Tag: pubmed

IEEE Trans Neural Syst Rehabil Eng. 2025 Jan 16;PP. doi: 10.1109/TNSRE.2025.3530154. Online ahead of print.

ABSTRACT

Assistive wearable devices can significantly enhance the quality of life for individuals with movement impairments, aid the rehabilitation process, and augment movement abilities of healthy users. However, personalizing the assistance to individual preferences and needs remains a challenge. Brain-Computer Interface (BCI) offers a promising solution for this personalization problem. The overarching goal of this study is to investigate the feasibility of utilizing passive BCI technology to personalize the assistance provided by a knee exoskeleton. Participants performed seated knee flexion-extension tasks while wearing a one-degree-of-freedom knee exoskeleton with varying levels of applied force. Their brain activities were recorded throughout the movements using electroencephalography (EEG). EEG spectral bands from several brain regions were compared between the conditions with the lowest and highest exoskeleton forces to identify statistically significant changes. A Naive Bayes classifier was trained on these spectral features to distinguish between the two conditions. Statistical analysis revealed significant increases in δ and θ activity and decreases in α and β activity in the frontal, motor, and occipital cortices. These changes suggest heightened attention, concentration, and motor engagement when the task became more difficult. The trained Naive Bayes classifier achieved an average accuracy of approximately 72% in distinguishing between the two conditions. The outcomes of our study demonstrate the potential of passive BCI in personalizing assistance provided by wearable devices. Future research should further explore integrating passive BCI into assistive wearable devices to enhance user experience.

PMID:40030934 | DOI:10.1109/TNSRE.2025.3530154

IEEE J Biomed Health Inform. 2025 Jan 15;PP. doi: 10.1109/JBHI.2025.3530107. Online ahead of print.

ABSTRACT

Employing a minimal array of electroencephalography (EEG) channels for neonatal sleep stage classification is essential for data acquisition in the Internet of Medical Things (IoMT), as single-channel and edge-based features can reduce data transfer and processing requirements, enhancing cost-effectiveness and practicality. In this paper, we evaluate the efficacy of a single channel and the viability of a binary classification scheme for discerning awake and sleep states and transitions to quiet sleep. For this, two datasets of EEG signals for neonate sleep analysis were recorded from Children’s Hospital of Fudan University, Shanghai, comprising recordings from 64 and 19 neonates, respectively. From each epoch, a diverse ensemble of 490 features was extracted through a blend of discrete and continuous wavelet transforms (DWT, CWT), spectral statistics, and temporal features. In addition, we introduced an innovative hybrid univariate and ensemble feature selection approach with multidomain feature fusion, a stacking-based ensemble classifier that outperforms existing work. We achieved 90.37%, 91.13%, and 94.88% accuracy for sleep/awake, quiet sleep/non-quiet sleep, and quiet sleep/awake, respectively. This was corroborated by significant Kappa values of 77.5%, 80.29%, and 89.76%. Using SelectPercentile, we devised three distinct feature selection mechanisms: one using DWT, one with CWT, and another incorporating both spectral and temporal features. Subsequently, SelectKBest was used to determine the most effective features. For our stacked model, we incorporated a trifecta of the ExtraTree model with variable estimators, a Random Forest, and an Artificial Neural Network (ANN) as base classifiers, and for the final prediction phase, ANN was implemented again. The model’s performance was evaluated using K-fold and leave-one-subject cross-validation.

PMID:40030895 | DOI:10.1109/JBHI.2025.3530107

IEEE Trans Pattern Anal Mach Intell. 2025 Jan 14;PP. doi: 10.1109/TPAMI.2025.3529711. Online ahead of print.

ABSTRACT

Subspace learning and Support Vector Machine (SVM) are two critical techniques in pattern recognition, playing pivotal roles in feature extraction and classification. However, how to learn the optimal subspace such that the SVM classifier can perform the best is still a challenging problem due to the difficulty in optimization, computation, and algorithm convergence. To address these problems, this paper develops a novel method named Optimal Discriminant Support Vector Machine (ODSVM), which integrates support vector classification with discriminative subspace learning in a seamless framework. As a result, the most discriminative subspace and the corresponding optimal SVM are obtained simultaneously to pursue the best classification performance. The efficient optimization framework is designed for binary and multi-class ODSVM. Moreover, a fast sequential minimization optimization (SMO) algorithm with pruning is proposed to accelerate the computation in multi-class ODSVM. Unlike other related methods, ODSVM has a strong theoretical guarantee of global convergence, highlighting its superiority and stability. Numerical experiments are conducted on thirteen datasets and the results demonstrate that ODSVM outperforms existing methods with statistical significance.

