Study protocol : Screening and treatment of alcohol-related trauma (START): a randomised controlled trial

Background: The incidence of mandibular fractures in the Northern Territory of Australia is very high, especially among Indigenous people. Alcohol intoxication is implicated in the majority of facial injuries, and substance use is therefore an important target for secondary prevention. The current study tests the efficacy of a brief therapy, Motivational Care Planning, in improving wellbeing and substance misuse in youth and adults hospitalised with alcohol-related facial trauma. Methods and design: The study is a randomised controlled trial with 6 months of follow-up, to examine the effectiveness of a brief and culturally adapted intervention in improving outcomes for trauma patients with at-risk drinking admitted to the Royal Darwin Hospital maxillofacial surgery unit. Potential participants are identified using AUDIT-C questionnaire. Eligible participants are randomised to either Motivational Care Planning (MCP) or Treatment as Usual (TAU). The outcome measures will include quantity and frequency of alcohol and other substance use by Timeline Followback. The recruitment target is 154 participants, which with 20% dropout, is hoped to provide 124 people receiving treatment and follow-up. Discussion: This project introduces screening and brief interventions for high-risk drinkers admitted to the hospital with facial trauma. It introduces a practical approach to integrating brief interventions in the hospital setting, and has potential to demonstrate significant benefits for at-risk drinkers with facial trauma.

Cement-in-cement revision for selected Vancouver Type B1 femoral periprosthetic fractures : A biomechanical analysis

The aim of this study was to perform a biomechanical analysis of the cement-in-cement (c-in-c) technique for fixation of selected Vancouver Type B1 femoral periprosthetic fractures and to assess the degree of cement interposition at the fracture site. Six embalmed cadaveric femora were implanted with a cemented femoral stem. Vancouver Type B1 fractures were created by applying a combined axial and rotational load to failure. The femora were repaired using the c-in-c technique and reloaded to failure. The mean primary fracture torque was 117 Nm (SD 16.6, range 89–133). The mean revision fracture torque was 50 Nm (SD 16.6, range 29–74), which is above the torque previously observed for activities of daily living. Cement interposition at the fracture site was found to be minimal.

Gradual training of cascaded shape regression for facial landmark localization and pose estimation

Facial landmarks play an important role in face recognition. They serve different steps of the recognition such as pose estimation, face alignment, and local feature extraction. Recently, cascaded shape regression has been proposed to accurately locate facial landmarks. A large number of weak regressors are cascaded in a sequence to fit face shapes to the correct landmark locations. In this paper, we propose to improve the method by applying gradual training. With this training, the regressors are not directly aimed to the true locations. The sequence instead is divided into successive parts each of which is aimed to intermediate targets between the initial and the true locations. We also investigate the incorporation of pose information in the cascaded model. The aim is to find out whether the model can be directly used to estimate head pose. Experiments on the Annotated Facial Landmarks in the Wild database have shown that the proposed method is able to improve the localization and give accurate estimates of pose.

A retrospective cohort investigation of active range of motion within one week of open reduction and internal fixation of distal radius fractures

Distal radius fractures stabilized by open reduction internal fixation (ORIF) have become increasingly common. There is currently no consensus on the optimal time to commence range of motion (ROM) exercises post-ORIF. A retrospective cohort review was conducted over a five-year period to compare wrist and forearm range of motion outcomes and number of therapy sessions between patients who commenced active ROM exercises within the first seven days and from day eight onward following ORIF of distal radius fractures. One hundred and twenty-one patient cases were identified. Clinical data, active ROM at initial and discharge therapy assessments, fracture type, surgical approaches, and number of therapy sessions attended were recorded. One hundred and seven (88.4%) cases had complete datasets. The early active ROM group (n = 37) commenced ROM a mean (SD) of 4.27 (1.8) days post-ORIF. The comparator group (n = 70) commenced ROM exercises 24.3 (13.6) days post-ORIF. No significant differences were identified between groups in ROM at initial or discharge assessments, or therapy sessions attended. The results from this study indicate that patients who commenced active ROM exercises an average of 24 days after surgery achieved comparable ROM outcomes with similar number of therapy sessions to those who commenced ROM exercises within the first week.

