Machine learning automatically detects COVID-19 using chest CTs in a large multicenter cohort.

OBJECTIVES: To investigate machine learning classifiers and interpretable models using chest CT for detection of COVID-19 and differentiation from other pneumonias, interstitial lung disease (ILD) and normal CTs. METHODS: Our retrospective multi-institutional study obtained 2446 chest CTs from 16 institutions (including 1161 COVID-19 patients). Training/validation/testing cohorts included 1011/50/100 COVID-19, 388/16/33 ILD, 189/16/33 other pneumonias, and 559/17/34 normal (no pathologies) CTs. A metric-based approach for the classification of COVID-19 used interpretable features, relying on logistic regression and random forests. A deep learning-based classifier differentiated COVID-19 via 3D features extracted directly from CT attenuation and probability distribution of airspace opacities. RESULTS: Most discriminative features of COVID-19 are the percentage of airspace opacity and peripheral and basal predominant opacities, concordant with the typical characterization of COVID-19 in the literature. Unsupervised hierarchical clustering compares feature distribution across COVID-19 and control cohorts. The metrics-based classifier achieved AUC = 0.83, sensitivity = 0.74, and specificity = 0.79 versus respectively 0.93, 0.90, and 0.83 for the DL-based classifier. Most of ambiguity comes from non-COVID-19 pneumonia with manifestations that overlap with COVID-19, as well as mild COVID-19 cases. Non-COVID-19 classification performance is 91% for ILD, 64% for other pneumonias, and 94% for no pathologies, which demonstrates the robustness of our method against different compositions of control groups. CONCLUSIONS: Our new method accurately discriminates COVID-19 from other types of pneumonia, ILD, and CTs with no pathologies, using quantitative imaging features derived from chest CT, while balancing interpretability of results and classification performance and, therefore, may be useful to facilitate diagnosis of COVID-19. KEY POINTS: • Unsupervised clustering reveals the key tomographic features including percent airspace opacity and peripheral and basal opacities most typical of COVID-19 relative to control groups. • COVID-19-positive CTs were compared with COVID-19-negative chest CTs (including a balanced distribution of non-COVID-19 pneumonia, ILD, and no pathologies). Classification accuracies for COVID-19, pneumonia, ILD, and CT scans with no pathologies are respectively 90%, 64%, 91%, and 94%. • Our deep learning (DL)-based classification method demonstrates an AUC of 0.93 (sensitivity 90%, specificity 83%). Machine learning methods applied to quantitative chest CT metrics can therefore improve diagnostic accuracy in suspected COVID-19, particularly in resource-constrained environments.

Rapid myelin water imaging in human cervical spinal cord.

PURPOSE: Myelin water imaging (MWI) using multi-echo T2 relaxation is a quantitative MRI technique that can be used as an in vivo biomarker for myelin in the central nervous system. MWI using a multi-echo spin echo sequence currently takes more than 20 min to acquire eight axial slices (5 mm thickness) in the cervical spinal cord, making spinal cord MWI impractical for implementation in clinical studies. METHODS: In this study, an accelerated gradient and spin echo sequence (GRASE), previously validated for brain MWI, was adapted for spinal cord MWI. Ten healthy volunteers were scanned with the GRASE sequence (acquisition time 8.5 min) and compared with the multi-echo spin echo sequence (acquisition time 23.5 min). RESULTS: Using region of interest analysis, myelin estimates obtained from the two sequences were found to be in good agreement (mean difference = -0.0092, 95% confidence interval = - 0.0092 ± 0.061; regression slope = 1.01, ρ = 0.9). MWI using GRASE was shown to be highly reproducible with an average coefficient of variation of 6.1%. CONCLUSION: The results from this study show that MWI can be performed in the cervical spinal cord in less than 10 min, allowing for practical implementation in multimodal clinical studies. Magn Reson Med 78:1482-1487, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

Fast computation of myelin maps from MRI T2 relaxation data using multicore CPU and graphics card parallelization.