PMID:40030888 | DOI:10.1109/TPAMI.2025.3529711

IEEE Trans Pattern Anal Mach Intell. 2025 Jan 6;PP. doi: 10.1109/TPAMI.2024.3523422. Online ahead of print.

ABSTRACT

Recent methods for synthesizing 3D-aware face images have achieved rapid development thanks to neural radiance fields, allowing for high quality and fast inference speed. However, existing solutions for editing facial geometry and appearance independently usually require retraining and are not optimized for the recent work of generation, thus tending to lag behind the generation process. To address these issues, we introduce NeRFFaceEditing, which enables editing and decoupling geometry and appearance in the pretrained tri-plane-based neural radiance field while retaining its high quality and fast inference speed. Our key idea for disentanglement is to use the statistics of the tri-plane to represent the high-level appearance of its corresponding facial volume. Moreover, we leverage a generated 3D-continuous semantic mask as an intermediary for geometry editing. We devise a geometry decoder (whose output is unchanged when the appearance changes) and an appearance decoder. The geometry decoder aligns the original facial volume with the semantic mask volume. We also enhance the disentanglement by explicitly regularizing rendered images with the same appearance but different geometry to be similar in terms of color distribution for each facial component separately. Our method allows users to edit via semantic masks with decoupled control of geometry and appearance. Both qualitative and quantitative evaluations show the superior geometry and appearance control abilities of our method compared to existing and alternative solutions.

PMID:40030881 | DOI:10.1109/TPAMI.2024.3523422

IEEE Trans Med Imaging. 2025 Jan 3;PP. doi: 10.1109/TMI.2024.3525095. Online ahead of print.

ABSTRACT

Unsupervised domain adaptation (UDA) in medical image segmentation aims to improve the generalization of deep models by alleviating domain gaps caused by inconsistency across equipment, imaging protocols, and patient conditions. However, existing UDA works remain insufficiently explored and present great limitations: (i) Exhibit cumbersome designs that prioritize aligning statistical metrics and distributions, which limits the model’s flexibility and generalization while also overlooking the potential knowledge embedded in unlabeled data; (ii) More applicable in a certain domain, lack the generalization capability to handle diverse shifts encountered in clinical scenarios. To overcome these limitations, we introduce MedCon, a unified framework that leverages general unsupervised contrastive pre-training to establish domain connections, effectively handling diverse domain shifts without tailored adjustments. Specifically, it initially explores a general contrastive pre-training to establish domain connections by leveraging the rich prior knowledge from unlabeled images. Thereafter, the pre-trained backbone is fine-tuned using source-based images to ultimately identify per-pixel semantic categories. To capture both intra- and inter-domain connections of anatomical structures, we construct positive-negative pairs from a hybrid aspect of both local and global scales. In this regard, a shared-weight encoder-decoder is employed to generate pixel-level representations, which are then mapped into hyper-spherical space using a non-learnable projection head to facilitate positive pair matching. Comprehensive experiments on diverse medical image datasets confirm that MedCon outperforms previous methods by effectively managing a wide range of domain shifts and showcasing superior generalization capabilities.

PMID:40030864 | DOI:10.1109/TMI.2024.3525095

IEEE Trans Haptics. 2024 Dec 26;PP. doi: 10.1109/TOH.2024.3522897. Online ahead of print.

ABSTRACT

In recent years, systems that utilize immersive space have been developed in various fields. Immersive spaces often contain considerable amounts of visual information; therefore, users often fail to obtain their desired information. Therefore, various methods have been developed to guide users toward haptic sensations. However, many of these methods have limitations in terms of the intuitive perception of haptic sensation and require practice for familiarization with haptic sensation. Fabric actuators are wearable haptic devices that combine fabric and McKibben artificial muscles to provide wearers with surface haptic sensation. These sensations can be provided to a wide area of the body with intuitive perception, instead of only to a part of the body. This paper presents a novel air pressure adjustment method for whole-body motion guidance using surface haptic sensations provided by a wearable fabric actuator. The proposed system can provide users with a directional sense without visual information in an immersive space. The effectiveness of the proposed system was evaluated through subject experiments and statistical data analysis. Finally, a directional sense presentation was conducted for users performing micromanipulations in a mixed-reality space to demonstrate the applicability of the proposed system for teleoperation.

PMID:40030816 | DOI:10.1109/TOH.2024.3522897

IEEE Trans Med Imaging. 2024 Dec 26;PP. doi: 10.1109/TMI.2024.3523319. Online ahead of print.

