Search

We describe OHBA Software Library for the analysis of electrophysiological data (osl-ephys). This toolbox builds on top of the widely used MNE-Python package and provides unique analysis tools for magneto-/electro-encephalography (M/EEG) sensor and source space analysis, which can be used modularly. In particular, it facilitates processing large amounts of data using batch parallel processing, with high standards for reproducibility through a config API and log keeping, and efficient quality assurance by producing HTML processing reports. It also provides new functionality for doing coregistration, source reconstruction and parcellation in volumetric space, allowing for an alternative pipeline that avoids the need for surface-based processing, e.g., through the use of Fieldtrip. Here, we introduce osl-ephys by presenting examples applied to a publicly available M/EEG data (the multimodal faces dataset). osl-ephys is open-source software distributed on the Apache License and available as a Python package through PyPi and GitHub.

Clinical machine learning research and AI driven clinical decision support models rely on clinically accurate labels. Manually extracting these labels with the help of clinical specialists is often time-consuming and expensive. This study tests the feasibility of automatic span- and document-level diagnosis extraction from unstructured Dutch echocardiogram reports. We included 115,692 unstructured echocardiogram reports from the UMCU a large university hospital in the Netherlands. A randomly selected subset was manually annotated for the occurrence and severity of eleven commonly described cardiac characteristics. We developed and tested several automatic labelling techniques at both span and document levels, using weighted and macro F1-score, precision, and recall for performance evaluation. We compared the performance of span labelling against document labelling methods, which included both direct document classifiers and indirect document classifiers that rely on span classification results. The SpanCategorizer and MedRoBERTa$.$nl models outperformed all other span and document classifiers, respectively. The weighted F1-score varied between characteristics, ranging from 0.60 to 0.93 in SpanCategorizer and 0.96 to 0.98 in MedRoBERTa$.$nl. Direct document classification was superior to indirect document classification using span classifiers. SetFit achieved competitive document classification performance using only 10% of the training data. Utilizing a reduced label set yielded near-perfect document classification results. We recommend using our published SpanCategorizer and MedRoBERTa$.$nl models for span- and document-level diagnosis extraction from Dutch echocardiography reports. For settings with limited training data, SetFit may be a promising alternative for document classification., Comment: 28 pages, 5 figures

Deep learning techniques can be used to first training unsupervised models on large amounts of unlabelled data, before fine-tuning the models on specific tasks. This approach has seen massive success for various kinds of data, e.g. images, language, audio, and holds the promise of improving performance in various downstream tasks (e.g. encoding or decoding brain data). However, there has been limited progress taking this approach for modelling brain signals, such as Magneto-/electroencephalography (M/EEG). Here we propose two classes of deep learning foundational models that can be trained using forecasting of unlabelled MEG. First, we consider a modified Wavenet; and second, we consider a modified Transformer-based (GPT2) model. The modified GPT2 includes a novel application of tokenisation and embedding methods, allowing a model developed initially for the discrete domain of language to be applied to continuous multichannel time series data. We also extend the forecasting framework to include condition labels as inputs, enabling better modelling (encoding) of task data. We compare the performance of these deep learning models with standard linear autoregressive (AR) modelling on MEG data. This shows that GPT2-based models provide better modelling capabilities than Wavenet and linear AR models, by better reproducing the temporal, spatial and spectral characteristics of real data and evoked activity in task data. We show how the GPT2 model scales well to multiple subjects, while adapting its model to each subject through subject embedding. Finally, we show how such a model can be useful in downstream decoding tasks through data simulation. All code is available on GitHub (https://github.com/ricsinaruto/MEG-transfer-decoding)., Comment: Code available on GitHub (https://github.com/ricsinaruto/MEG-transfer-decoding). Part of PhD thesis (https://ricsinaruto.github.io/docs/thesis_final_appendix.pdf)

Kurtosis minus squared skewness is bounded from below by 1, but for unimodal distributions this parameter is bounded by 189/125. In some applications it is natural to compare distributions by comparing their kurtosis-minus-squared-skewness parameters. The asymptotic behavior of the empirical version of this parameter is studied here for i.i.d. random variables. The result may be used to test the hypothesis of unimodality against the alternative that the kurtosis-minus-squared-skewness parameter is less than 189/125. However, such a test has to be applied with care, since this parameter can take arbitrarily large values, also for multimodal distributions. Numerical results are presented and for three classes of distributions the skewness-kurtosis sets are described in detail., Comment: 14 pages, 2 tables, 7 figures

