Diagnostic efficacy of combining diffusion-weighted magnetic resonance imaging with serum Mucin 1, Mucin 13, and Mucin 16 in distinguishing borderline from malignant epithelial ovarian tumors.

AIMS: To enhance ovarian tumor diagnosis beyond conventional methods, this study explored combining diffusion-weighted magnetic resonance imaging (DWI-MRI) and serum biomarkers (Mucin 1 [MUC1], MUC13, and MUC16) for distinguishing borderline from malignant epithelial ovarian tumors. METHODS: A total of 126 patients, including 71 diagnosed with borderline (BEOTs) and 55 with malignant epithelial ovarian tumors (MEOTs), underwent preoperative DWI-MRI. Region of interest (ROI) was manually drawn along the solid component's boundary of the largest tumor, focusing on areas with potentially the lowest apparent diffusion coefficient (ADC). For entirely cystic tumors, a free-form ROI enclosed the maximum number of septa while targeting the lowest ADC. Serum biomarkers were determined using enzyme-linked immunosorbent assay. RESULTS: Basic morphological traits proved inadequate for malignancy diagnosis, warranting this investigation. BEOTs had an ADC mean of (1.670 ± 0.250) × 103 mm2 /s, while MEOTs had a lower ADC mean of (1.332 ± 0.481) × 103 mm2 /s, with a sensitivity of 63.6% and specificity of 90.1%. Median MUC1 (167.0 U/mL vs. 87.3 U/mL), MUC13 (12.44 ng/mL vs. 7.77 ng/mL), and MUC16 (180.6 U/mL vs. 36.1 U/mL) levels were higher in MEOTs patients. The biomarker performance was: MUC1, sensitivity 50.9%, specificity 100%; MUC13, sensitivity 56.4%, specificity 78.9%; MUC16, sensitivity 83.64%, specificity 100%. Combining serum biomarkers and ADC mean resulted in a sensitivity of 96.4% and specificity of 100%. CONCLUSION: The integration of DWI-MRI with serum biomarkers (MUC1, MUC13, and MUC16) achieves exceptional diagnostic accuracy, offering a powerful tool for the precise differentiation between borderline and malignant epithelial ovarian tumors.

Graph Reasoning Module for Alzheimer's Disease Diagnosis: A Plug-and-Play Method.

Recent advances in deep learning have led to increased adoption of convolutional neural networks (CNN) for structural magnetic resonance imaging (sMRI)-based Alzheimer's disease (AD) detection. AD results in widespread damage to neurons in different brain regions and destroys their connections. However, current CNN-based methods struggle to relate spatially distant information effectively. To solve this problem, we propose a graph reasoning module (GRM), which can be directly incorporated into CNN-based AD detection models to simulate the underlying relationship between different brain regions and boost AD diagnosis performance. Specifically, in GRM, an adaptive graph Transformer (AGT) block is designed to adaptively construct a graph representation based on the feature map given by CNN, a graph convolutional network (GCN) block is adopted to update the graph representation, and a feature map reconstruction (FMR) block is built to convert the learned graph representation to a feature map. Experimental results demonstrate that the insertion of the GRM in the existing AD classification model can increase its balanced accuracy by more than 4.3%. The GRM-embedded model achieves state-of-the-art performance compared with current deep learning-based AD diagnosis methods, with a balanced accuracy of 86.2%.

Controllable Fabrication of Vertical Graphene with Tunable Growth Nature by Remote Plasma-Enhanced Chemical Vapor Deposition.

As an important member of the graphene family, vertical graphene (VG) has broad applications like field emission, energy storage, and sensors owing to its fascinating physical and chemical properties. Among various fabrication methods for VG, plasma enhanced chemical vapor deposition (PECVD) is most employed because of the fast growth rate at relatively low temperature for the high-quality VG. However, to date, relations between growth manner of VG and growth parameters such as growth temperature, dosage of gaseous carbon source, and electric power to generate plasma are still less known, which in turn hinder the massive production of VG for further applications. In this study, the growth behavior of VG was studied as functions of temperature, plasma power, and gas composition (or chamber pressure). It was found that the growth behavior of VG is sensitive to the growth conditions mentioned above. Although conditions with high growth temperature, large flow rate of mixed gas of methane and carrier gases, and high plasma power may be helpful for the fast growth of VG, brunching of VG is simultaneously enhanced, which in turn decreases the vertical growth nature of VG. High-quality VG can be achieved by optimizing the growth parameters. It was revealed that the vertical growth nature of VG is governed by the electric field at the interfacial layer between VG and the substrate, for which its strength is influenced by the density of plasma. These findings are important for the general understanding of the VG growth and provided a feasible way for the controllable fabrication of VG using the remote PECVD method which is usually believed to be unsuitable for the fabrication of VG.

Comparing Multi-Dimensional fNIRS Features Using Bayesian Optimization-Based Neural Networks for Mild Cognitive Impairment (MCI) Detection.

The diagnosis of mild cognitive impairment (MCI), a prodromal stage of Alzheimer's disease (AD), is essential for initiating timely treatment to delay the onset of AD. Previous studies have shown the potential of functional near-infrared spectroscopy (fNIRS) for diagnosing MCI. However, preprocessing fNIRS measurements requires extensive experience to identify poor-quality segments. Moreover, few studies have explored how proper multi-dimensional fNIRS features influence the classification results of the disease. Thus, this study outlined a streamlined fNIRS preprocessing method to process fNIRS measurements and compared multi-dimensional fNIRS features with neural networks in order to explore how temporal and spatial factors affect the classification of MCI and cognitive normality. More specifically, this study proposed using Bayesian optimization-based auto hyperparameter tuning neural networks to evaluate 1D channel-wise, 2D spatial, and 3D spatiotemporal features of fNIRS measurements for detecting MCI patients. The highest test accuracies of 70.83%, 76.92%, and 80.77% were achieved for 1D, 2D, and 3D features, respectively. Through extensive comparisons, the 3D time-point oxyhemoglobin feature was proven to be a more promising fNIRS feature for detecting MCI by using an fNIRS dataset of 127 participants. Furthermore, this study presented a potential approach for fNIRS data processing, and the designed models required no manual hyperparameter tuning, which promoted the general utilization of fNIRS modality with neural network-based classification to detect MCI.

