TractGeoNet: A geometric deep learning framework for pointwise analysis of tract microstructure to predict language assessment performance.

We propose a geometric deep-learning-based framework, TractGeoNet, for performing regression using diffusion magnetic resonance imaging (dMRI) tractography and associated pointwise tissue microstructure measurements. By employing a point cloud representation, TractGeoNet can directly utilize tissue microstructure and positional information from all points within a fiber tract without the need to average or bin data along the streamline as traditionally required by dMRI tractometry methods. To improve regression performance, we propose a novel loss function, the Paired-Siamese Regression loss, which encourages the model to focus on accurately predicting the relative differences between regression label scores rather than just their absolute values. In addition, to gain insight into the brain regions that contribute most strongly to the prediction results, we propose a Critical Region Localization algorithm. This algorithm identifies highly predictive anatomical regions within the white matter fiber tracts for the regression task. We evaluate the effectiveness of the proposed method by predicting individual performance on two neuropsychological assessments of language using a dataset of 20 association white matter fiber tracts from 806 subjects from the Human Connectome Project Young Adult dataset. The results demonstrate superior prediction performance of TractGeoNet compared to several popular regression models that have been applied to predict individual cognitive performance based on neuroimaging features. Of the twenty tracts studied, we find that the left arcuate fasciculus tract is the most highly predictive of the two studied language performance assessments. Within each tract, we localize critical regions whose microstructure and point information are highly and consistently predictive of language performance across different subjects and across multiple independently trained models. These critical regions are widespread and distributed across both hemispheres and all cerebral lobes, including areas of the brain considered important for language function such as superior and anterior temporal regions, pars opercularis, and precentral gyrus. Overall, TractGeoNet demonstrates the potential of geometric deep learning to enhance the study of the brain's white matter fiber tracts and to relate their structure to human traits such as language performance.

Self-Supervised Deep Unrolled Reconstruction Using Regularization by Denoising.

Deep learning methods have been successfully used in various computer vision tasks. Inspired by that success, deep learning has been explored in magnetic resonance imaging (MRI) reconstruction. In particular, integrating deep learning and model-based optimization methods has shown considerable advantages. However, a large amount of labeled training data is typically needed for high reconstruction quality, which is challenging for some MRI applications. In this paper, we propose a novel reconstruction method, named DURED-Net, that enables interpretable self-supervised learning for MR image reconstruction by combining a self-supervised denoising network and a plug-and-play method. We aim to boost the reconstruction performance of Noise2Noise in MR reconstruction by adding an explicit prior that utilizes imaging physics. Specifically, the leverage of a denoising network for MRI reconstruction is achieved using Regularization by Denoising (RED). Experiment results demonstrate that the proposed method requires a reduced amount of training data to achieve high reconstruction quality among the state-of-the-art approaches utilizing Noise2Noise.

Novel research and future prospects of artificial intelligence in cancer diagnosis and treatment.

Research into the potential benefits of artificial intelligence for comprehending the intricate biology of cancer has grown as a result of the widespread use of deep learning and machine learning in the healthcare sector and the availability of highly specialized cancer datasets. Here, we review new artificial intelligence approaches and how they are being used in oncology. We describe how artificial intelligence might be used in the detection, prognosis, and administration of cancer treatments and introduce the use of the latest large language models such as ChatGPT in oncology clinics. We highlight artificial intelligence applications for omics data types, and we offer perspectives on how the various data types might be combined to create decision-support tools. We also evaluate the present constraints and challenges to applying artificial intelligence in precision oncology. Finally, we discuss how current challenges may be surmounted to make artificial intelligence useful in clinical settings in the future.

Robust Hand Gesture Recognition Using a Deformable Dual-Stream Fusion Network Based on CNN-TCN for FMCW Radar.

