Assessing brain involvement in Fabry disease with deep learning and the brain-age paradigm

While neurological manifestations are core features of Fabry disease (FD), quantitative neuroimaging biomarkers allowing to measure brain involvement are lacking. We used deep learning and the brain-age paradigm to assess whether FD patients' brains appear older than normal and to validate brain-predicted age difference (brain-PAD) as a possible disease severity biomarker. MRI scans of FD patients and healthy controls (HCs) from a single Institution were, retrospectively, studied. The Fabry stabilization index (FASTEX) was recorded as a measure of disease severity. Using minimally preprocessed 3D T1-weighted brain scans of healthy subjects from eight publicly available sources (N = 2160; mean age = 33 years [range 4-86]), we trained a model predicting chronological age based on a DenseNet architecture and used it to generate brain-age predictions in the internal cohort. Within a linear modeling framework, brain-PAD was tested for age/sex-adjusted associations with diagnostic group (FD vs. HC), FASTEX score, and both global and voxel-level neuroimaging measures. We studied 52 FD patients (40.6 ± 12.6 years; 28F) and 58 HC (38.4 ± 13.4 years; 28F). The brain-age model achieved accurate out-of-sample performance (mean absolute error = 4.01 years, R2 = .90). FD patients had significantly higher brain-PAD than HC (estimated marginal means: 3.1 vs. -0.1, p = .01). Brain-PAD was associated with FASTEX score (B = 0.10, p = .02), brain parenchymal fraction (B = -153.50, p = .001), white matter hyperintensities load (B = 0.85, p = .01), and tissue volume reduction throughout the brain. We demonstrated that FD patients' brains appear older than normal. Brain-PAD correlates with FD-related multi-organ damage and is influenced by both global brain volume and white matter hyperintensities, offering a comprehensive biomarker of (neurological) disease severity.

VeerNet: Using Deep Neural Networks for Curve Classification and Digitization of Raster Well-Log Images

Raster logs are scanned representations of the analog data recorded in subsurface drilling. Geologists rely on these images to interpret well-log curves and deduce the physical properties of geological formations. Scanned images contain various artifacts, including hand-written texts, brightness variability, scan defects, etc. The manual effort involved in reading the data is substantial. To mitigate this, unsupervised computer vision techniques are employed to extract and interpret the curves digitally. Existing algorithms predominantly require manual intervention, resulting in slow processing times, and are erroneous. This research aims to address these challenges by proposing VeerNet, a deep neural network architecture designed to semantically segment the raster images from the background grid to classify and digitize (i.e., extracting the analytic formulation of the written curve) the well-log data. The proposed approach is based on a modified UNet-inspired architecture leveraging an attention-augmented read-process-write strategy to balance retaining key signals while dealing with the different input-output sizes. The reported results show that the proposed architecture efficiently classifies and digitizes the curves with an overall F1 score of 35% and Intersection over Union of 30%, achieving 97% recall and 0.11 Mean Absolute Error when compared with real data on binary segmentation of multiple curves. Finally, we analyzed VeerNet's ability in predicting Gamma-ray values, achieving a Pearson coefficient score of 0.62 when compared to measured data.

ReUse: REgressive Unet for Carbon Storage and Above-Ground Biomass Estimation

The United Nations Framework Convention on Climate Change (UNFCCC) has recently established the Reducing Emissions from Deforestation and forest Degradation (REDD+) program, which requires countries to report their carbon emissions and sink estimates through national greenhouse gas inventories (NGHGI). Thus, developing automatic systems capable of estimating the carbon absorbed by forests without in situ observation becomes essential. To support this critical need, in this work, we introduce ReUse, a simple but effective deep learning approach to estimate the carbon absorbed by forest areas based on remote sensing. The proposed method’s novelty is in using the public above-ground biomass (AGB) data from the European Space Agency’s Climate Change Initiative Biomass project as ground truth to estimate the carbon sequestration capacity of any portion of land on Earth using Sentinel-2 images and a pixel-wise regressive UNet. The approach has been compared with two literature proposals using a private dataset and human-engineered features. The results show a more remarkable generalization ability of the proposed approach, with a decrease in Mean Absolute Error and Root Mean Square Error over the runner-up of 16.9 and 14.3 in the area of Vietnam, 4.7 and 5.1 in the area of Myanmar, 8.0 and 1.4 in the area of Central Europe, respectively. As a case study, we also report an analysis made for the Astroni area, a World Wildlife Fund (WWF) natural reserve struck by a large fire, producing predictions consistent with values found by experts in the field after in situ investigations. These results further support the use of such an approach for the early detection of AGB variations in urban and rural areas.

