Unveiling peripheral neuropathy and cognitive dysfunction in diabetes: an observational and proof-of-concept study with video games and sensor-equipped insoles.

Background: Proactive screening for cognitive dysfunction (CD) and peripheral neuropathy (PNP) in elderly patients with diabetes mellitus is essential for early intervention, yet clinical examination is time-consuming and prone to bias. Objective: We aimed to investigate PNP and CD in a diabetes cohort and explore the possibility of identifying key features linked with the respective conditions by machine learning algorithms applied to data sets obtained in playful games controlled by sensor-equipped insoles. Methods: In a cohort of patients diagnosed with diabetes (n=261) aged over 50 years PNP and CD were diagnosed based on complete physical examination (neuropathy symptom and disability scores, and Montreal Cognitive Assessment). In an observational and proof-of-concept study patients performed a 15 min lasting gaming session encompassing tutorials and four video games with 5,244 predefined features. The steering of video games was solely achieved by modulating plantar pressure values, which were measured by sensor-equipped insoles in real-time. Data sets were used to identify key features indicating game performance with correlation regarding CD and PNP findings. Thereby, machine learning models (e.g. gradient boosting and lasso and elastic-net regularized generalized linear models) were set up to distinguish patients in the different groups. Results: PNP was diagnosed in 59% (n=153), CD in 34% (n=89) of participants, and 23% (n=61) suffered from both conditions. Multivariable regression analyses suggested that PNP was positively associated with CD in patients with diabetes (adjusted odds ratio = 1.95; 95% confidence interval: 1.03-3.76; P=0.04). Predictive game features were identified that significantly correlated with CD (n=59), PNP (n=40), or both (n=59). These features allowed to set up classification models that were enriched by individual risk profiles (i.e. gender, age, weight, BMI, diabetes type, and diabetes duration). The obtained models yielded good predictive performance with the area under the receiver-operating-characteristic curves reaching 0.95 for CD without PNP, 0.83 for PNP without CD, and 0.84 for CD and PNP combined. Conclusions: The video game-based assessment was able to categorize patients with CD and/or PNP with high accuracy. Future studies with larger cohorts are needed to validate these results and potentially enhance the discriminative power of video games.

Exploration of Interpretability Techniques for Deep COVID-19 Classification Using Chest X-ray Images.

The outbreak of COVID-19 has shocked the entire world with its fairly rapid spread, and has challenged different sectors. One of the most effective ways to limit its spread is the early and accurate diagnosing of infected patients. Medical imaging, such as X-ray and computed tomography (CT), combined with the potential of artificial intelligence (AI), plays an essential role in supporting medical personnel in the diagnosis process. Thus, in this article, five different deep learning models (ResNet18, ResNet34, InceptionV3, InceptionResNetV2, and DenseNet161) and their ensemble, using majority voting, have been used to classify COVID-19, pneumoniæ and healthy subjects using chest X-ray images. Multilabel classification was performed to predict multiple pathologies for each patient, if present. Firstly, the interpretability of each of the networks was thoroughly studied using local interpretability methods-occlusion, saliency, input X gradient, guided backpropagation, integrated gradients, and DeepLIFT-and using a global technique-neuron activation profiles. The mean micro F1 score of the models for COVID-19 classifications ranged from 0.66 to 0.875, and was 0.89 for the ensemble of the network models. The qualitative results showed that the ResNets were the most interpretable models. This research demonstrates the importance of using interpretability methods to compare different models before making a decision regarding the best performing model.

Deep learning based tomosynthesis denoising: a bias investigation across different breast types.

