Prediction of Stroke Infarct Growth Rates by Baseline Perfusion Imaging

Background and Purpose: Computed tomography perfusion imaging allows estimation of tissue status in patients with acute ischemic stroke. We aimed to improve prediction of the final infarct and individual infarct growth rates using a deep learning approach. Methods: We trained a deep neural network to predict the final infarct volume in patients with acute stroke presenting with large vessel occlusions based on the native computed tomography perfusion images, time to reperfusion and reperfusion status in a derivation cohort (MR CLEAN trial [Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands]). The model was internally validated in a 5-fold cross-validation and externally in an independent dataset (CRISP study [CT Perfusion to Predict Response to Recanalization in Ischemic Stroke Project]). We calculated the mean absolute difference between the predictions of the deep learning model and the final infarct volume versus the mean absolute difference between computed tomography perfusion imaging processing by RAPID software (iSchemaView, Menlo Park, CA) and the final infarct volume. Next, we determined infarct growth rates for every patient. Results: We included 127 patients from the MR CLEAN (derivation) and 101 patients of the CRISP study (validation). The deep learning model improved final infarct volume prediction compared with the RAPID software in both the derivation, mean absolute difference 34.5 versus 52.4 mL, and validation cohort, 41.2 versus 52.4 mL ( P <0.01). We obtained individual infarct growth rates enabling the estimation of final infarct volume based on time and grade of reperfusion. Conclusions: We validated a deep learning-based method which improved final infarct volume estimations compared with classic computed tomography perfusion imaging processing. In addition, the deep learning model predicted individual infarct growth rates which could enable the introduction of tissue clocks during the management of acute stroke.

In Vivo Measurement of Wrist Movements during the Dart-Throwing Motion Using Inertial Measurement Units

Background: This study investigates the dart-throwing motion (DTM) by comparing an inertial measurement unit-based system previously validated for basic motion tasks with an optoelectronic motion capture system. The DTM is interesting as wrist movement during many activities of daily living occur in this movement plane, but the complex movement is difficult to assess clinically. Methods: Ten healthy subjects were recorded while performing the DTM with their right wrist using inertial sensors and skin markers. Maximum range of motion obtained by the different systems and the mean absolute difference were calculated. Results: In the flexion–extension plane, both systems calculated a range of motion of 100° with mean absolute differences of 8°, while in the radial–ulnar deviation plane, a mean absolute difference of 17° and range of motion values of 48° for the optoelectronic system and 59° for the inertial measurement units were found. Conclusions: This study shows the challenge of comparing results of different kinematic motion capture systems for complex movements while also highlighting inertial measurement units as promising for future clinical application in dynamic and coupled wrist movements. Possible sources of error and solutions are discussed.

Mask-R$$^{2}$$CNN: a distance-field regression version of Mask-RCNN for fetal-head delineation in ultrasound images

Background and objectives Fetal head-circumference (HC) measurement from ultrasound (US) images provides useful hints for assessing fetal growth. Such measurement is performed manually during the actual clinical practice, posing issues relevant to intra- and inter-clinician variability. This work presents a fully automatic, deep-learning-based approach to HC delineation, which we named Mask-R$$^{2}$$ 2 CNN. It advances our previous work in the field and performs HC distance-field regression in an end-to-end fashion, without requiring a priori HC localization nor any postprocessing for outlier removal. Methods Mask-R$$^{2}$$ 2 CNN follows the Mask-RCNN architecture, with a backbone inspired by feature-pyramid networks, a region-proposal network and the ROI align. The Mask-RCNN segmentation head is here modified to regress the HC distance field. Results Mask-R$$^{2}$$ 2 CNN was tested on the HC18 Challenge dataset, which consists of 999 training and 335 testing images. With a comprehensive ablation study, we showed that Mask-R$$^{2}$$ 2 CNN achieved a mean absolute difference of 1.95 mm (standard deviation $$=\pm 1.92$$ = ± 1.92 mm), outperforming other approaches in the literature. Conclusions With this work, we proposed an end-to-end model for HC distance-field regression. With our experimental results, we showed that Mask-R$$^{2}$$ 2 CNN may be an effective support for clinicians for assessing fetal growth.

Extended-release naltrexone/bupropion is safe and effective among subjects with type 2 diabetes already taking incretin agents: a post-hoc analysis of the LIGHT trial