An approach for the automatic verification of blockchain protocols: the Tweetchain case study

This paper proposes a model-driven approach for the security modelling and analysis of blockchain based protocols. The modelling is built upon the definition of a UML profile, which is able to capture transaction-oriented information. The analysis is based on existing formal analysis tools. In particular, the paper considers the Tweetchain protocol, a recent proposal that leverages online social networks, i.e., Twitter, for extending blockchain to domains with small-value transactions, such as IoT. A specialized textual notation is added to the UML profile to capture features of this protocol. Furthermore, a model transformation is defined to generate a Tamarin model, from the UML models, via an intermediate well-known notation, i.e., the Alice &Bob notation. Finally, Tamarin Prover is used to verify the model of the protocol against some security properties. This work extends a previous one, where the Tamarin formal models were generated by hand. A comparison on the analysis results, both under the functional and non-functional aspects, is reported here too.

Interaction data are identifiable even across long periods of time

Fine-grained records of people’s interactions, both offline and online, are collected at large scale. These data contain sensitive information about whom we meet, talk to, and when. We demonstrate here how people’s interaction behavior is stable over long periods of time and can be used to identify individuals in anonymous datasets. Our attack learns the profile of an individual using geometric deep learning and triplet loss optimization. In a mobile phone metadata dataset of more than 40k people, it correctly identifies 52% of individuals based on their 2-hop interaction graph. We further show that the profiles learned by our method are stable over time and that 24% of people are still identifiable after 20 weeks. Our results suggest that people with well-balanced interaction graphs are more identifiable. Applying our attack to Bluetooth close-proximity networks, we show that even 1-hop interaction graphs are enough to identify people more than 26% of the time. Our results provide strong evidence that disconnected and even re-pseudonymized interaction data can be linked together making them personal data under the European Union’s General Data Protection Regulation.

Stratification of multiple sclerosis patients using unsupervised machine learning: a single-visit MRI-driven approach

OBJECTIVES

To stratify patients with multiple sclerosis (pwMS) based on brain MRI-derived volumetric features using unsupervised machine learning.

METHODS

The 3-T brain MRIs of relapsing-remitting pwMS including 3D-T1w and FLAIR-T2w sequences were retrospectively collected, along with Expanded Disability Status Scale (EDSS) scores and long-term (10 ± 2 years) clinical outcomes (EDSS, cognition, and progressive course). From the MRIs, volumes of demyelinating lesions and 116 atlas-defined gray matter regions were automatically segmented and expressed as z-scores referenced to external populations. Following feature selection, baseline MRI-derived biomarkers entered the Subtype and Stage Inference (SuStaIn) algorithm, which estimates subgroups characterized by distinct patterns of biomarker evolution and stages within subgroups. The trained model was then applied to longitudinal MRIs. Stability of subtypes and stage change over time were assessed via Krippendorf's α and multilevel linear regression models, respectively. The prognostic relevance of SuStaIn classification was assessed with ordinal/logistic regression analyses.

RESULTS

We selected 425 pwMS (35.9 ± 9.9 years; F/M: 301/124), corresponding to 1129 MRI scans, along with healthy controls (N = 148; 35.9 ± 13.0 years; F/M: 77/71) and external pwMS (N = 80; 40.4 ± 11.9 years; F/M: 56/24) as reference populations. Based on 11 biomarkers surviving feature selection, two subtypes were identified, designated as "deep gray matter (DGM)-first" subtype (N = 238) and "cortex-first" subtype (N = 187) according to the atrophy pattern. Subtypes were consistent over time (α = 0.806), with significant annual stage increase (b = 0.20; p < 0.001). EDSS was associated with stage and DGM-first subtype (p ≤ 0.02). Baseline stage predicted long-term disability, transition to progressive course, and cognitive impairment (p ≤ 0.03), with the latter also associated with DGM-first subtype (p = 0.005).

CONCLUSIONS

Unsupervised learning modelling of brain MRI-derived volumetric features provides a biologically reliable and prognostically meaningful stratification of pwMS.

KEY POINTS

• The unsupervised modelling of brain MRI-derived volumetric features can provide a single-visit stratification of multiple sclerosis patients. • The so-obtained classification tends to be consistent over time and captures disease-related brain damage progression, supporting the biological reliability of the model. • Baseline stratification predicts long-term clinical disability, cognition, and transition to secondary progressive course.