Purpose: High noise levels due to low X-ray dose are a challenge in digital breast tomosynthesis (DBT) reconstruction. Deep learning algorithms show promise in reducing this noise. However, these algorithms can be complex and biased toward certain patient groups if the training data are not representative. It is important to thoroughly evaluate deep learning-based denoising algorithms before they are applied in the medical field to ensure their effectiveness and fairness. In this work, we present a deep learning-based denoising algorithm and examine potential biases with respect to breast density, thickness, and noise level. Approach: We use physics-driven data augmentation to generate low-dose images from full field digital mammography and train an encoder-decoder network. The rectified linear unit (ReLU)-loss, specifically designed for mammographic denoising, is utilized as the objective function. To evaluate our algorithm for potential biases, we tested it on both clinical and simulated data generated with the virtual imaging clinical trial for regulatory evaluation pipeline. Simulated data allowed us to generate X-ray dose distributions not present in clinical data, enabling us to separate the influence of breast types and X-ray dose on the denoising performance. Results: Our results show that the denoising performance is proportional to the noise level. We found a bias toward certain breast groups on simulated data; however, on clinical data, our algorithm denoises different breast types equally well with respect to structural similarity index. Conclusions: We propose a robust deep learning-based denoising algorithm that reduces DBT projection noise levels and subject it to an extensive test that provides information about its strengths and weaknesses.

CHIASM-Net: Artificial Intelligence-Based Direct Identification of Chiasmal Abnormalities in Albinism.

Purpose: Albinism is a congenital disorder affecting pigmentation levels, structure, and function of the visual system. The identification of anatomical changes typical for people with albinism (PWA), such as optic chiasm malformations, could become an important component of diagnostics. Here, we tested an application of convolutional neural networks (CNNs) for this purpose. Methods: We established and evaluated a CNN, referred to as CHIASM-Net, for the detection of chiasmal malformations from anatomic magnetic resonance (MR) images of the brain. CHIASM-Net, composed of encoding and classification modules, was developed using MR images of controls (n = 1708) and PWA (n = 32). Evaluation involved 8-fold cross validation involving accuracy, precision, recall, and F1-score metrics and was performed on a subset of controls and PWA samples excluded from the training. In addition to quantitative metrics, we used Explainable AI (XAI) methods that granted insights into factors driving the predictions of CHIASM-Net. Results: The results for the scenario indicated an accuracy of 85 ± 14%, precision of 90 ± 14% and recall of 81 ± 18%. XAI methods revealed that the predictions of CHIASM-Net are driven by optic-chiasm white matter and by the optic tracts. Conclusions: CHIASM-Net was demonstrated to use relevant regions of the optic chiasm for albinism detection from magnetic resonance imaging (MRI) brain anatomies. This indicates the strong potential of CNN-based approaches for visual pathway analysis and ultimately diagnostics.

Active multitask learning with uncertainty-weighted loss for coronary calcium scoring.

PURPOSE: The coronary artery calcification (CAC) score is an independent marker for the risk of cardiovascular events. Automatic methods for quantifying CAC could reduce workload and assist radiologists in clinical decision-making. However, large annotated datasets are needed for training to achieve very good model performance, which is an expensive process and requires expert knowledge. The number of training data required can be reduced in an active learning scenario, which requires only the most informative samples to be labeled. Multitask learning techniques can improve model performance by joint learning of multiple related tasks and extraction of shared informative features. METHODS: We propose an uncertainty-weighted multitask learning model for coronary calcium scoring in electrocardiogram-gated (ECG-gated), noncontrast-enhanced cardiac calcium scoring CT. The model was trained to solve the two tasks of coronary artery region segmentation (weak labels) and coronary artery calcification segmentation (strong labels) simultaneously in an active learning scenario to improve model performance and reduce the number of samples needed for training. We compared our model with a single-task U-Net and a sequential-task model as well as other state-of-the-art methods. The model was evaluated on 1275 individual patients in three different datasets (DISCHARGE, CADMAN, orCaScore), and the relationship between model performance and various influencing factors (image noise, metal artifacts, motion artifacts, image quality) was analyzed. RESULTS: Joint learning of multiclass coronary artery region segmentation and binary coronary calcium segmentation improved calcium scoring performance. Since shared information can be learned from both tasks for complementary purposes, the model reached optimal performance with only 12% of the training data and one-third of the labeling time in an active learning scenario. We identified image noise as one of the most important factors influencing model performance along with anatomical abnormalities and metal artifacts. CONCLUSIONS: Our multitask learning approach with uncertainty-weighted loss improves calcium scoring performance by joint learning of shared features and reduces labeling costs when trained in an active learning scenario.

Conditional generative adversarial networks applied to EEG data can inform about the inter-relation of antagonistic behaviors on a neural level.

