EAG-RS: A Novel Explainability-Guided ROI-Selection Framework for ASD Diagnosis via Inter-Regional Relation Learning.

Deep learning models based on resting-state functional magnetic resonance imaging (rs-fMRI) have been widely used to diagnose brain diseases, particularly autism spectrum disorder (ASD). Existing studies have leveraged the functional connectivity (FC) of rs-fMRI, achieving notable classification performance. However, they have significant limitations, including the lack of adequate information while using linear low-order FC as inputs to the model, not considering individual characteristics (i.e., different symptoms or varying stages of severity) among patients with ASD, and the non-explainability of the decision process. To cover these limitations, we propose a novel explainability-guided region of interest (ROI) selection (EAG-RS) framework that identifies non-linear high-order functional associations among brain regions by leveraging an explainable artificial intelligence technique and selects class-discriminative regions for brain disease identification. The proposed framework includes three steps: (i) inter-regional relation learning to estimate non-linear relations through random seed-based network masking, (ii) explainable connection-wise relevance score estimation to explore high-order relations between functional connections, and (iii) non-linear high-order FC-based diagnosis-informative ROI selection and classifier learning to identify ASD. We validated the effectiveness of our proposed method by conducting experiments using the Autism Brain Imaging Database Exchange (ABIDE) dataset, demonstrating that the proposed method outperforms other comparative methods in terms of various evaluation metrics. Furthermore, we qualitatively analyzed the selected ROIs and identified ASD subtypes linked to previous neuroscientific studies.

Module of Axis-based Nexus Attention for weakly supervised object localization.

Weakly supervised object localization tasks remain challenging to identify and segment an entire object rather than only discriminative parts of the object. To tackle this problem, corruption-based approaches have been devised, which involve the training of non-discriminative regions by corrupting (e.g., erasing) the input images or intermediate feature maps. However, this approach requires an additional hyperparameter, the corrupting threshold, to determine the degree of corruption and can unfavorably disrupt training. It also tends to localize object regions coarsely. In this paper, we propose a novel approach, Module of Axis-based Nexus Attention (MoANA), which helps to adaptively activate less discriminative regions along with the class-discriminative regions without an additional hyperparameter, and elaborately localizes an entire object. Specifically, MoANA consists of three mechanisms (1) triple-view attentions representation, (2) attentions expansion, and (3) features calibration mechanism. Unlike other attention-based methods that train a coarse attention map with the same values across elements in feature maps, MoANA trains fine-grained values in an attention map by assigning different attention values to each element. We validated MoANA by comparing it with various methods. We also analyzed the effect of each component in MoANA and visualized attention maps to provide insights into the calibration.

Mutual Information-Driven Subject-Invariant and Class-Relevant Deep Representation Learning in BCI.

In recent years, deep learning-based feature representation methods have shown a promising impact on electroencephalography (EEG)-based brain-computer interface (BCI). Nonetheless, owing to high intra- and inter-subject variabilities, many studies on decoding EEG were designed in a subject-specific manner by using calibration samples, with no concern of its practical use, hampered by time-consuming steps and a large data requirement. To this end, recent studies adopted a transfer learning strategy, especially domain adaptation techniques. Among those, we have witnessed the potential of adversarial learning-based transfer learning in BCIs. In the meantime, it is known that adversarial learning-based domain adaptation methods are prone to negative transfer that disrupts learning generalized feature representations, applicable to diverse domains, for example, subjects or sessions in BCIs. In this article, we propose a novel framework that learns class-relevant and subject-invariant feature representations in an information-theoretic manner, without using adversarial learning. To be specific, we devise two operational components in a deep network that explicitly estimate mutual information between feature representations: 1) to decompose features in an intermediate layer into class-relevant and class-irrelevant ones and 2) to enrich class-discriminative feature representation. On two large EEG datasets, we validated the effectiveness of our proposed framework by comparing with several comparative methods in performance. Furthermore, we conducted rigorous analyses by performing an ablation study in regard to the components in our network, explaining our model's decision on input EEG signals via layer-wise relevance propagation, and visualizing the distribution of learned features via t-SNE.

TransSleep: Transitioning-Aware Attention-Based Deep Neural Network for Sleep Staging.

Sleep staging is essential for sleep assessment and plays a vital role as a health indicator. Many recent studies have devised various machine/deep learning methods for sleep staging. However, two key challenges hinder the practical use of those methods: 1) effectively capturing salient waveforms in sleep signals and 2) correctly classifying confusing stages in transitioning epochs. In this study, we propose a novel deep neural-network structure, TransSleep, that captures distinctive local temporal patterns and distinguishes confusing stages using two auxiliary tasks. In particular, TransSleep captures salient waveforms in sleep signals by an attention-based multiscale feature extractor and correctly classifies confusing stages in transitioning epochs, while modeling contextual relationships with two auxiliary tasks. Results show that TransSleep achieves promising performance in automatic sleep staging. The validity of TransSleep is demonstrated by its state-of-the-art performance on two publicly available datasets: 1) Sleep-EDF and 2) MASS. Furthermore, we performed ablations to analyze our results from different perspectives. Based on our overall results, we believe that TransSleep has immense potential to provide new insights into deep-learning-based sleep staging.