Background Extended-release naltrexone/bupropion (NB) is indicated for chronic weight management. Incretin agents are recommended for patients with type 2 diabetes. This analysis looked at the add-on of NB to incretins to see if weight loss could occur in patients already stabilized on incretin agents. Methods This was a post-hoc analysis of NB vs. placebo (PL) among subjects with type 2 diabetes stable on an incretin agent prior to randomization in a double-blind, PL-controlled cardiovascular outcome trial (N = 1317). Results Over 1 year, mean weight loss was significantly greater among NB patients vs. PL among those taking DPP-4i (mean absolute difference 4.6% [p < 0.0001]) and those taking GLP-1RAs (mean absolute difference 5.2%, p < 0.0001). Proportions of subjects achieving 5% weight loss were significantly greater for NB vs. PL at weeks 26 and 52 among those taking DPP-4is or GLP-1RAs. There were no significant differences in effectiveness observed between NB + DPP-4i and NB + GLP-1RA or between PL + DPP-4i and PL + GLP-1RA in any of the analyses. Serious adverse events were reported by 9.1% and 11.1% for PL + DPP-4i and PL + GLP-1RA, respectively, and 13.3% and 12.4% of NB + DPP-4i and NB + GLP-1RA, respectively. Conclusion NB appears to be effective in reducing weight in patients with T2DM and obesity/overweight who are taking DPP-4ihibitors or GLP-1RA. The SAE rates in all arms of this analysis were lower than have been reported in other cardiovascular outcome trials in type 2 diabetes.

Seven day pre-analytical stability of serum and plasma neurofilament light chain

Neurofilament light chain (NfL) has emerged as a biomarker of neuroaxonal damage in several neurologic conditions. With increasing availability of fourth-generation immunoassays detecting NfL in blood, aspects of pre-analytical stability of this biomarker remain unanswered. This study investigated NfL concentrations in serum and plasma samples of 32 patients with neurological diagnoses using state of the art Simoa technology. We tested the effect of delayed freezing of up to 7 days and statistically determined stability and validity of measured concentrations. We found concentrations of NfL in serum and plasma to remain stable at room temperature when processing of samples is delayed up to 7 days (serum: mean absolute difference 0.9 pg/mL, intraindividual variation 1.2%; plasma: mean absolute difference 0.5 pg/mL, intraindividual variation 1.3%). Consistency of these results was nearly perfect for serum and excellent for plasma (intraclass correlation coefficients 0.99 and 0.94, respectively). In conclusion, the soluble serum and plasma NfL concentration remains stable when unprocessed blood samples are stored up to 7 days at room temperature. This information is essential for ensuring reliable study protocols, for example, when shipment of fresh samples is needed.

Accuracy of Preoperative Breast MRI versus Conventional Imaging in Measuring Pathologic Extent of Invasive Lobular Carcinoma

Objective To determine whether invasive lobular carcinoma (ILC) extent is more accurately depicted with preoperative MRI (pMRI) than conventional imaging (mammography and/or ultrasound). Methods After IRB approval, we retrospectively identified women with pMRIs (February 2005 to January 2014) to evaluate pure ILC excluding those with ipsilateral pMRI BI-RADS 4 or 5 findings or who had neoadjuvant chemotherapy. Agreement between imaging and pathology sizes was summarized using Bland-Altman plots, absolute and percent differences, and the intraclass correlation coefficient (ICC). Rates of underestimation and overestimation were evaluated and their associations with clinical features were explored. Results Among the 56 women included, pMRI demonstrated better agreement with pathology than conventional imaging by mean absolute difference (1.6 mm versus −7.8 mm, P &lt; 0.001), percent difference (10.3% versus −16.4%, P &lt; 0.001), and ICC (0.88 versus 0.61, P = 0.019). Conventional imaging more frequently underestimated ILC span than pMRI using a 5 mm difference threshold (24/56 (43%) versus 10/56 (18%), P &lt; 0.001), a 25% threshold (19/53 (36%) versus 10/53 (19%), P = 0.035), and T category change (17/56 (30%) versus 7/56 (13%), P = 0.006). Imaging–pathology size concordance was greater for MRI-described solitary masses than other lesion types for both MRI and conventional imaging (P &lt; 0.05). Variability of conventional imaging was lower for patients ≥ to the median age of 62 years than for patients younger than the median age (SD: 12 mm versus 22 mm, P = 0.012). Conclusion MRI depicts the size of pure ILC more accurately than conventional imaging and may have particular value for younger women.

A Combined Lidar-Polarimeter Inversion Approach for Aerosol Remote Sensing Over Ocean

An optimization algorithm is developed to retrieve the vertical profiles of aerosol concentration, refractive index and size distribution, spherical particle fraction, as well as a set of ocean surface reflection properties. The retrieval uses a combined set of lidar and polarimeter measurements. Our inversion includes using 1) a hybrid radiative transfer (RT) model that combines the computational strengths of the Markov-chain and adding-doubling approaches in modeling polarized RT in vertically inhomogeneous and homogeneous media, respectively; 2) a bio-optical model that represents the water-leaving radiance as a function of chlorophyll-a concentration for open ocean; 3) the constraints regarding the smooth variations of several aerosol properties along altitude; and 4) an optimization scheme. We tested the retrieval using 50 sets of coincident lidar and polarimetric data acquired by NASA Langley airborne HSRL-2 and GISS RSP respectively during the ORACLES field campaign. The retrieved vertical profiles of aerosol single scattering albedo (SSA) and size distribution are compared to the reference data measured by University of Hawaii’s HiGEAR instrumentation suite. At the vertical resolution of 315 m, the mean absolute difference (MAD) between retrieved and HiGEAR derived aerosol SSA is 0.028. And the MADs between retrieved and HiGEAR effective radius of aerosol size distribution are 0.012 and 0.377 micron for fine and coarse aerosols, respectively. The retrieved aerosol optical depth (AOD) above aircraft are compared to NASA Ames 4-STAR measurement. The MADs are found to be 0.010, 0.006, and 0.004 for AOD at 355, 532 and 1,064 nm, respectively.