PURPOSE: To develop a fast algorithm for computing myelin maps from multiecho T2 relaxation data using parallel computation with multicore CPUs and graphics processing units (GPUs). MATERIALS AND METHODS: Using an existing MATLAB (MathWorks, Natick, MA) implementation with basic (nonalgorithm-specific) parallelism as a guide, we developed a new version to perform the same computations but using C++ to optimize the hybrid utilization of multicore CPUs and GPUs, based on experimentation to determine which algorithmic components would benefit from CPU versus GPU parallelization. Using 32-echo T2 data of dimensions 256 × 256 × 7 from 17 multiple sclerosis patients and 18 healthy subjects, we compared the two methods in terms of speed, myelin values, and the ability to distinguish between the two patient groups using Student's t-tests. RESULTS: The new method was faster than the MATLAB implementation by 4.13 times for computing a single map and 14.36 times for batch-processing 10 scans. The two methods produced very similar myelin values, with small and explainable differences that did not impact the ability to distinguish the two patient groups. CONCLUSION: The proposed hybrid multicore approach represents a more efficient alternative to MATLAB, especially for large-scale batch processing.

Contrastive self-supervised learning from 100 million medical images with optional supervision.

Purpose: Building accurate and robust artificial intelligence systems for medical image assessment requires the creation of large sets of annotated training examples. However, constructing such datasets is very costly due to the complex nature of annotation tasks, which often require expert knowledge (e.g., a radiologist). To counter this limitation, we propose a method to learn from medical images at scale in a self-supervised way. Approach: Our approach, based on contrastive learning and online feature clustering, leverages training datasets of over 100,000,000 medical images of various modalities, including radiography, computed tomography (CT), magnetic resonance (MR) imaging, and ultrasonography (US). We propose to use the learned features to guide model training in supervised and hybrid self-supervised/supervised regime on various downstream tasks. Results: We highlight a number of advantages of this strategy on challenging image assessment problems in radiography, CT, and MR: (1) significant increase in accuracy compared to the state-of-the-art (e.g., area under the curve boost of 3% to 7% for detection of abnormalities from chest radiography scans and hemorrhage detection on brain CT); (2) acceleration of model convergence during training by up to 85% compared with using no pretraining (e.g., 83% when training a model for detection of brain metastases in MR scans); and (3) increase in robustness to various image augmentations, such as intensity variations, rotations or scaling reflective of data variation seen in the field. Conclusions: The proposed approach enables large gains in accuracy and robustness on challenging image assessment problems. The improvement is significant compared with other state-of-the-art approaches trained on medical or vision images (e.g., ImageNet).

Artificial Intelligence with Statistical Confidence Scores for Detection of Acute or Subacute Hemorrhage on Noncontrast CT Head Scans.

Purpose: To present a method that automatically detects, subtypes, and locates acute or subacute intracranial hemorrhage (ICH) on noncontrast CT (NCCT) head scans; generates detection confidence scores to identify high-confidence data subsets with higher accuracy; and improves radiology worklist prioritization. Such scores may enable clinicians to better use artificial intelligence (AI) tools. Materials and Methods: This retrospective study included 46 057 studies from seven "internal" centers for development (training, architecture selection, hyperparameter tuning, and operating-point calibration; n = 25 946) and evaluation (n = 2947) and three "external" centers for calibration (n = 400) and evaluation (n = 16 764). Internal centers contributed developmental data, whereas external centers did not. Deep neural networks predicted the presence of ICH and subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and/or epidural hemorrhage) and segmentations per case. Two ICH confidence scores are discussed: a calibrated classifier entropy score and a Dempster-Shafer score. Evaluation was completed by using receiver operating characteristic curve analysis and report turnaround time (RTAT) modeling on the evaluation set and on confidence score-defined subsets using bootstrapping. Results: The areas under the receiver operating characteristic curve for ICH were 0.97 (0.97, 0.98) and 0.95 (0.94, 0.95) on internal and external center data, respectively. On 80% of the data stratified by calibrated classifier and Dempster-Shafer scores, the system improved the Youden indexes, increasing them from 0.84 to 0.93 (calibrated classifier) and from 0.84 to 0.92 (Dempster-Shafer) for internal centers and increasing them from 0.78 to 0.88 (calibrated classifier) and from 0.78 to 0.89 (Dempster-Shafer) for external centers (P < .001). Models estimated shorter RTAT for AI-prioritized worklists with confidence measures than for AI-prioritized worklists without confidence measures, shortening RTAT by 27% (calibrated classifier) and 27% (Dempster-Shafer) for internal centers and shortening RTAT by 25% (calibrated classifier) and 27% (Dempster-Shafer) for external centers (P < .001). Conclusion: AI that provided statistical confidence measures for ICH detection on NCCT scans reliably detected and subtyped hemorrhages, identified high-confidence predictions, and improved worklist prioritization in simulation.Keywords: CT, Head/Neck, Hemorrhage, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2022.