As structured data are often insufficient, labels need to be extracted from free text in electronic health records when developing models for clinical information retrieval and decision support systems. One of the most important contextual properties in clinical text is negation, which indicates the absence of findings. We aimed to improve large scale extraction of labels by comparing three methods for negation detection in Dutch clinical notes. We used the Erasmus Medical Center Dutch Clinical Corpus to compare a rule-based method based on ContextD, a biLSTM model using MedCAT and (finetuned) RoBERTa-based models. We found that both the biLSTM and RoBERTa models consistently outperform the rule-based model in terms of F1 score, precision and recall. In addition, we systematically categorized the classification errors for each model, which can be used to further improve model performance in particular applications. Combining the three models naively was not beneficial in terms of performance. We conclude that the biLSTM and RoBERTa-based models in particular are highly accurate accurate in detecting clinical negations, but that ultimately all three approaches can be viable depending on the use case at hand., Comment: 24, 8, journal

Decoding brain imaging data are gaining popularity, with applications in brain-computer interfaces and the study of neural representations. Decoding is typicallysubject-specific and does not generalise well over subjects, due to high amounts ofbetween subject variability. Techniques that overcome this will not only providericher neuroscientific insights but also make it possible for group-level models to out-perform subject-specific models. Here, we propose a method that uses subjectembedding, analogous to word embedding in natural language processing, to learnand exploit the structure in between-subject variability as part of a decoding model,our adaptation of the WaveNet architecture for classification. We apply this to mag-netoencephalography data, where 15 subjects viewed 118 different images, with30 examples per image; to classify images using the entire 1 s window followingimage presentation. We show that the combination of deep learning and subjectembedding is crucial to closing the performance gap between subject- and group-level decoding models. Importantly, group models outperform subject models onlow-accuracy subjects (although slightly impair high-accuracy subjects) and can behelpful for initialising subject models. While we have not generally found group-levelmodels to perform better than subject-level models, the performance of groupmodelling is expected to be even higher with bigger datasets. In order to providephysiological interpretation at the group level, we make use of permutation featureimportance. This provides insights into the spatiotemporal and spectral informationencoded in the models. All code is available on GitHub (https://github.com/ricsinaruto/MEG-group-decode)., Comment: Published in Human Brain Mapping

Mechatronic systems have increasingly stringent performance requirements for motion control, leading to a situation where many factors, such as position-dependency, cannot be neglected in feedforward control. The aim of this paper is to compensate for position-dependent effects by modeling feedforward parameters as a function of position. A framework to model and identify feedforward parameters as a continuous function of position is developed by combining Gaussian processes and feedforward parameter learning techniques. The framework results in a fully data-driven approach, which can be readily implemented for industrial control applications. The framework is experimentally validated and shows a significant performance increase on a commercial wire bonder., Comment: in IEEE 17th International Conference on Advanced Motion Control, Padova, Italy, 2022

We present the Engineering Development Array 2, which is one of two instruments built as a second generation prototype station for the future Square Kilometre Array Low Frequency Array. The array is comprised of 256 dual-polarization dipole antennas that can work as a phased array or as a standalone interferometer. We describe the design of the array and the details of design changes from previous generation instruments, as well as the motivation for the changes. Using the array as an imaging interferometer, we measure the sensitivity of the array at five frequencies ranging from 70 to 320 MHz., Comment: To appear in SPIE JATIS special section on SKA Observatory

Abnormal airway dilatation, termed traction bronchiectasis, is a typical feature of idiopathic pulmonary fibrosis (IPF). Volumetric computed tomography (CT) imaging captures the loss of normal airway tapering in IPF. We postulated that automated quantification of airway abnormalities could provide estimates of IPF disease extent and severity. We propose AirQuant, an automated computational pipeline that systematically parcellates the airway tree into its lobes and generational branches from a deep learning based airway segmentation, deriving airway structural measures from chest CT. Importantly, AirQuant prevents the occurrence of spurious airway branches by thick wave propagation and removes loops in the airway-tree by graph search, overcoming limitations of existing airway skeletonisation algorithms. Tapering between airway segments (intertapering) and airway tortuosity computed by AirQuant were compared between 14 healthy participants and 14 IPF patients. Airway intertapering was significantly reduced in IPF patients, and airway tortuosity was significantly increased when compared to healthy controls. Differences were most marked in the lower lobes, conforming to the typical distribution of IPF-related damage. AirQuant is an open-source pipeline that avoids limitations of existing airway quantification algorithms and has clinical interpretability. Automated airway measurements may have potential as novel imaging biomarkers of IPF severity and disease extent., Comment: 14 pages, 8 Figures, for associated source code, see https://github.com/ashkanpakzad/AirQuant

