Search

Injuries of the spine, and its posterior elements in particular, are a common occurrence in trauma patients, with potentially devastating consequences. Computer-aided detection (CADe) could assist in the detection and classification of spine fractures. Furthermore, CAD could help assess the stability and chronicity of fractures, as well as facilitate research into optimization of treatment paradigms. In this work, we apply deep convolutional networks (ConvNets) for the automated detection of posterior element fractures of the spine. First, the vertebra bodies of the spine with its posterior elements are segmented in spine CT using multi-atlas label fusion. Then, edge maps of the posterior elements are computed. These edge maps serve as candidate regions for predicting a set of probabilities for fractures along the image edges using ConvNets in a 2.5D fashion (three orthogonal patches in axial, coronal and sagittal planes). We explore three different methods for training the ConvNet using 2.5D patches along the edge maps of 'positive', i.e. fractured posterior-elements and 'negative', i.e. non-fractured elements. An experienced radiologist retrospectively marked the location of 55 displaced posterior-element fractures in 18 trauma patients. We randomly split the data into training and testing cases. In testing, we achieve an area-under-the-curve of 0.857. This corresponds to 71% or 81% sensitivities at 5 or 10 false-positives per patient, respectively. Analysis of our set of trauma patients demonstrates the feasibility of detecting posterior-element fractures in spine CT images using computer vision techniques such as deep convolutional networks.

Automated detection of sclerotic metastases (bone lesions) in Computed Tomography (CT) images has potential to be an important tool in clinical practice and research. State-of-the-art methods show performance of 79 % sensitivity or truepositive (TP) rate, at 10 false-positives (FP) per volume. We design a two-tiered coarse-to-fine cascade framework to first operate a highly sensitive candidate generation system at a maximum sensitivity of ∼92% but with high FP level (∼50 per patient). Regions of interest (ROI) for lesion candidates are generated in this step and function as input for the second tier. In the second tier we generate N 2D views, via scale, random translations, and rotations with respect to each ROI centroid coordinates. These random views are used to train a deep Convolutional Neural Network (CNN) classifier. In testing, the CNN is employed to assign individual probabilities for a new set of N random views that are averaged at each ROI to compute a final per-candidate classification probability. This second tier behaves as a highly selective process to reject difficult false positives while preserving high sensitivities. We validate the approach on CT images of 59 patients (49 with sclerotic metastases and 10 normal controls). The proposed method reduces the number of FP/vol.from 4 to 1.2, 7 to 3, and 12 to 9.5 when comparing a sensitivity rates of 60, 70, and 80% respectively in testing. The Area-Under-the-Curve (AUC) is 0.834. The results show marked improvement upon previous work.

BackgroundChronic obstructive pulmonary disease (COPD) is highly prevalent and significantly affects the daily functioning of patients. Self-management strategies, including increasing physical activity, can help people with COPD have better health and a better quality of life. Digital mobile health (mHealth) techniques have the potential to aid the delivery of self-management interventions for COPD. We developed an mHealth intervention (Self-Management supported by Assistive, Rehabilitative, and Telehealth technologies-COPD [SMART-COPD]), delivered via a smartphone app and an activity tracker, to help people with COPD maintain (or increase) physical activity after undertaking pulmonary rehabilitation (PR). ObjectiveThis study aimed to determine the feasibility and acceptability of using the SMART-COPD intervention for the self-management of physical activity and to explore the feasibility of conducting a future randomized controlled trial (RCT) to investigate its effectiveness. MethodsWe conducted a randomized feasibility study. A total of 30 participants with COPD were randomly allocated to receive the SMART-COPD intervention (n=19) or control (n=11). Participants used SMART-COPD throughout PR and for 8 weeks afterward (ie, maintenance) to set physical activity goals and monitor their progress. Questionnaire-based and physical activity–based outcome measures were taken at baseline, the end of PR, and the end of maintenance. Participants, and health care professionals involved in PR delivery, were interviewed about their experiences with the technology. ResultsOverall, 47% (14/30) of participants withdrew from the study. Difficulty in using the technology was a common reason for withdrawal. Participants who completed the study had better baseline health and more prior experience with digital technology, compared with participants who withdrew. Participants who completed the study were generally positive about the technology and found it easy to use. Some participants felt their health had benefitted from using the technology and that it assisted them in achieving physical activity goals. Activity tracking and self-reporting were both found to be problematic as outcome measures of physical activity for this study. There was dissatisfaction among some control group members regarding their allocation. ConclusionsmHealth shows promise in helping people with COPD self-manage their physical activity levels. mHealth interventions for COPD self-management may be more acceptable to people with prior experience of using digital technology and may be more beneficial if used at an earlier stage of COPD. Simplicity and usability were more important for engagement with the SMART-COPD intervention than personalization; therefore, the intervention should be simplified for future use. Future evaluation will require consideration of individual factors and their effect on mHealth efficacy and use; within-subject comparison of step count values; and an opportunity for control group participants to use the intervention if an RCT were to be carried out. Sample size calculations for a future evaluation would need to consider the high dropout rates.

Background: Allograft survival among black recipients is poorer than among whites. Delayed allograft function is associated with a significant reduction in renal allograft survival. The relationship between delayed allograft function and black race is incompletely specified and was the focus of this investigation. [ABSTRACT FROM PUBLISHER]

Little is known about infectious complications of lumbar puncture (LP) in children. We reviewed records of children with bacterial meningitis, intraspinal abscess, and vertebral osteomyelitis over a 3-year period to identify infections following LP. Four children with bacterial meningitis and 1 child with vertebral osteomyelitis were identified and their clinical presentations were described. These cases were scored by infectious disease experts, using a Likert scale, for the possibility of iatrogenic causation; these scores were variable, reflecting uncertainty. The bacterial meningitis cases had repeat LPs, and the latter cerebrospinal fluid analyses were diagnostic of bacterial meningitis; the interval between the initial "index" LP (I-LP) and symptom onset was 8 to 10 hours in most cases. Pediatricians should be aware of this possibility, and have a low threshold to repeat LP if there is a clinical change after the I-LP that could be consistent with meningitis., Competing Interests: Declaration of Conflicting InterestsThe author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.