamic measurements performed in the intensive care unit (ICU). The aim of this study was to assess the errors related to the technical aspects (zeroing and reference level) and actual measurement (curve interpretation) of the pulmonary artery occlusion pressure (PAOP). METHODS: Forty-seven participants in a special ICU training program and 22 ICU nurses were tested without pre-announcement. All participants had previously been exposed to the clinical use of the method. The first task was to set up a pressure measurement system for PAC (zeroing and reference level) and the second to measure the PAOP. RESULTS: The median difference from the reference mid-axillary zero level was - 3 cm (-8 to + 9 cm) for physicians and -1 cm (-5 to + 1 cm) for nurses. The median difference from the reference PAOP was 0 mmHg (-3 to 5 mmHg) for physicians and 1 mmHg (-1 to 15 mmHg) for nurses. When PAOP values were adjusted for the differences from the reference transducer level, the median differences from the reference PAOP values were 2 mmHg (-6 to 9 mmHg) for physicians and 2 mmHg (-6 to 16 mmHg) for nurses. CONCLUSIONS: Measurement of the PAOP is susceptible to substantial error as a result of practical mistakes. Comparison of results between ICUs or practitioners is therefore not possible.

Simulation in training: one-year experience using an efficiency index to assess interventional radiology fellow training status

PURPOSE: To compare objective fellow and expert efficiency indices for an interventional radiology renal artery stenosis skill set with the use of a high-fidelity simulator. MATERIALS AND METHODS: The Mentice VIST simulator was used for three different renal artery stenosis simulations of varying difficulty, which were used to grade performance. Fellows' indices at three intervals throughout 1 year were compared to expert baseline performance. Seventy-four simulated procedures were performed, 63 of which were captured as audiovisual recordings. Three levels of fellow experience were analyzed: 1, 6, and 12 months of dedicated interventional radiology fellowship. The recordings were compiled on a computer workstation and analyzed. Distinct measurable events in the procedures were identified with task analysis, and data regarding efficiency were extracted. Total scores were calculated as the product of procedure time, fluoroscopy time, tools, and contrast agent volume. The lowest scores, which reflected efficient use of tools, radiation, and time, were considered to indicate proficiency. Subjective analysis of participants' procedural errors was not included in this analysis. RESULTS: Fellows' mean scores diminished from 1 month to 12 months (42,960 at 1 month, 18,726 at 6 months, and 9,636 at 12 months). The experts' mean score was 4,660. In addition, the range of variance in score diminished with increasing experience (from a range of 5,940-120,156 at 1 month to 2,436-85,272 at 6 months and 2,160-32,400 at 12 months). Expert scores ranged from 1,450 to 10,800. CONCLUSIONS: Objective efficiency indices for simulated procedures can demonstrate scores directly comparable to the level of clinical experience.

European veterinary public health specialization: post-graduate training and expectations of potential employers

Residents of the European College of Veterinary Public Health (ECVPH) carried out a survey to explore the expectations and needs of potential employers of ECVPH diplomates and to assess the extent to which the ECVPH post-graduate training program meets those requirements. An online questionnaire was sent to 707 individuals working for universities, government organizations, and private companies active in the field of public health in 16 countries. Details on the structure and activities of the participants' organizations, their current knowledge of the ECVPH, and potential interest in employing veterinary public health (VPH) experts or hosting internships were collected. Participants were requested to rate 22 relevant competencies according to their importance for VPH professionals exiting the ECVPH training. A total of 138 completed questionnaires were included in the analysis. While generic skills such as "problem solving" and "broad horizon and inter-/multidisciplinary thinking" were consistently given high grades by all participants, the importance ascribed to more specialized skills was less homogeneous. The current ECVPH training more closely complies with the profile sought in academia, which may partly explain the lower employment rate of residents and diplomates within government and industry sectors. The study revealed a lack of awareness of the ECVPH among public health institutions and demonstrated the need for greater promotion of this veterinary specialization within Europe, both in terms of its training capacity and the professional skill-set of its diplomates. This study provides input for a critical revision of the ECVPH curriculum and the design of post-graduate training programs in VPH.

Models for intensive care training. A European perspective.