Evaluating deep learning methods in detecting and segmenting different sizes of brain metastases on 3D post-contrast T1-weighted images.

Purpose: We investigate the impact of various deep-learning-based methods for detecting and segmenting metastases with different lesion volume sizes on 3D brain MR images. Approach: A 2.5D U-Net and a 3D U-Net were selected. We also evaluated weak learner fusion of the prediction features generated by the 2.5D and the 3D networks. A 3D fully convolutional one-stage (FCOS) detector was selected as a representative of bounding-box regression-based detection methods. A total of 422 3D post-contrast T1-weighted scans from patients with brain metastases were used. Performances were analyzed based on lesion volume, total metastatic volume per patient, and number of lesions per patient. Results: The performance of detection of the 2.5D and 3D U-Net methods had recall of > 0.83 and precision of > 0.44 for lesion volume > 0.3 cm 3 but deteriorated as metastasis size decreased below 0.3 cm 3 to 0.58 to 0.74 in recall and 0.16 to 0.25 in precision. Compared the two U-Nets for detection capability, high precision was achieved by the 2.5D network, but high recall was achieved by the 3D network for all lesion sizes. The weak learner fusion achieved a balanced performance between the 2.5D and 3D U-Nets; particularly, it increased precision to 0.83 for lesion volumes of 0.1 to 0.3 cm 3 but decreased recall to 0.59. The 3D FCOS detector did not outperform the U-Net methods in detecting either the small or large metastases presumably because of the limited data size. Conclusions: Our study provides the performances of four deep learning methods in relationship to lesion size, total metastasis volume, and number of lesions per patient, providing insight into further development of the deep learning networks.

Quantifying and leveraging predictive uncertainty for medical image assessment.

The interpretation of medical images is a challenging task, often complicated by the presence of artifacts, occlusions, limited contrast and more. Most notable is the case of chest radiography, where there is a high inter-rater variability in the detection and classification of abnormalities. This is largely due to inconclusive evidence in the data or subjective definitions of disease appearance. An additional example is the classification of anatomical views based on 2D Ultrasound images. Often, the anatomical context captured in a frame is not sufficient to recognize the underlying anatomy. Current machine learning solutions for these problems are typically limited to providing probabilistic predictions, relying on the capacity of underlying models to adapt to limited information and the high degree of label noise. In practice, however, this leads to overconfident systems with poor generalization on unseen data. To account for this, we propose a system that learns not only the probabilistic estimate for classification, but also an explicit uncertainty measure which captures the confidence of the system in the predicted output. We argue that this approach is essential to account for the inherent ambiguity characteristic of medical images from different radiologic exams including computed radiography, ultrasonography and magnetic resonance imaging. In our experiments we demonstrate that sample rejection based on the predicted uncertainty can significantly improve the ROC-AUC for various tasks, e.g., by 8% to 0.91 with an expected rejection rate of under 25% for the classification of different abnormalities in chest radiographs. In addition, we show that using uncertainty-driven bootstrapping to filter the training data, one can achieve a significant increase in robustness and accuracy. Finally, we present a multi-reader study showing that the predictive uncertainty is indicative of reader errors.