Goal-directed actions frequently require a balance between antagonistic processes (e.g., executing and inhibiting a response), often showing an interdependency concerning what constitutes goal-directed behavior. While an inter-dependency of antagonistic actions is well described at a behavioral level, a possible inter-dependency of underlying processes at a neuronal level is still enigmatic. However, if there is an interdependency, it should be possible to predict the neurophysiological processes underlying inhibitory control based on the neural processes underlying speeded automatic responses. Based on that rationale, we applied artificial intelligence and source localization methods to human EEG recordings from N = 255 participants undergoing a response inhibition experiment (Go/Nogo task). We show that the amplitude and timing of scalp potentials and their functional neuroanatomical sources during inhibitory control can be inferred by conditional generative adversarial networks (cGANs) using neurophysiological data recorded during response execution. We provide insights into possible limitations in the use of cGANs to delineate the interdependency of antagonistic actions on a neurophysiological level. Nevertheless, artificial intelligence methods can provide information about interdependencies between opposing cognitive processes on a neurophysiological level with relevance for cognitive theory.

Uncertainty-aware temporal self-learning (UATS): Semi-supervised learning for segmentation of prostate zones and beyond.

Various convolutional neural network (CNN) based concepts have been introduced for the prostate's automatic segmentation and its coarse subdivision into transition zone (TZ) and peripheral zone (PZ). However, when targeting a fine-grained segmentation of TZ, PZ, distal prostatic urethra (DPU) and the anterior fibromuscular stroma (AFS), the task becomes more challenging and has not yet been solved at the level of human performance. One reason might be the insufficient amount of labeled data for supervised training. Therefore, we propose to apply a semi-supervised learning (SSL) technique named uncertainty-aware temporal self-learning (UATS) to overcome the expensive and time-consuming manual ground truth labeling. We combine the SSL techniques temporal ensembling and uncertainty-guided self-learning to benefit from unlabeled images, which are often readily available. Our method significantly outperforms the supervised baseline and obtained a Dice coefficient (DC) of up to 78.9%, 87.3%, 75.3%, 50.6% for TZ, PZ, DPU and AFS, respectively. The obtained results are in the range of human inter-rater performance for all structures. Moreover, we investigate the method's robustness against noise and demonstrate the generalization capability for varying ratios of labeled data and on other challenging tasks, namely the hippocampus and skin lesion segmentation. UATS achieved superiority segmentation quality compared to the supervised baseline, particularly for minimal amounts of labeled data.

Automatic prostate and prostate zones segmentation of magnetic resonance images using DenseNet-like U-net.

Magnetic resonance imaging (MRI) provides detailed anatomical images of the prostate and its zones. It has a crucial role for many diagnostic applications. Automatic segmentation such as that of the prostate and prostate zones from MR images facilitates many diagnostic and therapeutic applications. However, the lack of a clear prostate boundary, prostate tissue heterogeneity, and the wide interindividual variety of prostate shapes make this a very challenging task. To address this problem, we propose a new neural network to automatically segment the prostate and its zones. We term this algorithm Dense U-net as it is inspired by the two existing state-of-the-art tools-DenseNet and U-net. We trained the algorithm on 141 patient datasets and tested it on 47 patient datasets using axial T2-weighted images in a four-fold cross-validation fashion. The networks were trained and tested on weakly and accurately annotated masks separately to test the hypothesis that the network can learn even when the labels are not accurate. The network successfully detects the prostate region and segments the gland and its zones. Compared with U-net, the second version of our algorithm, Dense-2 U-net, achieved an average Dice score for the whole prostate of 92.1± 0.8% vs. 90.7 ± 2%, for the central zone of [Formula: see text]% vs. [Formula: see text] %, and for the peripheral zone of 78.1± 2.5% vs. [Formula: see text]%. Our initial results show Dense-2 U-net to be more accurate than state-of-the-art U-net for automatic segmentation of the prostate and prostate zones.

Applying deep learning to single-trial EEG data provides evidence for complementary theories on action control.