ABSTRACT

Learning a generalizable medical image segmentation model is an important but challenging task since the unseen (testing) domains may have significant discrepancies from seen (training) domains due to different vendors and scanning protocols. Existing segmentation methods, typically built upon domain generalization (DG), aim to learn multi-source domain-invariant features through data or feature augmentation techniques, but the resulting models either fail to characterize global domains during training or cannot sense unseen domain information during testing. To tackle these challenges, we propose a domain Unifying and Adapting network (UniAda) for generalizable medical image segmentation, a novel “unifying while training, adapting while testing” paradigm that can learn a domain-aware base model during training and dynamically adapt it to unseen target domains during testing. First, we propose to unify the multi-source domains into a global inter-source domain via a novel feature statistics update mechanism, which can sample new features for the unseen domains, facilitating the training of a domain base model. Second, we leverage the uncertainty map to guide the adaptation of the trained model for each testing sample, considering the specific target domain may be outside the global inter-source domain. Extensive experimental results on two public cross-domain medical datasets and one inhouse cross-domain dataset demonstrate the strong generalization capacity of the proposed UniAda over state-of-the-art DG methods. The source code of our UniAda is available at https://github.com/ZhouZhang233/UniAda.

PMID:40030769 | DOI:10.1109/TMI.2024.3523319

IEEE Trans Neural Netw Learn Syst. 2025 Jan 1;PP. doi: 10.1109/TNNLS.2024.3521056. Online ahead of print.

ABSTRACT

Data markets facilitate decentralized data exchange for applications such as prediction, learning, or inference. The design of these markets is challenged by varying privacy preferences and data similarity among data owners. Related works have often overlooked how data similarity impacts pricing and data value through statistical information leakage. We demonstrate that data similarity and privacy preferences are integral to market design and propose a query-response protocol using local differential privacy (LDP) for a two-party data acquisition mechanism. In our regression data market model, we analyze strategic interactions between privacy-aware owners and the learner as a Stackelberg game over the asked price and privacy factor. Finally, we numerically evaluate how data similarity affects market participation and traded data value.

PMID:40030760 | DOI:10.1109/TNNLS.2024.3521056

IEEE Trans Biomed Eng. 2024 Dec 26;PP. doi: 10.1109/TBME.2024.3512572. Online ahead of print.

ABSTRACT

Microwave imaging has been proposed for breast cancer detection and treatment monitoring. The introduction of new approaches or next-generation prototype systems requires characterization of expected variability when scanning participants over clinically relevant timeframes.

OBJECTIVE: The objective of this study is to quantify the reliability and variability in scans of a group of 35 volunteers collected at multiple time points with a next-generation microwave imaging system.

METHODS: Multiple scans of the same volunteer are collected both during one visit and over multiple visits. Test-retest reliability and variability in measurements are investigated for the average permittivity of breast tissues.

RESULTS: The average permittivity for each volunteer exhibited similarity during and between sessions, with some variation noted for smaller breast sizes. The average properties of right and left breasts were also similar. Reliability was demonstrated with the intra-class correlation coefficient (ICC) values statistically greater than 0.9 both within and between sessions. Variability of the measurement was typically less than one unit and coefficient of variation less than 5% (within sessions) or 6% (between sessions).

CONCLUSION: The microwave imaging system exhibits excellent reliability when scanning volunteers multiple times during one session and between sessions. This study represents the largest group of participants scanned at multiple time points reported to date.

SIGNIFICANCE: The excellent reliability demonstrated in this study suggests that microwave breast imaging has strong potential for capturing changes over time, such as treatment or therapy related effects, along with detecting changes in breast tissues.

PMID:40030750 | DOI:10.1109/TBME.2024.3512572

IEEE Trans Pattern Anal Mach Intell. 2024 Dec 17;PP. doi: 10.1109/TPAMI.2024.3519420. Online ahead of print.

ABSTRACT

In this article, we propose a new method of representing and analyzing music audio records. The method is based on the concept of the trajectory of fifths, which was initially developed for the analysis of music represented in MIDI format. To adapt this concept to the needs of audio signal processing, we implement a short-term spectral analysis of a musical piece, followed by a mapping of its subsequent spectral timeframes onto signatures of fifths reflecting relative intensities of sounds associated with each of the 12 pitch classes. Subsequently, the calculation of the characteristic points of the consecutive signatures of fifths enables the creation of the trajectory of fifths. The results of the experiments and statistical analysis conducted in a set of 8996 audio music pieces belonging to 10 genres indicate that this kind of trajectory, just as its MIDI-compliant precursor, is a source of valuable information (i.e., feature coefficients) concerning the harmonic structure of music, which may find use in audio music classification processes.

PMID:40030732 | DOI:10.1109/TPAMI.2024.3519420