Exploring the Contribution of Myelin Content in Normal Appearing White Matter to Cognitive Outcomes in Cerebral Small Vessel Disease.

BACKGROUND: Myelin damage is a salient feature in cerebral small vessel disease (cSVD). Of note, myelin damage extends into the normal appearing white matter (NAWM). Currently, the specific role of myelin content in cognition is poorly understood. OBJECTIVE: The objective of this exploratory study was to investigate the association between NAWM myelin and cognitive function in older adults with cSVD. METHODS: This exploratory study included 55 participants with cSVD. NAWM myelin was measured using myelin water imaging and was quantified as myelin water fraction (MWF). Assessment of cognitive function included processing speed (Trail Making Test Part A), set shifting (Trail Making Test Part B minus A), working memory (Verbal Digit Span Backwards Test), and inhibition (Stroop Test). Multiple linear regression analyses assessed the contribution of NAWM MWF on cognitive outcomes controlling for age, education, and total white matter hyperintensity volume. The overall alpha was set at ≤0.05. RESULTS: After accounting for age, education, and total white matter hyperintensity volume, lower NAWM MWF was significantly associated with slower processing speed (ß â€Š= -0.29, p = 0.037) and poorer working memory (ß= 0.30, p = 0.048). NAWM MWF was not significantly associated with set shifting or inhibitory control (p > 0.132). CONCLUSION: Myelin loss in NAWM may play a role in the evolution of impaired processing speed and working memory in people with cSVD. Future studies, with a longitudinal design and larger sample sizes, are needed to fully elucidate the role of myelin as a potential biomarker for cognitive function.

GAMER MRI: Gated-attention mechanism ranking of multi-contrast MRI in brain pathology.

INTRODUCTION: During the last decade, a multitude of novel quantitative and semiquantitative MRI techniques have provided new information about the pathophysiology of neurological diseases. Yet, selection of the most relevant contrasts for a given pathology remains challenging. In this work, we developed and validated a method, Gated-Attention MEchanism Ranking of multi-contrast MRI in brain pathology (GAMER MRI), to rank the relative importance of MR measures in the classification of well understood ischemic stroke lesions. Subsequently, we applied this method to the classification of multiple sclerosis (MS) lesions, where the relative importance of MR measures is less understood. METHODS: GAMER MRI was developed based on the gated attention mechanism, which computes attention weights (AWs) as proxies of importance of hidden features in the classification. In the first two experiments, we used Trace-weighted (Trace), apparent diffusion coefficient (ADC), Fluid-Attenuated Inversion Recovery (FLAIR), and T1-weighted (T1w) images acquired in 904 acute/subacute ischemic stroke patients and in 6,230 healthy controls and patients with other brain pathologies to assess if GAMER MRI could produce clinically meaningful importance orders in two different classification scenarios. In the first experiment, GAMER MRI with a pretrained convolutional neural network (CNN) was used in conjunction with Trace, ADC, and FLAIR to distinguish patients with ischemic stroke from those with other pathologies and healthy controls. In the second experiment, GAMER MRI with a patch-based CNN used Trace, ADC and T1w to differentiate acute ischemic stroke lesions from healthy tissue. The last experiment explored the performance of patch-based CNN with GAMER MRI in ranking the importance of quantitative MRI measures to distinguish two groups of lesions with different pathological characteristics and unknown quantitative MR features. Specifically, GAMER MRI was applied to assess the relative importance of the myelin water fraction (MWF), quantitative susceptibility mapping (QSM), T1 relaxometry map (qT1), and neurite density index (NDI) in distinguishing 750 juxtacortical lesions from 242 periventricular lesions in 47 MS patients. Pair-wise permutation t-tests were used to evaluate the differences between the AWs obtained for each quantitative measure. RESULTS: In the first experiment, we achieved a mean test AUC of 0.881 and the obtained AWs of FLAIR and the sum of AWs of Trace and ADC were 0.11 and 0.89, respectively, as expected based on previous knowledge. In the second experiment, we achieved a mean test F1 score of 0.895 and a mean AW of Trace = 0.49, of ADC = 0.28, and of T1w = 0.23, thereby confirming the findings of the first experiment. In the third experiment, MS lesion classification achieved test balanced accuracy = 0.777, sensitivity = 0.739, and specificity = 0.814. The mean AWs of T1map, MWF, NDI, and QSM were 0.29, 0.26, 0.24, and 0.22 (p < 0.001), respectively. CONCLUSIONS: This work demonstrates that the proposed GAMER MRI might be a useful method to assess the relative importance of MRI measures in neurological diseases with focal pathology. Moreover, the obtained AWs may in fact help to choose the best combination of MR contrasts for a specific classification problem.