A Deep Generative-Discriminative Learning for Multimodal Representation in Imaging Genetics.

Imaging genetics, one of the foremost emerging topics in the medical imaging field, analyzes the inherent relations between neuroimaging and genetic data. As deep learning has gained widespread acceptance in many applications, pioneering studies employed deep learning frameworks for imaging genetics. However, existing approaches suffer from some limitations. First, they often adopt a simple strategy for joint learning of phenotypic and genotypic features. Second, their findings have not been extended to biomedical applications, e.g., degenerative brain disease diagnosis and cognitive score prediction. Finally, existing studies perform insufficient and inappropriate analyses from the perspective of data science and neuroscience. In this work, we propose a novel deep learning framework to simultaneously tackle the aforementioned issues. Our proposed framework learns to effectively represent the neuroimaging and the genetic data jointly, and achieves state-of-the-art performance when used for Alzheimer's disease and mild cognitive impairment identification. Furthermore, unlike the existing methods, the framework enables learning the relation between imaging phenotypes and genotypes in a nonlinear way without any prior neuroscientific knowledge. To demonstrate the validity of our proposed framework, we conducted experiments on a publicly available dataset and analyzed the results from diverse perspectives. Based on our experimental results, we believe that the proposed framework has immense potential to provide new insights and perspectives in deep learning-based imaging genetics studies.

Semi-supervised generative and discriminative adversarial learning for motor imagery-based brain-computer interface.

Convolutional neural networks (CNNs), which can recognize structural/configuration patterns in data with different architectures, have been studied for feature extraction. However, challenges remain regarding leveraging advanced deep learning methods in BCIs. We focus on problems of small-sized training samples and interpretability of the learned parameters and leverages a semi-supervised generative and discriminative learning framework that effectively utilizes synthesized samples with real samples to discover class-discriminative features. Our framework learns the distributional characteristics of EEG signals in an embedding space using a generative model. By using artificially generated and real EEG signals, our framework finds class-discriminative spatio-temporal feature representations that help to correctly discriminate input EEG signals. It is noteworthy that the framework facilitates the exploitation of real, unlabeled samples to better uncover the underlying patterns inherent in a user's EEG signals. To validate our framework, we conducted experiments comparing our method with conventional linear models by utilizing variants of three existing CNN architectures as generator networks and measuring the performance on three public datasets. Our framework exhibited statistically significant improvements over the competing methods. We investigated the learned network via activation pattern maps and visualized generated artificial samples to empirically justify the stability and neurophysiological plausibility of our model.

Development of the Korea-Polyenvironmental Risk Score for Psychosis.

OBJECTIVE: Comprehensive understanding of polyenvironmental risk factors for the development of psychosis is important. Based on a review of related evidence, we developed the Korea Polyenvironmental Risk Score (K-PERS) for psychosis. We investigated whether the K-PERS can differentiate patients with schizophrenia spectrum disorders (SSDs) from healthy controls (HCs). METHODS: We reviewed existing tools for measuring polyenvironmental risk factors for psychosis, including the Maudsley Environmental Risk Score (ERS), polyenviromic risk score (PERS), and Psychosis Polyrisk Score (PPS). Using odds ratios and relative risks for Western studies and the "population proportion" (PP) of risk factors for Korean data, we developed the K-PERS, and compared the scores thereon between patients with SSDs and HCs. In addition, correlation was performed between the K-PERS and Positive and Negative Syndrome Scale (PANSS). RESULTS: We first constructed the "K-PERS-I," comprising five factors based on the PPS, and then the "K-PERS-II" comprising six factors based on the ERS. The instruments accurately predicted participants' status (case vs. control). In addition, the K-PERS-I and -II scores exhibited significant negative correlations with the negative symptom factor score of the PANSS. CONCLUSION: The K-PERS is the first comprehensive tool developed based on PP data obtained from Korean studies that measures polyenvironmental risk factors for psychosis. Using pilot data, the K-PERS predicted patient status (SSD vs. HC). Further research is warranted to examine the relationship of K-PERS scores with clinical outcomes of psychosis and schizophrenia.

Elephant genotypes reveal the size and connectivity of transnational ivory traffickers.