Recognising facial expressions with noisy data

Techniques to improve the automated analysis of natural and spontaneous facial expressions have been developed. The outcome of the research has applications in several fields including national security (eg: expression invariant face recognition); education (eg: affect aware interfaces); mental and physical health (eg: depression and pain recognition).

Facial expression recognition experiments with data from television broadcasts and the world wide web

Facial expression recognition (FER) systems must ultimately work on real data in uncontrolled environments although most research studies have been conducted on lab-based data with posed or evoked facial expressions obtained in pre-set laboratory environments. It is very difficult to obtain data in real-world situations because privacy laws prevent unauthorized capture and use of video from events such as funerals, birthday parties, marriages etc. It is a challenge to acquire such data on a scale large enough for benchmarking algorithms. Although video obtained from TV or movies or postings on the World Wide Web may also contain ‘acted’ emotions and facial expressions, they may be more ‘realistic’ than lab-based data currently used by most researchers. Or is it? One way of testing this is to compare feature distributions and FER performance. This paper describes a database that has been collected from television broadcasts and the World Wide Web containing a range of environmental and facial variations expected in real conditions and uses it to answer this question. A fully automatic system that uses a fusion based approach for FER on such data is introduced for performance evaluation. Performance improvements arising from the fusion of point-based texture and geometry features, and the robustness to image scale variations are experimentally evaluated on this image and video dataset. Differences in FER performance between lab-based and realistic data, between different feature sets, and between different train-test data splits are investigated.

Prevention of Alcohol-Related Crime and Trauma (PACT) : brief interventions in routine care pathway – a study protocol

Background Globally, alcohol-related injuries cause millions of deaths and huge economic loss each year . The incidence of facial (jawbone) fractures in the Northern Territory of Australia is second only to Greenland, due to a strong involvement of alcohol in its aetiology, and high levels of alcohol consumption. The highest incidences of alcohol-related trauma in the Territory are observed amongst patients in the Maxillofacial Surgery Unit of the Royal Darwin Hospital. Accordingly, this project aims to introduce screening and brief interventions into this unit, with the aims of changing health service provider practice, improving access to care, and improving patient outcomes. Methods Establishment of Project Governance: The project governance team includes a project manager, project leader, an Indigenous Reference Group (IRG) and an Expert Reference Group (ERG). Development of a best practice pathway: PACT project researchers collaborate with clinical staff to develop a best practice pathway suited to the setting of the surgical unit. The pathway provides clear guidelines for screening, assessment, intervention and referral. Implementation: The developed pathway is introduced to the unit through staff training workshops and associate resources and adapted in response to staff feedback. Evaluation: File audits, post workshop questionnaires and semi-structured interviews are administered. Discussion This project allows direct transfer of research findings into clinical practice and can inform future hospital-based injury prevention strategies.

Clinician-driven automated classification of limb fractures from free-text radiology reports

The aim of this research is to report initial experimental results and evaluation of a clinician-driven automated method that can address the issue of misdiagnosis from unstructured radiology reports. Timely diagnosis and reporting of patient symptoms in hospital emergency departments (ED) is a critical component of health services delivery. However, due to disperse information resources and vast amounts of manual processing of unstructured information, a point-of-care accurate diagnosis is often difficult. A rule-based method that considers the occurrence of clinician specified keywords related to radiological findings was developed to identify limb abnormalities, such as fractures. A dataset containing 99 narrative reports of radiological findings was sourced from a tertiary hospital. The rule-based method achieved an F-measure of 0.80 and an accuracy of 0.80. While our method achieves promising performance, a number of avenues for improvement were identified using advanced natural language processing (NLP) techniques.

