Convolutional Neural Network-Based Automated Segmentation of the Spinal Cord and Contusion Injury: Deep Learning Biomarker Correlates of Motor Impairment in Acute Spinal Cord Injury.

BACKGROUND AND PURPOSE: Our aim was to use 2D convolutional neural networks for automatic segmentation of the spinal cord and traumatic contusion injury from axial T2-weighted MR imaging in a cohort of patients with acute spinal cord injury. MATERIALS AND METHODS: Forty-seven patients who underwent 3T MR imaging within 24 hours of spinal cord injury were included. We developed an image-analysis pipeline integrating 2D convolutional neural networks for whole spinal cord and intramedullary spinal cord lesion segmentation. Linear mixed modeling was used to compare test segmentation results between our spinal cord injury convolutional neural network (Brain and Spinal Cord Injury Center segmentation) and current state-of-the-art methods. Volumes of segmented lesions were then used in a linear regression analysis to determine associations with motor scores. RESULTS: Compared with manual labeling, the average test set Dice coefficient for the Brain and Spinal Cord Injury Center segmentation model was 0.93 for spinal cord segmentation versus 0.80 for PropSeg and 0.90 for DeepSeg (both components of the Spinal Cord Toolbox). Linear mixed modeling showed a significant difference between Brain and Spinal Cord Injury Center segmentation compared with PropSeg (P < .001) and DeepSeg (P < .05). Brain and Spinal Cord Injury Center segmentation showed significantly better adaptability to damaged areas compared with PropSeg (P < .001) and DeepSeg (P < .02). The contusion injury volumes based on automated segmentation were significantly associated with motor scores at admission (P = .002) and discharge (P = .009). CONCLUSIONS: Brain and Spinal Cord Injury Center segmentation of the spinal cord compares favorably with available segmentation tools in a population with acute spinal cord injury. Volumes of injury derived from automated lesion segmentation with Brain and Spinal Cord Injury Center segmentation correlate with measures of motor impairment in the acute phase. Targeted convolutional neural network training in acute spinal cord injury enhances algorithm performance for this patient population and provides clinically relevant metrics of cord injury.

Multivariate Analysis of MRI Biomarkers for Predicting Neurologic Impairment in Cervical Spinal Cord Injury.

BACKGROUND AND PURPOSE: Acute markers of spinal cord injury are essential for both diagnostic and prognostic purposes. The goal of this study was to assess the relationship between early MR imaging biomarkers after acute cervical spinal cord injury and to evaluate their predictive validity of neurologic impairment. MATERIALS AND METHODS: We performed a retrospective cohort study of 95 patients with acute spinal cord injury and preoperative MR imaging within 24 hours of injury. The American Spinal Injury Association Impairment Scale was used as our primary outcome measure to define neurologic impairment. We assessed several MR imaging features of injury, including axial grade (Brain and Spinal Injury Center score), sagittal grade, length of injury, maximum canal compromise, and maximum spinal cord compression. Data-driven nonlinear principal component analysis was followed by correlation and optimal-scaled multiple variable regression to predict neurologic impairment. RESULTS: Nonlinear principal component analysis identified 2 clusters of MR imaging variables related to 1) measures of intrinsic cord signal abnormality and 2) measures of extrinsic cord compression. Neurologic impairment was best accounted for by MR imaging measures of intrinsic cord signal abnormality, with axial grade representing the most accurate predictor of short-term impairment, even when correcting for surgical decompression and degree of cord compression. CONCLUSIONS: This study demonstrates the utility of applying nonlinear principal component analysis for defining the relationship between MR imaging biomarkers in a complex clinical syndrome of cervical spinal cord injury. Of the assessed imaging biomarkers, the intrinsic measures of cord signal abnormality were most predictive of neurologic impairment in acute spinal cord injury, highlighting the value of axial T2 MR imaging.

Total quality management: doing things right.

Total quality management transforms quality assurance performance controls into a dynamic system for continuously improving healthcare services to internal and external "customers" in terms of outcomes. Success depends upon gaining and maintaining commitment of physicians, top management and key staff members through a working environment which values and rewards improvement efforts.

Health promotion of older adults: perceived barriers.

The purpose of this descriptive study was to examine the perceptions of rural men and women, ages 50 to 70 years, regarding barriers to health promotion in the treatment of a chronic disease entity--hypertension. Orem's constructs of self-care provided the theoretical framework for the study. Specific study aims were to (a) identify health belief/values, (b) assess perceptions of self-care abilities, (c) determine relative risk through health appraisal, and (d) describe phenomenological perceived barriers to health promotion as a lived experience. Major findings indicated no relationship between health beliefs/values and self-care. The health value scores of females for all four subscales were somewhat higher than the scores for males. Average, appraised and achievable ages for relative risk of dying from all causes were significant for men. Phenomenological themes revealed diet, weight and medication usage to be two factors associated with perceived barriers. Small sample size and voluntary participation limited generalization. Nursing implications included the need for (a) greater assessment of the influence of perceived barriers, (b) better approaches to health teaching, and (c) more appropriate design of educative--supportive nursing interventions for facilitating client self-care.

Perceptions of self-care in Sweden: a cross-cultural replication.

This cross-cultural study attempted to replicate the nursing phenomena of self-care and self-concept using two self-reporting instruments. Both instruments were translated from English into Swedish and administered on a convenience basis to 187 Swedish subjects, 117 women and 70 men, ages 19-66, compulsory to university educated, and residing in the southern districts of Sweden. Swedish mean self-care scores were lower (112.5) than the United States normative group of university nursing and psychology students, but the mean was comparable to East German (113.6) reported from an earlier study. Self-concept scores were similar to Nebraska teachers and East Germans. Alpha coefficients were used to assess reliability, ANOVA for differences, and item correlation of self-care agency were organized by factor analysis with four subfactors identified. The derived subscales appeared to identify potentially useful factors to aid in unravelling the complexity of the self-care agency construct. Study limitations were addressed. Cross-cultural directives for international nursing are discussed.

Perceptions of self-care in East Germany: a cross-cultural empirical investigation.

The purpose of this empirical investigation was replication for comparing self-care phenomena in a cross-cultural setting. Two self-reporting inventories were employed to measure perceptual dimensions of self-care agency and self-concept. Both inventories were translated into German and administered to a convenience sample of 17 adults living in an agricultural collective in East Germany. One research concern was the usability of American-constructed nursing assessment tools in another culture. Other research questions for cross-cultural comparisons of means were formulated. Self-care and self-concept were related in the East German sample. Self-care agency means for the East German sample were lower than for an American student sample. Study limitations are identified and cross-cultural implications of the findings for nursing are discussed.

Social dramatics: social skills development for the chronically mentally ill.

The purpose of this study was to investigate the use of social dramatics as a clinical tool for teaching social skills to the chronically mentally ill on adult inpatient units of a state hospital. The research tested the hypothesis that patients exposed to social dramatics with videotape feedback would demonstrate greater ability to perform social skills as measured by the Nurses' Observation Scale for Inpatient Evaluation (NOSIE-30). Fifteen schizophrenic adults of both sexes meeting specific criteria were randomly assigned to experimental and control groups. Subjects were exposed over an 8-week period to randomly introduced social dramatic scenarios. The Wilcoxin test for two independent samples was used for testing differences between experimental and control groups. The research findings supported the hypothesis for one positive factor, social competence. The findings did not support any treatment effect on either social interest and personal neatness or irritability, manifest psychosis, and psychotic depression. There were no significant differences on the total score NOSIE-30. Recommendations for psychiatric nursing are made. Limitations of research methodologies and sample size were addressed.