Healthy US population reference values for CT visceral fat measurements and the impact of IV contrast, HU range, and spinal levels.

Measurements of visceral adipose tissue cross-sectional area and radiation attenuation from computed tomography (CT) scans provide useful information about risk and mortality. However, scan protocols vary, encompassing differing vertebra levels and utilizing differing phases of contrast enhancement. Furthermore, fat measurements have been extracted from CT using different Hounsfield Unit (HU) ranges. To our knowledge, there have been no large studies of healthy cohorts that reported reference values for visceral fat area and radiation attenuation at multiple vertebra levels, for different contrast phases, and using different fat HU ranges. Two-phase CT scans from 1,677 healthy, adult kidney donors (age 18-65) between 1999 and 2017, previously studied to determine healthy reference values for skeletal muscle measures, were utilized. Visceral adipose tissue cross-sectional area (VFA) and radiation attenuation (VFRA) measures were quantified using axial slices at T10 through L4 vertebra levels. T-tests were used to compare males and females, while paired t-tests were conducted to determine the effect (magnitude and direction) of (a) contrast enhancement and (b) different fat HU ranges on each fat measure at each vertebra level. We report the means, standard deviations, and effect sizes of contrast enhancement and fat HU range. Male and female VFA and VFRA were significantly different at all vertebra levels in both contrast and non-contrast scans. Peak VFA was observed at L4 in females and L2 in males, while peak VFRA was observed at L1 in both females and males. In general, non-contrast scans showed significantly greater VFA and VFRA compared to contrast scans. The average paired difference due to contrast ranged from 1.6 to - 8% (VFA) and 3.2 to - 3.0% (VFRA) of the non-contrast value. HU range showed much greater differences in VFA and VFRA than contrast. The average paired differences due to HU range ranged from - 5.3 to 22.2% (VFA) and - 5.9 to 13.6% (VFRA) in non-contrast scans, and - 4.4 to 20.2% (VFA) and - 4.1 to 12.6% (VFRA) in contrast scans. The - 190 to - 30 HU range showed the largest differences in both VFA (10.8% to 22.2%) and VFRA (7.6% to 13.6%) compared to the reference range (- 205 to - 51 HU). Incidentally, we found that differences in lung inflation result in very large differences in visceral fat measures, particularly in the thoracic region. We assessed the independent effects of contrast presence and fat HU ranges on visceral fat cross-sectional area and mean radiation attenuation, finding significant differences particularly between different fat HU ranges. These results demonstrate that CT measurements of visceral fat area and radiation attenuation are strongly dependent upon contrast presence, fat HU range, sex, breath cycle, and vertebra level of measurement. We quantified contrast and non-contrast reference values separately for males and females, using different fat HU ranges, for lumbar and thoracic CT visceral fat measures at multiple vertebra levels in a healthy adult US population.

Simulated MRI Artifacts: Testing Machine Learning Failure Modes.

Objective. Seven types of MRI artifacts, including acquisition and preprocessing errors, were simulated to test a machine learning brain tumor segmentation model for potential failure modes. Introduction. Real-world medical deployments of machine learning algorithms are less common than the number of medical research papers using machine learning. Part of the gap between the performance of models in research and deployment comes from a lack of hard test cases in the data used to train a model. Methods. These failure modes were simulated for a pretrained brain tumor segmentation model that utilizes standard MRI and used to evaluate the performance of the model under duress. These simulated MRI artifacts consisted of motion, susceptibility induced signal loss, aliasing, field inhomogeneity, sequence mislabeling, sequence misalignment, and skull stripping failures. Results. The artifact with the largest effect was the simplest, sequence mislabeling, though motion, field inhomogeneity, and sequence misalignment also caused significant performance decreases. The model was most susceptible to artifacts affecting the FLAIR (fluid attenuation inversion recovery) sequence. Conclusion. Overall, these simulated artifacts could be used to test other brain MRI models, but this approach could be used across medical imaging applications.

Automated Measurements of Body Composition in Abdominal CT Scans Using Artificial Intelligence Can Predict Mortality in Patients With Cirrhosis.