Automatic classification of free-text radiology reports to identify limb fractures using machine learning and the SNOMED CT ontology

Objective To develop and evaluate machine learning techniques that identify limb fractures and other abnormalities (e.g. dislocations) from radiology reports. Materials and Methods 99 free-text reports of limb radiology examinations were acquired from an Australian public hospital. Two clinicians were employed to identify fractures and abnormalities from the reports; a third senior clinician resolved disagreements. These assessors found that, of the 99 reports, 48 referred to fractures or abnormalities of limb structures. Automated methods were then used to extract features from these reports that could be useful for their automatic classification. The Naive Bayes classification algorithm and two implementations of the support vector machine algorithm were formally evaluated using cross-fold validation over the 99 reports. Result Results show that the Naive Bayes classifier accurately identifies fractures and other abnormalities from the radiology reports. These results were achieved when extracting stemmed token bigram and negation features, as well as using these features in combination with SNOMED CT concepts related to abnormalities and disorders. The latter feature has not been used in previous works that attempted classifying free-text radiology reports. Discussion Automated classification methods have proven effective at identifying fractures and other abnormalities from radiology reports (F-Measure up to 92.31%). Key to the success of these techniques are features such as stemmed token bigrams, negations, and SNOMED CT concepts associated with morphologic abnormalities and disorders. Conclusion This investigation shows early promising results and future work will further validate and strengthen the proposed approaches.

Automated classification of limb fractures from free-text radiology reports using a clinician-informed gazetteer methodology

Background Timely diagnosis and reporting of patient symptoms in hospital emergency departments (ED) is a critical component of health services delivery. However, due to dispersed information resources and a vast amount of manual processing of unstructured information, accurate point-of-care diagnosis is often difficult. Aims The aim of this research is to report initial experimental evaluation of a clinician-informed automated method for the issue of initial misdiagnoses associated with delayed receipt of unstructured radiology reports. Method A method was developed that resembles clinical reasoning for identifying limb abnormalities. The method consists of a gazetteer of keywords related to radiological findings; the method classifies an X-ray report as abnormal if it contains evidence contained in the gazetteer. A set of 99 narrative reports of radiological findings was sourced from a tertiary hospital. Reports were manually assessed by two clinicians and discrepancies were validated by a third expert ED clinician; the final manual classification generated by the expert ED clinician was used as ground truth to empirically evaluate the approach. Results The automated method that attempts to individuate limb abnormalities by searching for keywords expressed by clinicians achieved an F-measure of 0.80 and an accuracy of 0.80. Conclusion While the automated clinician-driven method achieved promising performances, a number of avenues for improvement were identified using advanced natural language processing (NLP) and machine learning techniques.

Accurate placement of a pelvic binder improves reduction of unstable fractures of the pelvic ring

The aim of this study was to assess the accuracy of placement of pelvic binders and to determine whether circumferential compression at the level of the greater trochanters is the best method of reducing a symphyseal diastasis. Patients were identified by a retrospective review of all pelvic radiographs performed at a military hospital over a period of 30 months. We analysed any pelvic radiograph on which the buckle of the pelvic binder was clearly visible. The patients were divided into groups according to the position of the buckle in relation to the greater trochanters: high, trochanteric or low. Reduction of the symphyseal diastasis was measured in a subgroup of patients with an open-book fracture, which consisted of an injury to the symphysis and disruption of the posterior pelvic arch (AO/OTA 61-B/C). We identified 172 radiographs with a visible pelvic binder. Five cases were excluded due to inadequate radiographs. In 83 (50%) the binder was positioned at the level of the greater trochanters. A high position was the most common site of inaccurate placement, occurring in 65 (39%). Seventeen patients were identified as a subgroup to assess the effect of the position of the binder on reduction of the diastasis. The mean gap was 2.8 times greater (mean difference 22 mm) in the high group compared with the trochanteric group (p < 0.01). Application of a pelvic binder above the level of the greater trochanters is common and is an inadequate method of reducing pelvic fractures and is likely to delay cardiovascular recovery in these seriously injured patients.