Hand Gesture Recognition (HGR) using Frequency Modulated Continuous Wave (FMCW) radars is difficult because of the inherent variability and ambiguity caused by individual habits and environmental differences. This paper proposes a deformable dual-stream fusion network based on CNN-TCN (DDF-CT) to solve this problem. First, we extract range, Doppler, and angle information from radar signals with the Fast Fourier Transform to produce range-time (RT) and range-angle (RA) maps. Then, we reduce the noise of the feature map. Subsequently, the RAM sequence (RAMS) is generated by temporally organizing the RAMs, which captures a target's range and velocity characteristics at each time point while preserving the temporal feature information. To improve the accuracy and consistency of gesture recognition, DDF-CT incorporates deformable convolution and inter-frame attention mechanisms, which enhance the extraction of spatial features and the learning of temporal relationships. The experimental results show that our method achieves an accuracy of 98.61%, and even when tested in a novel environment, it still achieves an accuracy of 97.22%. Due to its robust performance, our method is significantly superior to other existing HGR approaches.

Mid-Infrared Bipolar and Unipolar Linear Polarization Detections in Nb2 GeTe4 /MoS2 Heterostructures.

Detecting and distinguishing light polarization states, one of the most basic elements of optical fields, have significant importance in both scientific studies and industry applications. Artificially fabricated structures, e.g., metasurfaces with anisotropic absorptions, have shown the capabilities of detecting polarization light and controlling. However, their operations mainly rely on resonant absorptions based on structural designs that are usually narrow bands. Here, a mid-infrared (MIR) broadband polarization photodetector with high PRs and wavelength-dependent polarities using a 2D anisotropic/isotropic Nb2 GeTe4 /MoS2 van der Waals (vdWs) heterostructure is demonstrated. It is shown that the photodetector exhibits high PRs of 48 and 34 at 4.6  and 11.0 µm wavelengths, respectively, and even a negative PR of -3.38 for 3.7 µm under the zero bias condition at room temperature. Such interesting results can be attributed to the superimposed effects of a photovoltaic (PV) mechanism in the Nb2 GeTe4 /MoS2 hetero-junction region and a bolometric mechanism in the MoS2 layer. Furthermore, the photodetector demonstrates its effectiveness in bipolar and unipolar polarization encoding communications and polarization imaging enabled by its unique and high PRs.

Light response and adsorption interaction of black phosphorus quantum dots and single-layer graphene phototransistor.

Black phosphorus quantum dots (BPQDs) are synthesized and combined with graphene sheet. The fabricated BPQDs/graphene devices are capable of detecting visible and near infrared radiation. The adsorption effect of BPQDs in graphene is clarified by the relationship of the photocurrent and the shift of the Dirac point with different substrate. The Dirac point moves toward a neutral point under illumination with both SiO2/Si and Si3N4/Si substrates, indicating an anti-doped feature of photo-excitation. To our knowledge, this provides the first observation of photoresist induced photocurrent in such systems. Without the influence of the photoresist the device can respond to infrared light up to 980 nm wavelength in vacuum in a cryostat, in which the photocurrent is positive and photoconduction effect is believed to dominate the photocurrent. Finally, the adsorption effect is modeled using a first-principle method to give a picture of charge transfer and orbital contribution in the interaction of phosphorus atoms and single-layer graphene.

Deep fiber clustering: Anatomically informed fiber clustering with self-supervised deep learning for fast and effective tractography parcellation.

White matter fiber clustering is an important strategy for white matter parcellation, which enables quantitative analysis of brain connections in health and disease. In combination with expert neuroanatomical labeling, data-driven white matter fiber clustering is a powerful tool for creating atlases that can model white matter anatomy across individuals. While widely used fiber clustering approaches have shown good performance using classical unsupervised machine learning techniques, recent advances in deep learning reveal a promising direction toward fast and effective fiber clustering. In this work, we propose a novel deep learning framework for white matter fiber clustering, Deep Fiber Clustering (DFC), which solves the unsupervised clustering problem as a self-supervised learning task with a domain-specific pretext task to predict pairwise fiber distances. This process learns a high-dimensional embedding feature representation for each fiber, regardless of the order of fiber points reconstructed during tractography. We design a novel network architecture that represents input fibers as point clouds and allows the incorporation of additional sources of input information from gray matter parcellation. Thus, DFC makes use of combined information about white matter fiber geometry and gray matter anatomy to improve the anatomical coherence of fiber clusters. In addition, DFC conducts outlier removal naturally by rejecting fibers with low cluster assignment probability. We evaluate DFC on three independently acquired cohorts, including data from 220 individuals across genders, ages (young and elderly adults), and different health conditions (healthy control and multiple neuropsychiatric disorders). We compare DFC to several state-of-the-art white matter fiber clustering algorithms. Experimental results demonstrate superior performance of DFC in terms of cluster compactness, generalization ability, anatomical coherence, and computational efficiency.

