Single-source domain generalization (SDG) in medical image segmentation (MIS) aims to generalize a model using only one source domain data to segment data from an unseen target domain. Despite substantial advances in SDG with data augmentation, existing methods often fail to fully consider the details and uncertain areas prevalent in MIS, leading to mis-segmentation. In this study, we propose a Fourier-based semantic augmentation method called FIESTA using uncertainty guidance (UG) to enhance the fundamental goals of MIS in an SDG context by manipulating the amplitude and phase components in the frequency domain. The proposed Fourier augmentative transformer (FAT) addresses semantic amplitude modulation based on meaningful angular points to induce pertinent variations and harnesses the phase spectrum to ensure structural coherence. Moreover, FIESTA employs uncertainty estimation to fine-tune the augmentation process, improving the ability of the model to adapt to diverse augmented data and concentrate on areas with higher ambiguity. Extensive experiments across three cross-domain scenarios demonstrate that FIESTA surpasses recent state-of-the-art SDG approaches in segmentation performance and significantly contributes to boosting the model's applicability in medical imaging modalities.

Dynamic treatment regimes (DTRs), which comprise a series of decisions taken to select adequate treatments, have attracted considerable attention in the clinical domain, especially from sepsis researchers. Existing sepsis DTR learning studies are mainly based on offline reinforcement learning (RL) approaches working on electronic healthcare records data. However, a trained policy may choose a treatment different from a human clinician's prescription. Furthermore, most of them do not consider: 1) heterogeneity in sepsis; 2) short-term transitions; and 3) the relationship between a patient's health state and the prescription. We propose a novel framework, an adaptive decision transformer for DTR (ADT2R), which recommends an optimal treatment action for each time step depending on the heterogeneity of the sepsis and a patient's evolving health states. Specifically, we devise a trajectory-optimization-based module to be trained with supervision for treatments and adaptively aggregate the multihead self-attentions by deliberating on various inherent time-varying patterns among sepsis patients. Furthermore, we estimate the patient's health state by adopting an actor-critic (AC) algorithm and inform the treatment recommendation by learning about its short-term changes. We validated the effectiveness of the proposed framework on the Medical Information Mart for Intensive Care III (MIMIC-III) dataset, an extensive intensive care database, by demonstrating performance comparable to the state-of-the-art methods.

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.

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.

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.

Sleep staging is essential for sleep assessment and plays a vital role as one of the health indicators. It is challenging to correctly classify stage-transitioning epochs of sleep electroencephalography (EEG) because of their mixed signals of stages. To this end, recent studies exploited and devised various deep learning architectures. However, those are still suffering from confusing two or more stages, especially in stage-transitioning epochs. In this work, we propose a novel network architecture that takes advantage of two auxiliary classification tasks and exploits their outputs to adapt feature representations, thus effectively discriminating confusing stages. Specifically, one auxiliary task is an epoch-level stage classification to produce confidence scores about stages. The other is a stage-transition detection to learn inter-epoch relations. Using inferred information about stage-confusion at an epoch level and stage-transition across neighboring epochs helps learn more concrete representations for stage identification. We demonstrated and analyzed the validity of our proposed method over two publicly available datasets, achieving promising performances.

In this article, we formulate the problem of estimating and selecting task-relevant temporal signal segments from a single electroencephalogram (EEG) trial in the form of a Markov decision process and propose a novel reinforcement-learning mechanism that can be combined with the existing deep-learning-based brain–computer interface methods. To be specific, we devise an actor–critic network such that an agent can determine which timepoints need to be used (informative) or discarded (uninformative) in composing the intention-related features in a given trial, and thus enhancing the intention identification performance. To validate the effectiveness of our proposed method, we conduct experiments with a publicly available big motor imagery (MI) dataset and apply our novel mechanism to various recent deep-learning architectures designed for MI classification. Based on the exhaustive experiments, we observe that our proposed method helped achieve statistically significant improvements in performance.

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.

Recently, deep learning, a branch of machine learning and data mining, has gained widespread acceptance in many applications thanks to its unprecedented successes. In this regard, pioneering studies employed deep learning frameworks for imaging genetics in virtue of their own representation caliber. But, existing approaches suffer from some limitations: (i) exploiting a simple concatenation strategy for joint analysis, (ii) a lack of extension to biomedical applications, and (iii) insufficient and inappropriate interpretations in the viewpoint of both data science and bio-neuroscience. In this work, we propose a novel deep learning framework to tackle the aforementioned issues simultaneously. Our proposed framework learns to effectively represent the neuroimaging and the genetic data jointly, and achieves state-of-the-art performance in its use for Alzheimer’s disease and mild cognitive impairment identification. Further, unlike the existing methods in the literature, the framework allows 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 a great potential to give new insights and perspectives in deep learning-based imaging genetics studies.