We present a study of multiple sclerosis segmentation algorithms conducted at the international MICCAI 2016 challenge. This challenge was operated using a new open-science computing infrastructure. This allowed for the automatic and independent evaluation of a large range of algorithms in a fair and completely automatic manner. This computing infrastructure was used to evaluate thirteen methods of MS lesions segmentation, exploring a broad range of state-of-theart algorithms, against a high-quality database of 53 MS cases coming from four centers following a common definition of the acquisition protocol. Each case was annotated manually by an unprecedented number of seven different experts. Results of the challenge highlighted that automatic algorithms, including the recent machine learning methods (random forests, deep learning, …), are still trailing human expertise on both detection and delineation criteria. In addition, we demonstrate that computing a statistically robust consensus of the algorithms performs closer to human expertise on one score (segmentation) although still trailing on detection scores.

This retrospective analysis from 5 Maryland and Washington, DC area hospitals determines factors on hospital admission predictive of severe disease or death from COVID-19 and describes patient traj... Visual Trajectories Among Patients Hospitalized for COVID-19 This retrospective analysis from 5 Maryland and Washington, DC, area hospitals determines factors on hospital admission predict... Background: Risk factors for progression of coronavirus 2019 (COVID-19) to severe disease or death are underexplored in U.S. cohorts. Objective: To determine the factors on hospital admission that ...

Successful automated diagnoses of attention deficit hyperactive disorder (ADHD) using imaging and functional biomarkers would have fundamental consequences on the public health impact of the disease. In this work, we show results on the predictability of ADHD using imaging biomarkers and discuss the scientific and diagnostic impacts of the research. We created a prediction model using the landmark ADHD 200 data set focusing on resting state functional connectivity (rs-fc) and structural brain imaging. We predicted ADHD status and subtype, obtained by behavioral examination, using imaging data, intelligence quotients and other covariates. The novel contributions of this manuscript include a thorough exploration of prediction and image feature extraction methodology on this form of data, including the use of singular value decompositions (SVDs), CUR decompositions, random forest, gradient boosting, bagging, voxel-based morphometry, and support vector machines as well as important insights into the value, and potentially lack thereof, of imaging biomarkers of disease. The key results include the CUR-based decomposition of the rs-fc-fMRI along with gradient boosting and the prediction algorithm based on a motor network parcellation and random forest algorithm. We conjecture that the CUR decomposition is largely diagnosing common population directions of head motion. Of note, a byproduct of this research is a potential automated method for detecting subtle in-scanner motion. The final prediction algorithm, a weighted combination of several algorithms, had an external test set specificity of 94% with sensitivity of 21%. The most promising imaging biomarker was a correlation graph from a motor network parcellation. In summary, we have undertaken a large-scale statistical exploratory prediction exercise on the unique ADHD 200 data set. The exercise produced several potential leads for future scientific exploration of the neurological basis of ADHD.

Intracerebral hemorrhage (ICH), where a blood vessel ruptures into areas of the brain, accounts for approximately 10-15% of all strokes. X-ray computed tomography (CT) scanning is largely used to assess the location and volume of these hemorrhages. Manual segmentation of the CT scan using planimetry by an expert reader is the gold standard for volume estimation, but is time-consuming and has within- and across-reader variability. We propose a fully automated segmentation approach using a random forest algorithm with features extracted from X-ray computed tomography (CT) scans. The Minimally Invasive Surgery plus rt-PA in ICH Evacuation (MISTIE) trial was a multi-site Phase II clinical trial that tested the safety of hemorrhage removal using recombinant-tissue plasminogen activator (rt-PA). For this analysis, we use 112 baseline CT scans from patients enrolled in the MISTE trial, one CT scan per patient. ICH was manually segmented on these CT scans by expert readers. We derived a set of imaging predictors from each scan. Using 10 randomly-selected scans, we used a first-pass voxel selection procedure based on quantiles of a set of predictors and then built 4 models estimating the voxel-level probability of ICH. The models used were: 1) logistic regression, 2) logistic regression with a penalty on the model parameters using LASSO, 3) a generalized additive model (GAM) and 4) a random forest classifier. The remaining 102 scans were used for model validation.For each validation scan, the model predicted the probability of ICH at each voxel. These voxel-level probabilities were then thresholded to produce binary segmentations of the hemorrhage. These masks were compared to the manual segmentations using the Dice Similarity Index (DSI) and the correlation of hemorrhage volume of between the two segmentations. We tested equality of median DSI using the Kruskal-Wallis test across the 4 models. We tested equality of the median DSI from sets of 2 models using a Wilcoxon signed-rank test. All results presented are for the 102 scans in the validation set. The median DSI for each model was: 0.89 (logistic), 0.885 (LASSO), 0.88 (GAM), and 0.899 (random forest). Using the random forest results in a slightly higher median DSI compared to the other models. After Bonferroni correction, the hypothesis of equality of median DSI was rejected only when comparing the random forest DSI to the DSI from the logistic (p < 0.001), LASSO (p < 0.001), or GAM (p < 0.001) models. In practical terms the difference between the random forest and the logistic regression is quite small. The correlation (95% CI) between the volume from manual segmentation and the predicted volume was 0.93 (0.9,0.95) for the random forest model. These results indicate that random forest approach can achieve accurate segmentation of ICH in a population of patients from a variety of imaging centers. We provide an R package (https://github.com/muschellij2/ichseg) and a Shiny R application online (http://johnmuschelli.com/ich_segment_all.html) for implementing and testing the proposed approach.