Efficient continuous wave and broad tunable lasers with the Tm:GdScO3 crystal.

The spectroscopic properties and tunable laser performances of the orthorhombic perovskite Tm:GdScO3 crystal grown by the Czochralski method are comparatively studied for polarization along different crystallographic axes. The polarized emission spectrum of Tm:GdScO3 along the b-axis exhibits, to the best of our knowledge, the broadest bandwidth among all the single Tm3+-doped bulk gain media, indicating the strong inhomogeneous line broadening of Tm3+ ions in GdScO3 and thus leads to a broad and smooth gain spectrum. Tunable laser operation with a tuning range as broad as 321 nm from 1824 nm to 2145 nm is achieved, which indicates its potential for few-optical-cycle pulse generation in the 2-µm spectral range.

Measurement, data analysis and modeling of electromagnetic wave propagation gain in a typical vegetation environment.

This paper takes the specific environment covered by vegetation as the research object, carries out modeling and analysis, takes the large-scale fading model of wireless channel as the basis of data processing, researches the transmission law of electromagnetic wave in a typical vegetation environment, which can be divided into four situations. The signal attenuation in each case is theoretically derived and numerically simulated. From the view point of supporting vegetation environment channel, the large-scale channel measurement system is built to meet the actual needs, such as bandwidth, frequency, vegetation coverage, etc. the final vegetation environment channel model under the large-scale fading model is obtained. The results show that the path gain of four scenarios respectively are 81.3 dB, 36.5 dB, 1.6 dB, 1.5 dB, the value of path gain index is within the range of 2~3.5, four scenarios shadow fading standard deviation values are 7.1, 4.8, 10.1, 9.2, reflects the change of received power at the point caused by random factors such as reflection, absorption and scattering. In addition, the proposed channel model improves the gain about 15% compared with the tradition SUI model within vegetation coverage scene. The design process of the proposed model is carried out in the order of "studied the existing foundation → analyzed the existing problems → proposed the optimization scheme → simulation and verification results → actual measurement system". The advantage of paper's method is that, when the signal frequency, transceiver distance, antenna height and vegetation environment characteristic parameters are given, the statistical analysis results of wireless channel data are obtained. The purpose of the proposed work establishes a signal propagation prediction model under the vegetation environment, realizes a theoretical basis for channel simulation, and provides the basis of anti-fading technologies.

Superficial white matter analysis: An efficient point-cloud-based deep learning framework with supervised contrastive learning for consistent tractography parcellation across populations and dMRI acquisitions.

Diffusion MRI tractography is an advanced imaging technique that enables in vivo mapping of the brain's white matter connections. White matter parcellation classifies tractography streamlines into clusters or anatomically meaningful tracts. It enables quantification and visualization of whole-brain tractography. Currently, most parcellation methods focus on the deep white matter (DWM), whereas fewer methods address the superficial white matter (SWM) due to its complexity. We propose a novel two-stage deep-learning-based framework, Superficial White Matter Analysis (SupWMA), that performs an efficient and consistent parcellation of 198 SWM clusters from whole-brain tractography. A point-cloud-based network is adapted to our SWM parcellation task, and supervised contrastive learning enables more discriminative representations between plausible streamlines and outliers for SWM. We train our model on a large-scale tractography dataset including streamline samples from labeled long- and medium-range (over 40 mm) SWM clusters and anatomically implausible streamline samples, and we perform testing on six independently acquired datasets of different ages and health conditions (including neonates and patients with space-occupying brain tumors). Compared to several state-of-the-art methods, SupWMA obtains highly consistent and accurate SWM parcellation results on all datasets, showing good generalization across the lifespan in health and disease. In addition, the computational speed of SupWMA is much faster than other methods.

Neural mechanism underlying depressive-like state associated with social status loss.