Electrocardiography (ECG) is an effective and non-invasive diagnostic tool that measures the electrical activity of the heart. Interpretation of ECG signals to detect various abnormalities is a challenging task that requires expertise. Recently, the use of deep neural networks for ECG classification to aid medical practitioners has become popular, but their black box nature hampers clinical implementation. Several saliency-based interpretability techniques have been proposed, but they only indicate the location of important features and not the actual features. We present a novel interpretability technique called qLST, a query-based latent space traversal technique that is able to provide explanations for any ECG classification model. With qLST, we train a neural network that learns to traverse in the latent space of a variational autoencoder trained on a large university hospital dataset with over 800,000 ECGs annotated for 28 diseases. We demonstrate through experiments that we can explain different black box classifiers by generating ECGs through these traversals., Comment: Machine Learning for Health (ML4H) - Extended Abstract

The design and development process for the Square Kilometre Array (SKA) radio telescope, the Low Frequency Aperture Array component, was progressed during the SKA pre-construction phase by an international consortium, with the goal of meeting requirements for a critical design review. As part of the development process a full-sized prototype SKA Low station was deployed, the Aperture Array Verification System 1 (AAVS1). We provide a system overview and describe the commissioning results of AAVS1, which is a low frequency radio telescope with 256 dual-polarisation log-periodic dipole antennas working as a phased array. A detailed system description is provided, including an in-depth overview of relevant sub-systems, ranging from hardware, firmware, software, calibration,and control sub-systems. Early commissioning results cover initial bootstrapping, array calibration, stability testing, beam-forming,and on-sky sensitivity validation. Lessons learned are presented, along with future developments.

The Thrombolysis in Cerebral Infarction (TICI) score is an important metric for reperfusion therapy assessment in acute ischemic stroke. It is commonly used as a technical outcome measure after endovascular treatment (EVT). Existing TICI scores are defined in coarse ordinal grades based on visual inspection, leading to inter- and intra-observer variation. In this work, we present autoTICI, an automatic and quantitative TICI scoring method. First, each digital subtraction angiography (DSA) acquisition is separated into four phases (non-contrast, arterial, parenchymal and venous phase) using a multi-path convolutional neural network (CNN), which exploits spatio-temporal features. The network also incorporates sequence level label dependencies in the form of a state-transition matrix. Next, a minimum intensity map (MINIP) is computed using the motion corrected arterial and parenchymal frames. On the MINIP image, vessel, perfusion and background pixels are segmented. Finally, we quantify the autoTICI score as the ratio of reperfused pixels after EVT. On a routinely acquired multi-center dataset, the proposed autoTICI shows good correlation with the extended TICI (eTICI) reference with an average area under the curve (AUC) score of 0.81. The AUC score is 0.90 with respect to the dichotomized eTICI. In terms of clinical outcome prediction, we demonstrate that autoTICI is overall comparable to eTICI., Comment: Accepted for publication in IEEE Transactions on Medical Imaging (IEEE TMI)

While Atomic Force Microscopy is mostly used to investigate surface properties, people have almost since its invention sought to apply its high resolution capability to image also structures buried within samples. One of the earliest techniques for this was based on using ultrasound excitations to visualize local differences in effective tip-sample stiffness caused by the presence of buried structures with different visco-elasticity from their surroundings. While the use of ultrasound has often triggered discussions on the contribution of diffraction or scattering of acoustic waves in visualizing buried structures, no conclusive papers on this topic have been published. Here we demonstrate and discuss how such acoustical effects can be unambiguously recognized and can be used with Atomic Force Microscopy to visualize deeply buried structures., Comment: 18 pages, 5 figures