Transnational ivory traffickers continue to smuggle large shipments of elephant ivory out of Africa, yet prosecutions and convictions remain few. We identify trafficking networks on the basis of genetic matching of tusks from the same individual or close relatives in separate shipments. Analyses are drawn from 4,320 savannah (Loxodonta africana) and forest (L. cyclotis) elephant tusks, sampled from 49 large ivory seizures totalling 111 t, shipped out of Africa between 2002 and 2019. Network analyses reveal a repeating pattern wherein tusks from the same individual or close relatives are found in separate seizures that were containerized in, and transited through, common African ports. Results suggest that individual traffickers are exporting dozens of shipments, with considerable connectivity between traffickers operating in different ports. These tools provide a framework to combine evidence from multiple investigations, strengthen prosecutions and support indictment and prosecution of transnational ivory traffickers for the totality of their crimes.

A Survey on Deep Learning-Based Short/Zero-Calibration Approaches for EEG-Based Brain-Computer Interfaces.

Brain-computer interfaces (BCIs) utilizing machine learning techniques are an emerging technology that enables a communication pathway between a user and an external system, such as a computer. Owing to its practicality, electroencephalography (EEG) is one of the most widely used measurements for BCI. However, EEG has complex patterns and EEG-based BCIs mostly involve a cost/time-consuming calibration phase; thus, acquiring sufficient EEG data is rarely possible. Recently, deep learning (DL) has had a theoretical/practical impact on BCI research because of its use in learning representations of complex patterns inherent in EEG. Moreover, algorithmic advances in DL facilitate short/zero-calibration in BCI, thereby suppressing the data acquisition phase. Those advancements include data augmentation (DA), increasing the number of training samples without acquiring additional data, and transfer learning (TL), taking advantage of representative knowledge obtained from one dataset to address the so-called data insufficiency problem in other datasets. In this study, we review DL-based short/zero-calibration methods for BCI. Further, we elaborate methodological/algorithmic trends, highlight intriguing approaches in the literature, and discuss directions for further research. In particular, we search for generative model-based and geometric manipulation-based DA methods. Additionally, we categorize TL techniques in DL-based BCIs into explicit and implicit methods. Our systematization reveals advances in the DA and TL methods. Among the studies reviewed herein, ~45% of DA studies used generative model-based techniques, whereas ~45% of TL studies used explicit knowledge transferring strategy. Moreover, based on our literature review, we recommend an appropriate DA strategy for DL-based BCIs and discuss trends of TLs used in DL-based BCIs.

Anti-inflammatory Activity of Saxifragin via Inhibition of NF-κB Involves Caspase-1 Activation.

Saxifragin, the 5-glucoside of the flavonoid quercetin, is found in plants and insects. It has been reported that saxifragin has peroxynitrite-scavenging effects. However, the mechanism of anti-inflammatory effects of saxifragin has not yet been clearly identified. In this study, we investigated the anti-inflammatory effects of saxifragin in lipopolysaccharide (LPS)-stimulated RAW 264.7 macrophages and animal models of inflammation. We found that saxifragin suppressed the production of nitric oxide (NO) and prostaglandin E2 (PGE2) in LPS-activated RAW 264.7 macrophages by suppressing the level of protein and mRNA expression of inducible nitric oxide synthase (iNOS) and cyclooxygenase-2 (COX-2), respectively. Furthermore, saxifragin inhibited mRNA expression of pro-inflammatory cytokines including tumor necrosis factor (TNF)-α, interleukin (IL)-6, and IL-1ß. We studied the inhibitory effects of saxifragin on the nuclear translocation of nuclear factor (NF)-κB, activation of caspase-1, and phosphorylation of c-Jun N-terminal kinase (JNK) and extracellular signal-regulated kinase (ERK). Furthermore, pretreatment with saxifragin increased the survival rate of mice with LPS-induced septic death. Collectively, these findings suggest that saxifragin exerts anti-inflammatory activity by inhibiting NF-κB, caspase-1, and mitogen-activated protein kinase (MAPK) activation.

Analysis of the facial measurements of Korean Air Force pilots for oxygen mask design.

This study measured the facial dimensions of Korean Air Force (KAF) pilots, to design a pilot oxygen mask, and compared them with those of Korean civilians and US Air Force (USAF) personnel. Twenty-two facial dimensions were measured for 278 KAF male pilots (KMP) and 58 KAF female pilots and cadets (KFP) using an anthropometer and a three-dimensional scanner. The KMP face measurements were found to be significantly larger (mean difference, [Formula: see text] = 0.7-26.5 mm) and less varied (ratio of SDs = 0.29-0.82) than those of Korean male civilians. The average face length, lip width and nasal root breadth of the KMP were significantly longer ([Formula: see text] = 4.7 mm), narrower ([Formula: see text] = -2.4 mm), and wider ([Formula: see text] = 5.2 mm), respectively, than those of USAF male personnel. Lastly, the KMP face measurements were significantly larger ([Formula: see text] = 1.8-26.1 mm) than those of the KFP. PRACTITIONER SUMMARY: The face measurements of KAF pilots were collected and compared with those of Korean civilians and USAF personnel. The distinct facial features of the populations identified in this study are applicable to custom design of an oxygen mask for prevention of excessive pressure and oxygen leakage.