Automated detection of critical findings in multi-parametric brain MRI using a system of 3D neural networks.

With the rapid growth and increasing use of brain MRI, there is an interest in automated image classification to aid human interpretation and improve workflow. We aimed to train a deep convolutional neural network and assess its performance in identifying abnormal brain MRIs and critical intracranial findings including acute infarction, acute hemorrhage and mass effect. A total of 13,215 clinical brain MRI studies were categorized to training (74%), validation (9%), internal testing (8%) and external testing (8%) datasets. Up to eight contrasts were included from each brain MRI and each image volume was reformatted to common resolution to accommodate for differences between scanners. Following reviewing the radiology reports, three neuroradiologists assigned each study to abnormal vs normal, and identified three critical findings including acute infarction, acute hemorrhage, and mass effect. A deep convolutional neural network was constructed by a combination of localization feature extraction (LFE) modules and global classifiers to identify the presence of 4 variables in brain MRIs including abnormal, acute infarction, acute hemorrhage and mass effect. Training, validation and testing sets were randomly defined on a patient basis. Training was performed on 9845 studies using balanced sampling to address class imbalance. Receiver operating characteristic (ROC) analysis was performed. The ROC analysis of our models for 1050 studies within our internal test data showed AUC/sensitivity/specificity of 0.91/83%/86% for normal versus abnormal brain MRI, 0.95/92%/88% for acute infarction, 0.90/89%/81% for acute hemorrhage, and 0.93/93%/85% for mass effect. For 1072 studies within our external test data, it showed AUC/sensitivity/specificity of 0.88/80%/80% for normal versus abnormal brain MRI, 0.97/90%/97% for acute infarction, 0.83/72%/88% for acute hemorrhage, and 0.87/79%/81% for mass effect. Our proposed deep convolutional network can accurately identify abnormal and critical intracranial findings on individual brain MRIs, while addressing the fact that some MR contrasts might not be available in individual studies.

Automated Quantification of CT Patterns Associated with COVID-19 from Chest CT.

PURPOSE: To present a method that automatically segments and quantifies abnormal CT patterns commonly present in coronavirus disease 2019 (COVID-19), namely ground glass opacities and consolidations. MATERIALS AND METHODS: In this retrospective study, the proposed method takes as input a non-contrasted chest CT and segments the lesions, lungs, and lobes in three dimensions, based on a dataset of 9749 chest CT volumes. The method outputs two combined measures of the severity of lung and lobe involvement, quantifying both the extent of COVID-19 abnormalities and presence of high opacities, based on deep learning and deep reinforcement learning. The first measure of (PO, PHO) is global, while the second of (LSS, LHOS) is lobewise. Evaluation of the algorithm is reported on CTs of 200 participants (100 COVID-19 confirmed patients and 100 healthy controls) from institutions from Canada, Europe and the United States collected between 2002-Present (April, 2020). Ground truth is established by manual annotations of lesions, lungs, and lobes. Correlation and regression analyses were performed to compare the prediction to the ground truth. RESULTS: Pearson correlation coefficient between method prediction and ground truth for COVID-19 cases was calculated as 0.92 for PO (P < .001), 0.97 for PHO(P < .001), 0.91 for LSS (P < .001), 0.90 for LHOS (P < .001). 98 of 100 healthy controls had a predicted PO of less than 1%, 2 had between 1-2%. Automated processing time to compute the severity scores was 10 seconds per case compared to 30 minutes required for manual annotations. CONCLUSION: A new method segments regions of CT abnormalities associated with COVID-19 and computes (PO, PHO), as well as (LSS, LHOS) severity scores.