A Tool for Translating Polygenic Scores onto the Absolute Scale Using Summary Statistics

Background: There is growing interest in the clinical application of polygenic scores as their predictive utility increases for a range of health-related phenotypes. However, providing polygenic score predictions on the absolute scale is an important step for their safe interpretation. Currently, polygenic scores can only be converted to the absolute scale when a validation sample is available, presenting a major limitation in the interpretability and clinical utility of polygenic scores. Methods: We have developed a method to convert polygenic scores to the absolute scale for binary and normally distributed phenotypes. This method uses summary statistics, requiring only the area-under-the-ROC curve (AUC) or variance explained (R2) by the polygenic score, and the prevalence of binary phenotypes, or mean and standard deviation of normally distributed phenotypes. Polygenic scores are converted using normal distribution theory. Given the AUC/R2 of polygenic scores may be unknown, we also evaluate two methods (AVENGEME, lassosum) for estimating these values from genome-wide association study (GWAS) summary statistics alone. We validate the absolute risk conversion and AUC/R2 estimation using data for eight binary and three continuous phenotypes in the UK Biobank sample. Results: When the AUC/R2 of the polygenic score is known, the observed and estimated absolute values were highly concordant. Across binary phenotypes, the mean absolute difference between the observed and estimated proportion of cases was 5%. For continuous phenotypes, the mean absolute difference between observed and estimated means was <0.3%. Estimates of AUC/R2 from the lassosum pseudovalidation method were most similar to the observed AUC/R2 values, though estimated values deviated substantially from the observed for autoimmune disorders. Conclusion: This study enables accurate interpretation of polygenic scores using only summary statistics, providing a useful tool for educational and clinical purposes. Furthermore, we have created interactive webtools implementing the conversion to the absolute scale for binary and normally distributed phenotypes (https://opain.github.io/GenoPred/PRS_to_Abs_tool.html). Several further barriers must be addressed before clinical implementation of polygenic scores, such as ensuring target individuals are well represented by the GWAS sample.

Performance of an artificial intelligence system for bone age assessment in Tibet

Objective: To investigate whether bone age (BA) of children living in Tibet Highland could be accurately assessed using a fully automated artificial intelligence (AI) system. Methods： Left hand radiographs of 385 children (300 Tibetan and 85 immigrant Han) aged 4–18 years who presented to the largest medical center of Tibet between September 2013 and November 2019 were consecutively collected. From these radiographs, BA was determined using the Greulich and Pyle (GP) method by experts in a consensus manner; furthermore, BA was estimated by a previously reported artificial intelligence (AI) BA system based on Han children from southern China. The performance of the AI system was compared with that of experts by using statistical analysis. Results: Compared with the experts’ results, the accuracy of the AI system for Tibetan and Han children within 1 year was 84.67 and 89.41%, respectively, and its mean absolute difference (MAD) was 0.65 and 0.56 years, respectively. The discrepancy in hand-wrist bone maturation was the main cause of low accuracy of the system in the 4- to 6-year-old group. Conclusion: The AI BA system developed for Han Chinese children living in flat regions could enable to assess BA accurately in Tibet where medical resources are limited. Advances in knowledge: AI-based BA system may serve as an effective and efficient solution to assess BA in Tibet.

DNA methylation architecture of the ACE2 gene in nasal cells of children

Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) has led to the global coronavirus disease 2019 (COVID-19) pandemic. SARS-CoV-2 enters cells via angiotensin-Converting Enzyme 2 (ACE2) receptors, highly expressed in nasal epithelium with parallel high infectivity.1,2 The nasal epigenome is in direct contact with the environment and could explain COVID-19 disparities by reflecting social and environmental influences on ACE2 regulation. We collected nasal swabs from anterior nares of 547 children, measured DNA methylation (DNAm), and tested differences at 15 ACE2 CpGs by sex, age, race/ethnicity and epigenetic age. ACE2 CpGs were differentially methylated by sex with 12 sites having lower DNAm (mean = 12.71%) and 3 sites greater DNAm (mean = 1.45%) among females relative to males. We observed differential DNAm at 5 CpGs for Hispanic females (mean absolute difference = 3.22%) and lower DNAm at 8 CpGs for Black males (mean absolute difference = 1.33%), relative to white participants. Longer DNAm telomere length was associated with greater ACE2 DNAm at 11 and 13 CpGs among males (mean absolute difference = 7.86%) and females (mean absolute difference = 8.21%), respectively. Nasal ACE2 DNAm differences could contribute to our understanding COVID-19 severity and disparities reflecting upstream environmental and social influences. Findings need to be confirmed among adults and patients with risk factors for COVID-19 severity.