Body composition measures derived from already available electronic medical records (computed tomography [CT] scans) can have significant value, but automation of measurements is needed for clinical implementation. We sought to use artificial intelligence to develop an automated method to measure body composition and test the algorithm on a clinical cohort to predict mortality. We constructed a deep learning algorithm using Google's DeepLabv3+ on a cohort of de-identified CT scans (n = 12,067). To test for the accuracy and clinical usefulness of the algorithm, we used a unique cohort of prospectively followed patients with cirrhosis (n = 238) who had CT scans performed. To assess model performance, we used the confusion matrix and calculated the mean accuracy of 0.977 ± 0.02 (0.975 ± 0.018 for the training and test sets, respectively). To assess for spatial overlap, we measured the mean intersection over union and mean boundary contour scores and found excellent overlap between the manual and automated methods with mean scores of 0.954 ± 0.030, 0.987 ± 0.009, and 0.948 ± 0.039 (0.983 ± 0.013 for the training and test set, respectively). Using these automated measurements, we found that body composition features were predictive of mortality in patients with cirrhosis. On multivariate analysis, the addition of body composition measures significantly improved prediction of mortality for patients with cirrhosis over Model for End-Stage Liver Disease alone (P < 0.001). Conclusion: The measurement of body composition can be automated using artificial intelligence and add significant value for incidental CTs performed for other clinical indications. This is proof of concept that this methodology could allow for wider implementation into the clinical arena.

Optimal body size adjustment of L3 CT skeletal muscle area for sarcopenia assessment.

Measurements of skeletal muscle cross-sectional area (SMA) at the level of the third lumbar (L3) vertebra derived from clinical computed tomography (CT) scans are commonly used in assessments of sarcopenia, the loss of skeletal muscle mass and function associated with aging. As SMA is correlated with height and Body Mass Index (BMI), body size adjustment is necessary to fairly assess sarcopenic low muscle mass in individuals of different height and BMI. The skeletal muscle index, a widely used measure, adjusts for height as [Formula: see text] but uses no BMI adjustment. There is no agreed upon standard for body size adjustment. We extracted L3 SMA using non-contrast-enhanced CT scans from healthy adults, split into 'Under-40' and 'Over-40' cohorts. Sex-specific allometric analysis showed that height to the power of one was the optimal integer coefficient for height adjusted SMA in both males and females. We computed two height-adjusted measures [Formula: see text] and [Formula: see text], comparing their Pearson correlations versus age, height, weight, and BMI separately by sex and cohort. Finally, in the 'Under-40' cohort, we used linear regression to convert each height-adjusted measure into a z-score ([Formula: see text], [Formula: see text]) adjusted for BMI. [Formula: see text] was less correlated with height in both males and females ([Formula: see text], [Formula: see text] and [Formula: see text], [Formula: see text]) than [Formula: see text] ([Formula: see text] and [Formula: see text], [Formula: see text]). [Formula: see text] was uncorrelated with BMI and weight, and minimally correlated with height in males and females ([Formula: see text], [Formula: see text] and [Formula: see text], [Formula: see text]). The final [Formula: see text] equation was: [Formula: see text], where [Formula: see text], [Formula: see text], [Formula: see text], and sex = 1 if male, 0 if female. We propose [Formula: see text] for optimal height adjustment and the [Formula: see text] score for optimal height and BMI adjustment. By minimizing correlations with height and BMI, the [Formula: see text] score produces unbiased assessments of relative L3 skeletal muscle area across the full range of body sizes.

Automated Measurements of Muscle Mass Using Deep Learning Can Predict Clinical Outcomes in Patients With Liver Disease.

INTRODUCTION: There is increasing recognition of the central role of muscle mass in predicting clinical outcomes in patients with liver disease. Muscle size can be extracted from computed tomography (CT) scans, but clinical implementation will require increased automation. We hypothesize that we can achieve this by using artificial intelligence. METHODS: Using deep convolutional neural networks, we trained an algorithm on the Reference Analytic Morphomics Population (n = 5,268) and validated the automated methodology in an external cohort of adult kidney donors with a noncontrast CT scan (n = 1,655). To test the clinical usefulness, we examined its ability to predict clinical outcomes in a prospectively followed cohort of patients with clinically diagnosed cirrhosis (n = 254). RESULTS: Between the manual and automated methodologies, we found excellent inter-rater agreement with an intraclass correlation coefficient of 0.957 (confidence interval 0.953-0.961, P < 0.0001) in the adult kidney donor cohort. The calculated dice similarity coefficient was 0.932 ± 0.042, suggesting excellent spatial overlap between manual and automated methodologies. To assess the clinical usefulness, we examined its ability to predict clinical outcomes in a cirrhosis cohort and found that automated psoas muscle index was independently associated with mortality after adjusting for age, gender, and child's classification (P < 0.001). DISCUSSION: We demonstrated that deep learning techniques can allow for automation of muscle measurements on clinical CT scans in a diseased cohort. These automated psoas size measurements were predictive of mortality in patients with cirrhosis showing proof of principal that this methodology may allow for wider implementation in the clinical arena.

Comparisons of Manual Tape Measurement and Morphomics Measurement of Patients with Upper Extremity Lymphedema.