Random Gabor based templates for facial expression recognition in images with facial occlusion

Robust facial expression recognition (FER) under occluded face conditions is challenging. It requires robust algorithms of feature extraction and investigations into the effects of different types of occlusion on the recognition performance to gain insight. Previous FER studies in this area have been limited. They have spanned recovery strategies for loss of local texture information and testing limited to only a few types of occlusion and predominantly a matched train-test strategy. This paper proposes a robust approach that employs a Monte Carlo algorithm to extract a set of Gabor based part-face templates from gallery images and converts these templates into template match distance features. The resulting feature vectors are robust to occlusion because occluded parts are covered by some but not all of the random templates. The method is evaluated using facial images with occluded regions around the eyes and the mouth, randomly placed occlusion patches of different sizes, and near-realistic occlusion of eyes with clear and solid glasses. Both matched and mis-matched train and test strategies are adopted to analyze the effects of such occlusion. Overall recognition performance and the performance for each facial expression are investigated. Experimental results on the Cohn-Kanade and JAFFE databases demonstrate the high robustness and fast processing speed of our approach, and provide useful insight into the effects of occlusion on FER. The results on the parameter sensitivity demonstrate a certain level of robustness of the approach to changes in the orientation and scale of Gabor filters, the size of templates, and occlusions ratios. Performance comparisons with previous approaches show that the proposed method is more robust to occlusion with lower reductions in accuracy from occlusion of eyes or mouth.

Inpatient facial expression recognition with SMS alert

Facial expression recognition (FER) has been dramatically developed in recent years, thanks to the advancements in related fields, especially machine learning, image processing and human recognition. Accordingly, the impact and potential usage of automatic FER have been growing in a wide range of applications, including human-computer interaction, robot control and driver state surveillance. However, to date, robust recognition of facial expressions from images and videos is still a challenging task due to the difficulty in accurately extracting the useful emotional features. These features are often represented in different forms, such as static, dynamic, point-based geometric or region-based appearance. Facial movement features, which include feature position and shape changes, are generally caused by the movements of facial elements and muscles during the course of emotional expression. The facial elements, especially key elements, will constantly change their positions when subjects are expressing emotions. As a consequence, the same feature in different images usually has different positions. In some cases, the shape of the feature may also be distorted due to the subtle facial muscle movements. Therefore, for any feature representing a certain emotion, the geometric-based position and appearance-based shape normally changes from one image to another image in image databases, as well as in videos. This kind of movement features represents a rich pool of both static and dynamic characteristics of expressions, which playa critical role for FER. The vast majority of the past work on FER does not take the dynamics of facial expressions into account. Some efforts have been made on capturing and utilizing facial movement features, and almost all of them are static based. These efforts try to adopt either geometric features of the tracked facial points, or appearance difference between holistic facial regions in consequent frames or texture and motion changes in loca- facial regions. Although achieved promising results, these approaches often require accurate location and tracking of facial points, which remains problematic.

A pilot study on affective classification of facial images for emerging news topics

The proliferation of news reports published in online websites and news information sharing among social media users necessitates effective techniques for analysing the image, text and video data related to news topics. This paper presents the first study to classify affective facial images on emerging news topics. The proposed system dynamically monitors and selects the current hot (of great interest) news topics with strong affective interestingness using textual keywords in news articles and social media discussions. Images from the selected hot topics are extracted and classified into three categorized emotions, positive, neutral and negative, based on facial expressions of subjects in the images. Performance evaluations on two facial image datasets collected from real-world resources demonstrate the applicability and effectiveness of the proposed system in affective classification of facial images in news reports. Facial expression shows high consistency with the affective textual content in news reports for positive emotion, while only low correlation has been observed for neutral and negative. The system can be directly used for applications, such as assisting editors in choosing photos with a proper affective semantic for a certain topic during news report preparation.