Learning Skill Characteristics From Manipulations.

Percutaneous coronary intervention (PCI) has increasingly become the main treatment for coronary artery disease. The procedure requires high experienced skills and dexterous manipulations. However, there are few techniques to model PCI skill so far. In this study, a learning framework with local and ensemble learning is proposed to learn skill characteristics of different skill-level subjects from their PCI manipulations. Ten interventional cardiologists (four experts and six novices) were recruited to deliver a medical guidewire to two target arteries on a porcine model for in vivo studies. Simultaneously, translation and twist manipulations of thumb, forefinger, and wrist are acquired with electromagnetic (EM) and fiber-optic bend (FOB) sensors, respectively. These behavior data are then processed with wavelet packet decomposition (WPD) under 1-10 levels for feature extraction. The feature vectors are further fed into three candidate individual classifiers in the local learning layer. Furthermore, the local learning results from different manipulation behaviors are fused in the ensemble learning layer with three rule-based ensemble learning algorithms. In subject-dependent skill characteristics learning, the ensemble learning can achieve 100% accuracy, significantly outperforming the best local result (90%). Furthermore, ensemble learning can also maintain 73% accuracy in subject-independent schemes. These promising results demonstrate the great potential of the proposed method to facilitate skill learning in surgical robotics and skill assessment in clinical practice.

Brown Adipose Tissue and Novel Management Strategies for Polycystic Ovary Syndrome Therapy.

Brown adipose tissue (BAT), a unique tissue, plays a key role in metabolism and energy expenditure through adaptive nonshivering thermogenesis. It has recently become a therapeutic target in the treatment of obesity and metabolic diseases. The thermogenic effect of BAT occurs through uncoupling protein-1 by uncoupling adenosine triphosphate (ATP) synthesis from energy substrate oxidation. The review discusses the recent developments and progress associated with the biology, function, and activation of BAT, with a focus on its therapeutic potential for the treatment of polycystic ovary syndrome (PCOS). The endocrine activity of brown adipocytes affects the energy balance and homeostasis of glucose and lipids, thereby affecting the association of BAT activity and the metabolic profile. PCOS is a complex reproductive and metabolic disorder of reproductive-age women. Functional abnormalities of adipose tissue (AT) have been reported in patients with PCOS. Numerous studies have shown that BAT could regulate the features of PCOS and that increases in BAT mass or activity were effective in the treatment of PCOS through approaches including cold stimulation, BAT transplantation and compound activation in various animal models. Therefore, BAT may be used as a novel management strategy for the patients with PCOS to improve women's health clinically. It is highly important to identify key brown adipokines for the discovery and development of novel candidates to establish an efficacious therapeutic strategy for patients with PCOS in the future.

TR-GAN: Multi-Session Future MRI Prediction With Temporal Recurrent Generative Adversarial Network.

Magnetic Resonance Imaging (MRI) has been proven to be an efficient way to diagnose Alzheimer's disease (AD). Recent dramatic progress on deep learning greatly promotes the MRI analysis based on data-driven CNN methods using a large-scale longitudinal MRI dataset. However, most of the existing MRI datasets are fragmented due to unexpected quits of volunteers. To tackle this problem, we propose a novel Temporal Recurrent Generative Adversarial Network (TR-GAN) to complete missing sessions of MRI datasets. Unlike existing GAN-based methods, which either fail to generate future sessions or only generate fixed-length sessions, TR-GAN takes all past sessions to recurrently and smoothly generate future ones with variant length. Specifically, TR-GAN adopts recurrent connection to deal with variant input sequence length and flexibly generate future variant sessions. Besides, we also design a multiple scale & location (MSL) module and a SWAP module to encourage the model to better focus on detailed information, which helps to generate high-quality MRI data. Compared with other popular GAN architectures, TR-GAN achieved the best performance in all evaluation metrics of two datasets. After expanding the Whole MRI dataset, the balanced accuracy of AD vs. cognitively normal (CN) vs. mild cognitive impairment (MCI) and stable MCI vs. progressive MCI classification can be increased by 3.61% and 4.00%, respectively.

Bilinear neural network with 3-D attention for brain decoding of motor imagery movements from the human EEG.

Deep learning has achieved great success in areas such as computer vision and natural language processing. In the past, some work used convolutional networks to process EEG signals and reached or exceeded traditional machine learning methods. We propose a novel network structure and call it QNet. It contains a newly designed attention module: 3D-AM, which is used to learn the attention weights of EEG channels, time points, and feature maps. It provides a way to automatically learn the electrode and time selection. QNet uses a dual branch structure to fuse bilinear vectors for classification. It performs four, three, and two classes on the EEG Motor Movement/Imagery Dataset. The average cross-validation accuracy of 65.82%, 74.75%, and 82.88% was obtained, which are 7.24%, 4.93%, and 2.45% outperforms than the state-of-the-art, respectively. The article also visualizes the attention weights learned by QNet and shows its possible application for electrode channel selection.