BACKGROUND: Lymphedema is a debilitating condition characterized by swelling from lymph fluid exceeding transport capacity. A gold standard for arm measurement is not established, and measurement methods vary. This study evaluates the comparability of the tape measure and Analytic Morphomics in deriving limb circumference measurements in patients with upper extremity lymphedema. METHODS: Fifteen participants with diagnosed upper limb lymphedema were included between July 2013 and June 2017 at Chang Gung Memorial Hospital in Taipei, Taiwan. Affected and unaffected arm circumferences were measured using a flexible tape or morphomic measurement at 10 cm above and below the elbow. Computed tomography scans were standardized, processed, smoothed with a piecewise polynomial algorithm for Analytic Morphomics of arm circumference. Comparative plots, mean percent difference, and adjusted coefficient of determination (R 2) were utilized to compare the consistency of both measurement procedures. RESULTS: The tape measure and Analytic Morphomics demonstrated consistent measures of arm circumference. On the affected arm, the mean (95% CI) difference in arm circumference between methods was 1.60 cm (0.99-2.20) above, and 0.57 cm (0.23-0.91) below the elbow. Mean percent differences in circumference was 6.65% (SD 3.52%) above and 1.38% (SD 2.11%) below the elbow. The adjusted R 2 for both methods was 94% above and 96% below the elbow. CONCLUSIONS: Analytic Morphomics showed strong consistency with the manual tape measure of arm circumference measurement in those with upper extremity lymphedema. Analytic Morphomics present an opportunity for a precise, granular measurement of limb composition for assessment of disease state and patient planning.

Computed tomography correlation of skeletal landmarks and vascular anatomy in civilian adult trauma patients: Implications for resuscitative endovascular balloon occlusion of the aorta.

BACKGROUND: Resuscitative endovascular balloon occlusion of the aorta (REBOA) is a valuable resuscitative adjunct in a variety of clinical settings. In resource-limited or emergency environments, REBOA may be required with delayed or absent image-guidance or verification. Catheter insertion lengths may be informed by making computed tomography (CT) correlations of skeletal landmarks with vascular lengths. METHODS: Between 2000 and 2015 at a single civilian tertiary care center, 2,247 trauma patients with CT imaging were identified, yielding 1,789 patients with adequate contrast opacification of the arterial system in the chest, abdomen, and pelvis. Individual scans were analyzed using MATLAB software, with custom high-throughput image processing algorithms applied to correlate centerline vascular anatomy with musculoskeletal landmarks. Data were analyzed using R version 3.3. RESULTS: The median centerline distance from the skin access to the aortic bifurcation was longer by 0.3 cm on the right than on the left side. Median aortic zone I length was 21.6 (interquartile range, 20.3-22.9) cm, while zone III was 8.7 (7.8-9.5) cm. Torso extent (TE) correlation to zone I was much higher than that for zone III (R2, 0.58 vs. 0.26 (right) and 0.58 vs. 0.27 (left); p < 0.001). Assuming a 4-cm balloon length, optimal fixed insertion length would be 48 cm and 28 cm for zones I and III (error, 0.4% vs. 33.3%), respectively, although out of zone placements can be reduced if adjusted for TE (error, 0% vs. 26.4%). CONCLUSION: Computed tomography morphometry suggests that a fixed REBOA catheter insertion length of 48 cm for zone I and 28 cm for zone III is optimal (on average, for average-height individuals), with improved accuracy by formulaic adjustments for TE. High residual error for zone III placement may require redesign of existing catheter balloon lengths or consideration of the relative risk associated with placing the balloon catheter too low or too high. LEVEL OF EVIDENCE: Prognostic/epidemiological, level III.

Skeletal muscle cutoff values for sarcopenia diagnosis using T10 to L5 measurements in a healthy US population.

Measurements of skeletal muscle cross-sectional area, index, and radiation attenuation utilizing clinical computed tomography (CT) scans are used in assessments of sarcopenia, the loss of skeletal muscle mass and function associated with aging. To classify individuals as sarcopenic, sex-specific cutoffs for 'low' values are used. Conventionally, cutoffs for skeletal muscle measurements at the level of the third lumbar (L3) vertebra are used, however L3 is not included in several clinical CT protocols. Non-contrast-enhanced CT scans from healthy kidney donor candidates (age 18-40) at Michigan Medicine were utilized. Skeletal muscle area (SMA), index (SMI), and mean attenuation (SMRA) were measured at each vertebral level between the tenth thoracic (T10) and the fifth lumbar (L5) vertebra. Sex-specific means, standard deviations (s.d.), and sarcopenia cutoffs (mean-2 s.d.) at each vertebral level were computed. Associations between vertebral levels were assessed using Pearson correlations and Tukey's difference test. Classification agreement between different vertebral level cutoffs was assessed using overall accuracy, specificity, and sensitivity. SMA, SMI, and SMRA L3 cutoffs for sarcopenia were 92.2 cm2, 34.4 cm2/m2, and 34.3 HU in females, and 144.3 cm2, 45.4 cm2/m2, and 38.5 HU in males, consistent with previously reported cutoffs. Correlations between all level pairs were statistically significant and high, ranging from 0.65 to 0.95 (SMA), 0.64 to 0.95 (SMI), and 0.63 to 0.95 (SMRA). SMA peaks at L3, supporting its use as the primary site for CT sarcopenia measurements. However, when L3 is not available alternative levels (in order of preference) are L2, L4, L5, L1, T12, T11, and T10. Healthy reference values reported here enable sarcopenia assessment and sex-specific standardization of SMA, SMI, and SMRA in clinical populations, including those whose CT protocols do not include L3.