A Pipelined Tracer-Aware Approach for Lesion Segmentation in Breast DCE-MRI

The recent spread of Deep Learning (DL) in medical imaging is pushing researchers to explore its suitability for lesion segmentation in Dynamic Contrast-Enhanced Magnetic-Resonance Imaging (DCE-MRI), a complementary imaging procedure increasingly used in breast-cancer analysis. Despite some promising proposed solutions, we argue that a "naive" use of DL may have limited effectiveness as the presence of a contrast agent results in the acquisition of multimodal 4D images requiring thorough processing before training a DL model. We thus propose a pipelined approach where each stage is intended to deal with or to leverage a peculiar characteristic of breast DCE-MRI data: the use of a breast-masking pre-processing to remove non-breast tissues; the use of Three-Time-Points (3TP) slices to effectively highlight contrast agent time course; the application of a motion-correction technique to deal with patient involuntary movements; the leverage of a modified U-Net architecture tailored on the problem; and the introduction of a new "Eras/Epochs" training strategy to handle the unbalanced dataset while performing a strong data augmentation. We compared our pipelined solution against some literature works. The results show that our approach outperforms the competitors by a large margin (+9.13% over our previous solution) while also showing a higher generalization ability.

Machine Learning Applications in Head and Neck Radiation Oncology: Lessons From Open-Source Radiomics Challenges

Radiomics leverages existing image datasets to provide non-visible data extraction via image post-processing, with the aim of identifying prognostic, and predictive imaging features at a sub-region of interest level. However, the application of radiomics is hampered by several challenges such as lack of image acquisition/analysis method standardization, impeding generalizability. As of yet, radiomics remains intriguing, but not clinically validated. We aimed to test the feasibility of a non-custom-constructed platform for disseminating existing large, standardized databases across institutions for promoting radiomics studies. Hence, University of Texas MD Anderson Cancer Center organized two public radiomics challenges in head and neck radiation oncology domain. This was done in conjunction with MICCAI 2016 satellite symposium using Kaggle-in-Class, a machine-learning and predictive analytics platform. We drew on clinical data matched to radiomics data derived from diagnostic contrast-enhanced computed tomography (CECT) images in a dataset of 315 patients with oropharyngeal cancer. Contestants were tasked to develop models for (i) classifying patients according to their human papillomavirus status, or (ii) predicting local tumor recurrence, following radiotherapy. Data were split into training, and test sets. Seventeen teams from various professional domains participated in one or both of the challenges. This review paper was based on the contestants' feedback; provided by 8 contestants only (47%). Six contestants (75%) incorporated extracted radiomics features into their predictive model building, either alone (n = 5; 62.5%), as was the case with the winner of the "HPV" challenge, or in conjunction with matched clinical attributes (n = 2; 25%). Only 23% of contestants, notably, including the winner of the "local recurrence" challenge, built their model relying solely on clinical data. In addition to the value of the integration of machine learning into clinical decision-making, our experience sheds light on challenges in sharing and directing existing datasets toward clinical applications of radiomics, including hyper-dimensionality of the clinical/imaging data attributes. Our experience may help guide researchers to create a framework for sharing and reuse of already published data that we believe will ultimately accelerate the pace of clinical applications of radiomics; both in challenge or clinical settings.

Publisher's Note: JLab Measurements of the ^{3}He Form Factors at Large Momentum Transfers [Phys. Rev. Lett. 119, 162501 (2017)]

This corrects the article DOI: 10.1103/PhysRevLett.119.162501.

JLab Measurements of the ^{3}He Form Factors at Large Momentum Transfers

The charge and magnetic form factors, F_{C} and F_{M}, respectively, of ^{3}He are extracted in the kinematic range 25  fm^{-2}≤Q^{2}≤61  fm^{-2} from elastic electron scattering by detecting ^{3}He recoil nuclei and scattered electrons in coincidence with the two High Resolution Spectrometers of the Hall A Facility at Jefferson Lab. The measurements find evidence for the existence of a second diffraction minimum for the magnetic form factor at Q^{2}=49.3  fm^{-2} and for the charge form factor at Q^{2}=62.0  fm^{-2}. Both minima are predicted to exist in the Q^{2} range accessible by this Jefferson Lab experiment. The data are in qualitative agreement with theoretical calculations based on realistic interactions and accurate methods to solve the three-body nuclear problem.