Efficient action control is indispensable for goal-directed behaviour. Different theories have stressed the importance of either attention or response selection sub-processes for action control. Yet, it is unclear to what extent these processes can be identified in the dynamics of neurophysiological (EEG) processes at the single-trial level and be used to predict the presence of conflicts in a given moment. Applying deep learning, which was blind to cognitive theory, on single-trial EEG data allowed to predict the presence of conflict in ~95% of subjects ~33% above chance level. Neurophysiological features related to attentional and motor response selection processes in the occipital cortex and the superior frontal gyrus contributed most to prediction accuracy. Importantly, deep learning was able to identify predictive neurophysiological processes in single-trial neural dynamics. Hence, mathematical (artificial intelligence) approaches may be used to foster the validation and development of links between cognitive theory and neurophysiology of human behavior.

Deep Learning Based on Event-Related EEG Differentiates Children with ADHD from Healthy Controls.

Attention Deficit Hyperactivity Disorder (ADHD) is one of the most prevalent neuropsychiatric disorders in childhood and adolescence and its diagnosis is based on clinical interviews, symptom questionnaires, and neuropsychological testing. Much research effort has been undertaken to evaluate the usefulness of neurophysiological (EEG) data to aid this diagnostic process. In the current study, we applied deep learning methods on event-related EEG data to examine whether it is possible to distinguish ADHD patients from healthy controls using purely neurophysiological measures. The same was done to distinguish between ADHD subtypes. The results show that the applied deep learning model ("EEGNet") was able to distinguish between both ADHD subtypes and healthy controls with an accuracy of up to 83%. However, a significant fraction of individuals could not be classified correctly. It is shown that neurophysiological processes indicating attentional selection associated with superior parietal cortical areas were the most important for that. Using the applied deep learning method, it was not possible to distinguish ADHD subtypes from each other. This is the first study showing that deep learning methods applied to EEG data are able to dissociate between ADHD patients and healthy controls. The results show that the applied method reflects a promising means to support clinical diagnosis in ADHD. However, more work needs to be done to increase the reliability of the taken approach.

Moving Beyond ERP Components: A Selective Review of Approaches to Integrate EEG and Behavior.

Relationships between neuroimaging measures and behavior provide important clues about brain function and cognition in healthy and clinical populations. While electroencephalography (EEG) provides a portable, low cost measure of brain dynamics, it has been somewhat underrepresented in the emerging field of model-based inference. We seek to address this gap in this article by highlighting the utility of linking EEG and behavior, with an emphasis on approaches for EEG analysis that move beyond focusing on peaks or "components" derived from averaging EEG responses across trials and subjects (generating the event-related potential, ERP). First, we review methods for deriving features from EEG in order to enhance the signal within single-trials. These methods include filtering based on user-defined features (i.e., frequency decomposition, time-frequency decomposition), filtering based on data-driven properties (i.e., blind source separation, BSS), and generating more abstract representations of data (e.g., using deep learning). We then review cognitive models which extract latent variables from experimental tasks, including the drift diffusion model (DDM) and reinforcement learning (RL) approaches. Next, we discuss ways to access associations among these measures, including statistical models, data-driven joint models and cognitive joint modeling using hierarchical Bayesian models (HBMs). We think that these methodological tools are likely to contribute to theoretical advancements, and will help inform our understandings of brain dynamics that contribute to moment-to-moment cognitive function.

Toward Studying Music Cognition with Information Retrieval Techniques: Lessons Learned from the OpenMIIR Initiative.

As an emerging sub-field of music information retrieval (MIR), music imagery information retrieval (MIIR) aims to retrieve information from brain activity recorded during music cognition-such as listening to or imagining music pieces. This is a highly inter-disciplinary endeavor that requires expertise in MIR as well as cognitive neuroscience and psychology. The OpenMIIR initiative strives to foster collaborations between these fields to advance the state of the art in MIIR. As a first step, electroencephalography (EEG) recordings of music perception and imagination have been made publicly available, enabling MIR researchers to easily test and adapt their existing approaches for music analysis like fingerprinting, beat tracking or tempo estimation on this new kind of data. This paper reports on first results of MIIR experiments using these OpenMIIR datasets and points out how these findings could drive new research in cognitive neuroscience.