Automated Quantification of CT Patterns Associated with COVID-19 from Chest CT.

PURPOSE: To present a method that automatically segments and quantifies abnormal CT patterns commonly present in coronavirus disease 2019 (COVID-19), namely ground glass opacities and consolidations. MATERIALS AND METHODS: In this retrospective study, the proposed method takes as input a non-contrasted chest CT and segments the lesions, lungs, and lobes in three dimensions, based on a dataset of 9749 chest CT volumes. The method outputs two combined measures of the severity of lung and lobe involvement, quantifying both the extent of COVID-19 abnormalities and presence of high opacities, based on deep learning and deep reinforcement learning. The first measure of (PO, PHO) is global, while the second of (LSS, LHOS) is lobe-wise. Evaluation of the algorithm is reported on CTs of 200 participants (100 COVID-19 confirmed patients and 100 healthy controls) from institutions from Canada, Europe and the United States collected between 2002-Present (April 2020). Ground truth is established by manual annotations of lesions, lungs, and lobes. Correlation and regression analyses were performed to compare the prediction to the ground truth. RESULTS: Pearson correlation coefficient between method prediction and ground truth for COVID-19 cases was calculated as 0.92 for PO (P < .001), 0.97 for PHO (P < .001), 0.91 for LSS (P < .001), 0.90 for LHOS (P < .001). 98 of 100 healthy controls had a predicted PO of less than 1%, 2 had between 1-2%. Automated processing time to compute the severity scores was 10 seconds per case compared to 30 minutes required for manual annotations. CONCLUSION: A new method segments regions of CT abnormalities associated with COVID-19 and computes (PO, PHO), as well as (LSS, LHOS) severity scores.

Brain Myelin Water Fraction and Diffusion Tensor Imaging Atlases for 9-10 Year-Old Children.

BACKGROUND AND PURPOSE: Myelin water imaging (MWI) and diffusion tensor imaging (DTI) provide information about myelin and axon-related brain microstructure, which can be useful for investigating normal brain development and many childhood brain disorders. While pediatric DTI atlases exist, there are no pediatric MWI atlases available for the 9-10 years old age group. As myelination and structural development occurs throughout childhood and adolescence, studies of pediatric brain pathologies must use age-specific MWI and DTI healthy control data. We created atlases of myelin water fraction (MWF) and DTI metrics for healthy children aged 9-10 years for use as normative data in pediatric neuroimaging studies. METHODS: 3D-T1 , DTI, and MWI scans were acquired from 20 healthy children (mean age: 9.6 years, range: 9.2-10.3 years, 4 females). ANTs and FSL registration were used to create quantitative MWF and DTI atlases. Region of interest (ROI) analysis in nine white matter regions was used to compare pediatric MWF with adult MWF values from a recent study and to investigate the correlation between pediatric MWF and DTI metrics. RESULTS: Adults had significantly higher MWF than the pediatric cohort in seven of the nine white matter ROIs, but not in the genu of the corpus callosum or the cingulum. In the pediatric data, MWF correlated significantly with mean diffusivity, but not with axial diffusivity, radial diffusivity, or fractional anisotropy. CONCLUSIONS: Normative MWF and DTI metrics from a group of 9-10 year old healthy children provide a resource for comparison to pathologies. The age-specific atlases are ready for use in pediatric neuroimaging research and can be accessed: https://sourceforge.net/projects/pediatric-mri-myelin-diffusion/.