Precision Measurement of the p(e,e^{'}p)π^{0} Reaction at Threshold

New results are reported from a measurement of π^{0} electroproduction near threshold using the p(e,e^{'}p)π^{0} reaction. The experiment was designed to determine precisely the energy dependence of s- and p-wave electromagnetic multipoles as a stringent test of the predictions of chiral perturbation theory (ChPT). The data were taken with an electron beam energy of 1192 MeV using a two-spectrometer setup in Hall A at Jefferson Lab. For the first time, complete coverage of the ϕ_{π}^{*} and θ_{π}^{*} angles in the pπ^{0} center of mass was obtained for invariant energies above threshold from 0.5 up to 15 MeV. The 4-momentum transfer Q^{2} coverage ranges from 0.05 to 0.155 (GeV/c)^{2} in fine steps. A simple phenomenological analysis of our data shows strong disagreement with p-wave predictions from ChPT for Q^{2}>0.07 (GeV/c)^{2}, while the s-wave predictions are in reasonable agreement.

Measurement of the target-normal single-spin asymmetry in deep-inelastic scattering from the reaction (3)He(↑)(e,e')X

We report the first measurement of the target-normal single-spin asymmetry in deep-inelastic scattering from the inclusive reaction 3)He(↑)(e,e')X on a polarized (3)He gas target. Assuming time-reversal invariance, this asymmetry is strictly zero in the Born approximation but can be nonzero if two-photon-exchange contributions are included. The experiment, conducted at Jefferson Lab using a 5.89 GeV electron beam, covers a range of 1.7<W<2.9  GeV, 1.0<Q(2)<4.0  GeV(2) and 0.16<x<0.65. Neutron asymmetries were extracted using the effective nucleon polarization and measured proton-to-(3)He cross-section ratios. The measured neutron asymmetries are negative with an average value of (-1.09±0.38)×10(-2) for invariant mass W>2  GeV, which is nonzero at the 2.89σ level. Our measured asymmetry agrees both in sign and magnitude with a two-photon-exchange model prediction that uses input from the Sivers transverse momentum distribution obtained from semi-inclusive deep-inelastic scattering.

JLab measurement of the 4He charge form factor at large momentum transfers

The charge form factor of 4He has been extracted in the range 29  fm(-2) ≤ Q2 ≤ 77  fm(-2) from elastic electron scattering, detecting 4He recoil nuclei and electrons in coincidence with the high resolution spectrometers of the Hall A Facility of Jefferson Lab. The measurements have uncovered a second diffraction minimum for the form factor, which was predicted in the Q2 range of this experiment. The data are in qualitative agreement with theoretical calculations based on realistic interactions and accurate methods to solve the few-body problem.

Beam-target double-spin asymmetry A{LT} in charged pion production from deep inelastic scattering on a transversely polarized {3}He target at 1.4<Q{2}<2.7 GeV{2}

We report the first measurement of the double-spin asymmetry A{LT} for charged pion electroproduction in semi-inclusive deep-inelastic electron scattering on a transversely polarized {3}He target. The kinematics focused on the valence quark region, 0.16<x<0.35 with 1.4<Q{2}<2.7  GeV{2}. The corresponding neutron A{LT} asymmetries were extracted from the measured {3}He asymmetries and proton over {3}He cross section ratios using the effective polarization approximation. These new data probe the transverse momentum dependent parton distribution function g{1T}{q} and therefore provide access to quark spin-orbit correlations. Our results indicate a positive azimuthal asymmetry for π{-} production on {3}He and the neutron, while our π{+} asymmetries are consistent with zero.

Single spin asymmetries in charged pion production from semi-inclusive deep inelastic scattering on a transversely polarized 3He Target at Q2 = 1.4-2.7 GeV2

We report the first measurement of target single spin asymmetries in the semi-inclusive (3)He(e,e'π(±))X reaction on a transversely polarized target. The experiment, conducted at Jefferson Lab using a 5.9 GeV electron beam, covers a range of 0.16 < x < 0.35 with 1.4 < Q(2) < 2.7 GeV(2). The Collins and Sivers moments were extracted from the azimuthal angular dependence of the measured asymmetries. The π(±) Collins moments for (3)He are consistent with zero, except for the π(+) moment at x = 0.35, which deviates from zero by 2.3σ. While the π(-) Sivers moments are consistent with zero, the π(+) Sivers moments favor negative values. The neutron results were extracted using the nucleon effective polarization and measured cross section ratios of proton to (3)He, and are largely consistent with the predictions of phenomenological fits and quark model calculations.