The Michigan Surgical Home and Optimization Program is a scalable model to improve care and reduce costs.

BACKGROUND: The Michigan Surgical Home and Optimization Program is a structured, home-based, preoperative training program targeting physical, nutritional, and psychological guidance. The purpose of this study was to determine if participation in this program was associated with reduced hospital duration of stay and health care costs. METHODS: We conducted a retrospective, single center, cohort study evaluating patients who participated in the Michigan Surgical Home and Optimization Program and subsequently underwent major elective general and thoracic operative care between June 2014 and December 2015. Propensity score matching was used to match program participants to a control group who underwent operative care prior to program implementation. Primary outcome measures were hospital duration of stay and payer costs. Multivariate regression was used to determine the covariate-adjusted effect of program participation. RESULTS: A total of 641 patients participated in the program; 82% were actively engaged in the program, recording physical activity at least 3 times per week for the majority of the program; 182 patients were propensity matched to patients who underwent operative care prior to program implementation. Multivariate analysis demonstrated that participation in the Michigan Surgical Home and Optimization Program was associated with a 31% reduction in hospital duration of stay (P < .001) and 28% lower total costs (P < .001) after adjusting for covariates. CONCLUSION: A home-based, preoperative training program decreased hospital duration of stay, lowered costs of care, and was well accepted by patients. Further efforts will focus on broader implementation and linking participation to postoperative complications and rigorous patient-reported outcomes.

Quantification of pediatric and adult cervical vertebra-anatomical characteristics by age and gender for automotive application.

OBJECTIVE: The cervical anatomy has been shown to affect injury patterns in vehicle crashes. Characterizing the spine anatomy and changes associated with growth and gender is important when assessing occupant protection. In this study, selected cervical characteristics were quantified. METHODS: Computed tomography (CT) scans of 750 patients were selected from the University of Michigan trauma database; 314 were children and 436 were adults. Four variables were obtained: the maximum spinal canal radius, vertebral body depth, facet angles, and retroversion angles. RESULTS: The cervical spine measurements varied with age and gender. The body depth increased nonlinearly with age. The average vertebral body depth at C4 was 9.2 ± 0.38 mm in the 0-3 age group, 15.7 ± 0.29 mm in the 18-29 age group, and 17.2 ± 0.46 mm in the 60+ age group. Pediatric and adult males had larger vertebral body depth than females overall, irrespective of vertebral level (P <.001). Compared to females, the vertebral body depth was 8-9 percent greater in male children and 13-16 percent greater in adult males. The average radius varied with gender, with male children generally having a larger radius than females irrespective of vertebral level (P <.001). Overall, spinal canal radius was smallest in the 0-3 and 60+ age groups and largest in the 18-29 age group. The C4 radius was 5.91 ± 0.17, 6.28 ± 0.14, and 6.73 ± 0.17 mm respectively. The radius was larger in the 4-7 age group than in the 0-3 age group, irrespective of vertebral level (P <.0001). There were nonsignificant radius changes between the 4-7 and 8-11 age groups and the 8-11 and age 12-17 groups, suggesting that the size of the spinal cord reaches near maturation by the age of 7. Facet angles decreased with age in children and increased with age in adults. The average facet angles were largest in the 0-3 age group (P <.1, C2-C6). Adult facet angles were greater in the 60+ age group than in the 18-29 age group (P <.0001, C2-C6). Males had larger facet angles than females overall (P <.01 at C2, C5-C7). The retroversion angles were largest at C6 and C7. They increased with age in children and decreased in the adult population; they were larger (5-22%) in the 18-29 age group than in the 60+ age group (P <.0001, C2-C6). CONCLUSIONS: The results obtained in this study help explain variations in cervical anatomical changes associated with age and gender. The information is useful when assessing differences in injury patterns between different segments of the population. Anatomical measurements of the cervical spine should be considered for the development of models used to assess injury mechanisms for various occupant age groups.