Imaging outcome measures of neuroprotection and repair in MS: A consensus statement from NAIMS.

OBJECTIVE: To summarize current and emerging imaging techniques that can be used to assess neuroprotection and repair in multiple sclerosis (MS), and to provide a consensus opinion on the potential utility of each technique in clinical trial settings. METHODS: Clinicians and scientists with expertise in the use of MRI in MS convened in Toronto, Canada, in November 2016 at a North American Imaging in Multiple Sclerosis (NAIMS) Cooperative workshop meeting. The discussion was compiled into a manuscript and circulated to all NAIMS members in attendance. Edits and feedback were incorporated until all authors were in agreement. RESULTS: A wide spectrum of imaging techniques and analysis methods in the context of specific study designs were discussed, with a focus on the utility and limitations of applying each technique to assess neuroprotection and repair. Techniques were discussed under specific themes, and included conventional imaging, magnetization transfer ratio, diffusion tensor imaging, susceptibility-weighted imaging, imaging cortical lesions, magnetic resonance spectroscopy, PET, advanced diffusion imaging, sodium imaging, multimodal techniques, imaging of special regions, statistical considerations, and study design. CONCLUSIONS: Imaging biomarkers of neuroprotection and repair are an unmet need in MS. There are a number of promising techniques with different strengths and limitations, and selection of a specific technique will depend on a number of factors, notably the question the trial seeks to answer. Ongoing collaborative efforts will enable further refinement and improved methods to image the effect of novel therapeutic agents that exert benefit in MS predominately through neuroprotective and reparative mechanisms.

Deep learning of joint myelin and T1w MRI features in normal-appearing brain tissue to distinguish between multiple sclerosis patients and healthy controls.

Myelin imaging is a form of quantitative magnetic resonance imaging (MRI) that measures myelin content and can potentially allow demyelinating diseases such as multiple sclerosis (MS) to be detected earlier. Although focal lesions are the most visible signs of MS pathology on conventional MRI, it has been shown that even tissues that appear normal may exhibit decreased myelin content as revealed by myelin-specific images (i.e., myelin maps). Current methods for analyzing myelin maps typically use global or regional mean myelin measurements to detect abnormalities, but ignore finer spatial patterns that may be characteristic of MS. In this paper, we present a machine learning method to automatically learn, from multimodal MR images, latent spatial features that can potentially improve the detection of MS pathology at early stage. More specifically, 3D image patches are extracted from myelin maps and the corresponding T1-weighted (T1w) MRIs, and are used to learn a latent joint myelin-T1w feature representation via unsupervised deep learning. Using a data set of images from MS patients and healthy controls, a common set of patches are selected via a voxel-wise t-test performed between the two groups. In each MS image, any patches overlapping with focal lesions are excluded, and a feature imputation method is used to fill in the missing values. A feature selection process (LASSO) is then utilized to construct a sparse representation. The resulting normal-appearing features are used to train a random forest classifier. Using the myelin and T1w images of 55 relapse-remitting MS patients and 44 healthy controls in an 11-fold cross-validation experiment, the proposed method achieved an average classification accuracy of 87.9% (SD = 8.4%), which is higher and more consistent across folds than those attained by regional mean myelin (73.7%, SD = 13.7%) and T1w measurements (66.7%, SD = 10.6%), or deep-learned features in either the myelin (83.8%, SD = 11.0%) or T1w (70.1%, SD = 13.6%) images alone, suggesting that the proposed method has strong potential for identifying image features that are more sensitive and specific to MS pathology in normal-appearing brain tissues.

Evaluation methods of a middleware for networked surgical simulations.

Distributed surgical virtual environments are desirable since they substantially extend the accessibility of computational resources by network communication. However, network conditions critically affects the quality of a networked surgical simulation in terms of bandwidth limit, delays, and packet losses, etc. A solution to this problem is to introduce a middleware between the simulation application and the network so that it can take actions to enhance the user-perceived simulation performance. To comprehensively assess the effectiveness of such a middleware, we propose several evaluation methods in this paper, i.e., semi-automatic evaluation, middleware overhead measurement, and usability test.