High-resolution spectroscopy of Lambda16N by electroproduction

An experimental study of the (16)O(e,e'K(+))(Lambda)(16)N reaction has been performed at Jefferson Lab. A thin film of falling water was used as a target. This permitted a simultaneous measurement of the p(e,e'K(+))Lambda, Sigma(0) exclusive reactions and a precise calibration of the energy scale. A ground-state binding energy of 13.76+/-0.16 MeV was obtained for (Lambda)(16)N with better precision than previous measurements on the mirror hypernucleus (Lambda)(16)O. Precise energies have been determined for peaks arising from a Lambda in s and p orbits coupled to the p(1/2) and p(3/2) hole states of the (15)N core nucleus.

Investigation of proton-proton short-range correlations via the 12C(e,e'pp) reaction

We investigated simultaneously the 12C(e,e'p) and 12C(e,e'pp) reactions at Q2=2 (GeV/c)2, xB=1.2, and in an (e, e'p) missing-momentum range from 300 to 600 MeV/c. At these kinematics, with a missing momentum greater than the Fermi momentum of nucleons in a nucleus and far from the delta excitation, short-range nucleon-nucleon correlations are predicted to dominate the reaction. For (9.5+/-2)% of the 12C(e,e'p) events, a recoiling partner proton was observed back-to-back to the 12C(e,e'p) missing-momentum vector, an experimental signature of correlations.

High resolution spectroscopy of (lambda)(12)B by electroproduction

An experiment measuring electroproduction of hypernuclei has been performed in hall A at Jefferson Lab on a 12C target. In order to increase counting rates and provide unambiguous kaon identification two superconducting septum magnets and a ring imaging Cherenkov detector were added to the hall A standard equipment. An unprecedented energy resolution of less than 700 keV FWHM has been achieved. Thus, the observed (Lambda)(12)B spectrum shows for the first time identifiable strength in the core-excited region between the ground-state s-wave Lambda peak and the 11 MeV p-wave Lambda peak.

Neutron capture cross section measurement of 151Sm at the CERN neutron time of flight facility (n_TOF)

The151Sm(n,gamma)152Sm cross section has been measured at the spallation neutron facility n_TOF at CERN in the energy range from 1 eV to 1 MeV. The new facility combines excellent resolution in neutron time-of-flight, low repetition rates, and an unsurpassed instantaneous luminosity, resulting in rather favorable signal/background ratios. The 151Sm cross section is of importance for characterizing neutron capture nucleosynthesis in asymptotic giant branch stars. At a thermal energy of kT=30 keV the Maxwellian averaged cross section of this unstable isotope (t(1/2)=93 yr) was determined to be 3100+/-160 mb, significantly larger than theoretical predictions.

Possibility to deduce the emission time sequence of neutrons and protons from the neutron-proton correlation function

Experimental information has been derived from the neutron-proton correlation function in order to deduce the time sequence of neutrons and protons emitted at 45 degrees in the E/A = 45 MeV 58Ni + 27Al reaction.

The Use of Gaming Strategies in a Transcultural Setting

Saudi Arabia's vast economic resources have enabled the development of state-of-the-art hospitals. Nurses recruited from around the world staff these hospitals creating one of the most multicultural practice settings in the world. Ethnic, educational, and experiential diversity; language and communication barriers; and alternative ways of knowing and learning challenge nurse educators to be more creative and explore opportunities for greater participation and learning among various cultural groups. Gaming, as a teaching-learning strategy for multicultural participants, affords the necessary flexibility and nonthreatening atmosphere which facilitates positive interactions among different, and often competing, communication patterns and learning styles. This article explores how and why gaming is as an effective educational strategy in a transcultural setting.

The employer's bird's-eye view

Managed care has become a viable alternative for employers nationwide, Pittsburgh employers explain why.

Marketing accessibility in Pittsburgh

Surviving in the practice management world these days isn't quite like it used to be. It requires innovative marketing and expanded efforts. In this second in a series of articles profiling group practices and their administrators. The author focuses on management of an academic group.

ChoiceCare physicians: reaching out with value-added service

The wave of the future has broken. Group practices are everywhere. In some cases, practices are formed to efficiently and effectively market physician services. In other cases. It's a matter of physicians banding together to maintain control of patient care. In this issue of Pennsylvania Medicine, we debut a new series of bimonthly articles profiling group practices in Pennsylvania. We begin in Pittsburgh...

Office managers: nobody knows the trouble they see

Computers, code revisions, and patients' changing expectations have added responsibility and a new level of complexity to the job of medical office manager. How are you and your office manager coping? Some experienced managers relay their views of this rapidly changing field.