The diversity of European culture is reflected in its healthcare training programs. In intensive care medicine (ICM), the differences in national training programs were so marked that it was unlikely that they could produce specialists of equivalent skills. The Competency-Based Training in Intensive Care Medicine in Europe (CoBaTrICE) program was established in 2003 as a Europe-based worldwide collaboration of national training organizations to create core competencies for ICM using consensus methodologies to establish common ground. The group's professional and research ethos created a social identity that facilitated change. The program was easily adaptable to different training structures and incorporated the voice of patients and relatives. The CoBaTrICE program has now been adopted by 15 European countries, with another 12 countries planning to adopt the training program, and is currently available in nine languages, including English. ICM is now recognized as a primary specialty in Spain, Switzerland, and the UK. There are still wide variations in structures and processes of training in ICM across Europe, although there has been agreement on a set of common program standards. The combination of a common "product specification" for an intensivist, combined with persisting variation in the educational context in which competencies are delivered, provides a rich source of research inquiry. Pedagogic research in ICM could usefully focus on the interplay between educational interventions, healthcare systems and delivery, and patient outcomes, such as including whether competency-based program are associated with lower error rates, whether communication skills training is associated with greater patient and family satisfaction, how multisource feedback might best be used to improve reflective learning and teamworking, or whether increasing the proportion of specialists trained in acute care in the hospital at weekends results in better patient outcomes.

International standards for programmes of training in intensive care medicine in Europe.

PURPOSE To develop internationally harmonised standards for programmes of training in intensive care medicine (ICM). METHODS Standards were developed by using consensus techniques. A nine-member nominal group of European intensive care experts developed a preliminary set of standards. These were revised and refined through a modified Delphi process involving 28 European national coordinators representing national training organisations using a combination of moderated discussion meetings, email, and a Web-based tool for determining the level of agreement with each proposed standard, and whether the standard could be achieved in the respondent's country. RESULTS The nominal group developed an initial set of 52 possible standards which underwent four iterations to achieve maximal consensus. All national coordinators approved a final set of 29 standards in four domains: training centres, training programmes, selection of trainees, and trainers' profiles. Only three standards were considered immediately achievable by all countries, demonstrating a willingness to aspire to quality rather than merely setting a minimum level. Nine proposed standards which did not achieve full consensus were identified as potential candidates for future review. CONCLUSIONS This preliminary set of clearly defined and agreed standards provides a transparent framework for assuring the quality of training programmes, and a foundation for international harmonisation and quality improvement of training in ICM.

Evaluation of Medical Students’ Attitudes and Performance of Basic Surgery Skills in a Training Program Using Fresh Human skin, Excised During Body Contouring Surgeries

BACKGROUND: Learning surgical skills in the operating room may be a challenge for medical students. Therefore, more approaches using simulation to enable students to develop their practical skills are required. OBJECTIVES: We hypothesized that (1) there would be a need for additional surgical training for medical students in the pre-final year, and (2) our basic surgery skills training program using fresh human skin would improve medical students' surgical skills. DESIGN: We conducted a preliminary survey of medical students to clarify the need for further training in basic surgery procedures. A new approach using simulation to teach surgical skills on human skin was set up. The procedural skills of 15 randomly selected students were assessed in the operating room before and after participation in the simulation, using Objective Structured Assessment of Technical Skills. Furthermore, subjective assessment was performed based on students' self-evaluation. The data were analyzed using SPSS, version 21 (SPSS, Inc., Chicago, IL). SETTING: The study took place at the Inselspital, Bern University Hospital. PARTICIPANTS: A total of 186 pre-final-year medical students were enrolled into the preliminary survey; 15 randomly selected medical students participated in the basic surgical skills training course on the fresh human skin operating room. RESULTS: The preliminary survey revealed the need for a surgical skills curriculum. The simulation approach we developed showed significant (p < 0.001) improvement for all 12 surgical skills, with mean cumulative precourse and postcourse values of 31.25 ± 5.013 and 45.38 ± 3.557, respectively. The self-evaluation contained positive feedback as well. CONCLUSION: Simulation of surgery using human tissue samples could help medical students become more proficient in handling surgical instruments before stepping into a real surgical situation. We suggest further studies evaluating our proposed teaching method and the possibility of integrating this simulation approach into the medical school curriculum.

How specific is apprenticeship training? Evidence from inter-firm and occupational mobility after graduation

Do apprenticeships convey mainly general or also firm- and occupation-specific human capital? Specific human capital may allow for specialization gains, but may also lead to allocative inefficiency due to mobility barriers. We analyse the case of Switzerland, which combines a comprehensive, high-quality apprenticeship system with a lightly regulated labour market. To assess human capital transferability after standardized firm-based apprenticeship training, we analyse inter-firm and occupational mobility and their effects on post-training wages. Using a longitudinal data set based on the PISA 2000 survey, we find high inter-firm and low occupational mobility within one year after graduation. Accounting for endogenous changes, we find a negative effect of occupation changes on wages, but no significant wage effect for firm changes. This indicates that occupation-specific human capital is an important component of apprenticeship training and that skills are highly transferable within an occupational field.