Modeling the variability in brain morphology and lesion distribution in multiple sclerosis by deep learning.

Changes in brain morphology and white matter lesions are two hallmarks of multiple sclerosis (MS) pathology, but their variability beyond volumetrics is poorly characterized. To further our understanding of complex MS pathology, we aim to build a statistical model of brain images that can automatically discover spatial patterns of variability in brain morphology and lesion distribution. We propose building such a model using a deep belief network (DBN), a layered network whose parameters can be learned from training images. In contrast to other manifold learning algorithms, the DBN approach does not require a prebuilt proximity graph, which is particularly advantageous for modeling lesions, because their sparse and random nature makes defining a suitable distance measure between lesion images challenging. Our model consists of a morphology DBN, a lesion DBN, and a joint DBN that models concurring morphological and lesion patterns. Our results show that this model can automatically discover the classic patterns of MS pathology, as well as more subtle ones, and that the parameters computed have strong relationships to MS clinical scores.

Non-local spatial regularization of MRI T2 relaxation images for myelin water quantification.

Myelin is an essential component of nerve fibers and monitoring its health is important for studying diseases that attack myelin, such as multiple sclerosis (MS). The amount of water trapped within myelin, which is a surrogate for myelin content and integrity, can be measured in vivo using MRI relaxation techniques that acquire a series of images at multiple echo times to produce a T2 decay curve at each voxel. These curves are then analyzed, most commonly using non-negative least squares (NNLS) fitting, to produce T2 distributions from which water measurements are made. NNLS is unstable with respect to the noise and variations found in typical T2 relaxation images, making some form of regularization inevitable. The current methods of NNLS regularization for measuring myelin water have two key limitations: 1) they use strictly local neighborhood information to regularize each voxel, which limits their effectiveness for very noisy images, and 2) the neighbors of each voxel contribute to its regularization equally, which can over-smooth fine details. To overcome these limitations, we propose a new regularization algorithm in which local and non-local information is gathered and used adaptively for each voxel. Our results demonstrate that the proposed method provides more globally consistent myelin water measurements yet preserves fine structures. Our experiment with real patient data also shows that the algorithm improves the ability to distinguish two sample groups, one of MS patients and the other of healthy subjects.

Effects of Aeration of Sawdust Cultivation Bags on Hyphal Growth of Lentinula edodes.

The effects of aeration through lid filters on the hyphal growth of Lentinula edodes (oak mushroom) in sawdust cultivation bags were investigated. The aeration treatment levels were traditional 27 mm hole cotton plugs, cotton balls and combinations of seven hole sizes × two hole positions (up and under) in the lids covering plastic bags containing 1.4 kg sawdust medium at 63% moisture that had been autoclaved for one hour and inoculated with sawdust spawn of L. edodes strain 921. Aeration treatment effects were measured based on the CO(2) concentration at the 15th wk, as well as the hyphal growth rate and degree of weight loss of bags every 14 days for 15 wk. In bags with traditional cotton plugs, the CO(2) concentration was 3.8 ± 1.3%, daily mean hyphal growth was 2.3 ± 0.6 mm and daily mean weight loss was 0.84 ± 0.26 g. In the bags with 15 mm diameter holes, the CO(2) concentration was 6.0 ± 1.6%, daily hyphal growth was 2.8 ± 0.2 mm and daily weight loss was 0.86 ± 0.4 g. The bags with 15 mm holes had a higher CO(2) concentration and lower water loss than bags with other hole sizes, but the hyphal growth was not significantly different from that of other bags. The weight loss of bags increased proportionally relative to the lid hole sizes. Taken together, these results indicate that traditional cotton plugs are economically efficient, but 15 mm hole lids are the most efficient at maintaining hyphal growth and controlling water loss while allowing CO(2) emissions.