Downward social mobility is a well-known mental risk factor for depression, but its neural mechanism remains elusive. Here, by forcing mice to lose against their subordinates in a non-violent social contest, we lower their social ranks stably and induce depressive-like behaviors. These rank-decline-associated depressive-like behaviors can be reversed by regaining social status. In vivo fiber photometry and single-unit electrophysiological recording show that forced loss, but not natural loss, generates negative reward prediction error (RPE). Through the lateral hypothalamus, the RPE strongly activates the brain's anti-reward center, the lateral habenula (LHb). LHb activation inhibits the medial prefrontal cortex (mPFC) that controls social competitiveness and reinforces retreats in contests. These results reveal the core neural mechanisms mutually promoting social status loss and depressive behaviors. The intertwined neuronal signaling controlling mPFC and LHb activities provides a mechanistic foundation for the crosstalk between social mobility and psychological disorder, unveiling a promising target for intervention.

SuperMAP: Deep ultrafast MR relaxometry with joint spatiotemporal undersampling.

PURPOSE: To develop an ultrafast and robust MR parameter mapping network using deep learning. THEORY AND METHODS: We design a deep learning framework called SuperMAP that directly converts a series of undersampled (both in k-space and parameter-space) parameter-weighted images into several quantitative maps, bypassing the conventional exponential fitting procedure. We also present a novel technique to simultaneously reconstruct T1rho and T2 relaxation maps within a single scan. Full data were acquired and retrospectively undersampled for training and testing using traditional and state-of-the-art techniques for comparison. Prospective data were also collected to evaluate the trained network. The performance of all methods is evaluated using the parameter qualification errors and other metrics in the segmented regions of interest. RESULTS: SuperMAP achieved accurate T1rho and T2 mapping with high acceleration factors (R = 24 and R = 32). It exploited both spatial and temporal information and yielded low error (normalized mean square error of 2.7% at R = 24 and 2.8% at R = 32) and high resemblance (structural similarity of 97% at R = 24 and 96% at R = 32) to the gold standard. The network trained with retrospectively undersampled data also works well for the prospective data (with a slightly lower acceleration factor). SuperMAP is also superior to conventional methods. CONCLUSION: Our results demonstrate the feasibility of generating superfast MR parameter maps through very few undersampled parameter-weighted images. SuperMAP can simultaneously generate T1rho and T2 relaxation maps in a short scan time.

Promoted Mid-Infrared Photodetection of PbSe Film by Iodine Sensitization Based on Chemical Bath Deposition.

In recent years, lead selenide (PbSe) has gained considerable attention for its potential applications in optoelectronic devices. However, there are still some challenges in realizing mid-infrared detection applications with single PbSe film at room temperature. In this paper, we use a chemical bath deposition method to deposit PbSe thin films by varying deposition time. The effects of the deposition time on the structure, morphology, and optical absorption of the deposited PbSe films were investigated by x-ray diffraction, scanning electron microscopy, and infrared spectrometer. In addition, in order to activate the mid-infrared detection capability of PbSe, we explored its application in infrared photodetection by improving its crystalline quality and photoconductivity and reducing tge noise and high dark current of PbSe thin films through subsequent iodine treatment. The iodine sensitization PbSe film showed superior photoelectric properties compared to the untreated sample, which exhibited the maximum of responsiveness, which is 30.27 A/W at 808 nm, and activated its detection ability in the mid-infrared (5000 nm) by introducing PbI2, increasing the barrier height of the crystallite boundary and carrier lifetimes. This facile synthesis strategy and the sensitization treatment process provide a potential experimental scheme for the simple, rapid, low-cost, and efficient fabrication of large-area infrared PbSe devices.

Epitaxial Topological Insulator Bi2Te3 for Fast Visible to Mid-Infrared Heterojunction Photodetector by Graphene As Charge Collection Medium.

Three dimensional topological insulators have a thriving application prospect in broadband photodetectors due to the possessed topological quantum states. Herein, a large area and uniform topological insulator bismuth telluride (Bi2Te3) layer with high crystalline quality is directly epitaxial grown on GaAs(111)B wafer using a molecular beam epitaxy process, ensuring efficient out-of-plane carriers transportation due to reduced interface defects influence. By tiling monolayer graphene (Gr) on the as-prepared Bi2Te3 layer, a Gr/Bi2Te3/GaAs heterojunction array prototype was further fabricated, and our photodetector array exhibited the capability of sensing ultrabroad photodetection wavebands from visible (405 nm) to mid-infrared (4.5 µm) with a high specific detectivity (D*) up to 1012 Jones and a fast response speed at about microseconds at room temperature. The enhanced device performance can be attributed to enhanced light-matter interaction at the high-quality heterointerface of Bi2Te3/GaAs and improved carrier collection efficiency through graphene as a charge collection medium, indicating an application prospect of topological insulator Bi2Te3 for fast-speed broadband photodetection up to a mid-infrared waveband. This work demonstrated the potential of integrated topological quantum materials with a conventional functional substrate to fabricate the next generation of broadband photodetection devices for uncooled focal plane array or infrared communication systems in future.

DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis.

We present a novel weakly-supervised framework for classifying whole slide images (WSIs). WSIs, due to their gigapixel resolution, are commonly processed by patch-wise classification with patch-level labels. However, patch-level labels require precise annotations, which is expensive and usually unavailable on clinical data. With image-level labels only, patch-wise classification would be sub-optimal due to inconsistency between the patch appearance and image-level label. To address this issue, we posit that WSI analysis can be effectively conducted by integrating information at both high magnification (local) and low magnification (regional) levels. We auto-encode the visual signals in each patch into a latent embedding vector representing local information, and down-sample the raw WSI to hardware-acceptable thumbnails representing regional information. The WSI label is then predicted with a Dual-Stream Network (DSNet), which takes the transformed local patch embeddings and multi-scale thumbnail images as inputs and can be trained by the image-level label only. Experiments conducted on three large-scale public datasets demonstrate that our method outperforms all recent state-of-the-art weakly-supervised WSI classification methods.

The effect of prolonged formalin fixation on the expression of proteins in human brain tissues.

Formalin-fixed, paraffin-embedded (FFPE) tissues have been widely used in researches. Proteins and nucleic acids in prolonged FFPE tissues display different degrees of degradation. We investigated the effect of prolonged formalin fixation on protein expression in human brain tissues. Twenty-eight middle prefrontal front cortex tissue blocks from human brains prefixed in formalin were obtained from a brain bank. The tissue blocks were divided into two groups, the control group and the prolonged fixation group. Quantitative immunocytochemistry was used to analyse the biological markers of Fox-3, Rbfox3 (NeuN), glial fibrillary acidic protein (GFAP), ionized calcium binding adapter molecule-1 (IBA-1) and glyceraldehyde-3-phosphate dehydrogenase (GAPDH). Nissl staining showed that positive signaling of Nissl body was significantly decreased by 16.6% in the prolonged fixation group. In addition, the staining intensity of Nissl body was negatively correlated with fixation time. The level of NeuN immunoreactivity (ir) was significantly reduced by 19.31% in the prolonged fixation group. Moreover, there was a significant negative correlation between NeuN-ir and fixation time. There were no significant changes in GFAP-ir, IBA-1-ir and GAPDH-ir between control group and the prolonged fixation group. Prolonged formalin-fixed tissues showed time- and molecule-dependent protein changes, which may be potential confounders in the clinic and researches. Our study suggested short formalin fixation time is recommended when using PPFE brain tissues.

Towards bi-directional skip connections in encoder-decoder architectures and beyond.

U-Net, as an encoder-decoder architecture with forward skip connections, has achieved promising results in various medical image analysis tasks. Many recent approaches have also extended U-Net with more complex building blocks, which typically increase the number of network parameters considerably. Such complexity makes the inference stage highly inefficient for clinical applications. Towards an effective yet economic segmentation network design, in this work, we propose backward skip connections that bring decoded features back to the encoder. Our design can be jointly adopted with forward skip connections in any encoder-decoder architecture forming a recurrence structure without introducing extra parameters. With the backward skip connections, we propose a U-Net based network family, namely Bi-directional O-shape networks, which set new benchmarks on multiple public medical imaging segmentation datasets. On the other hand, with the most plain architecture (BiO-Net), network computations inevitably increase along with the pre-set recurrence time. We have thus studied the deficiency bottleneck of such recurrent design and propose a novel two-phase Neural Architecture Search (NAS) algorithm, namely BiX-NAS, to search for the best multi-scale bi-directional skip connections. The ineffective skip connections are then discarded to reduce computational costs and speed up network inference. The finally searched BiX-Net yields the least network complexity and outperforms other state-of-the-art counterparts by large margins. We evaluate our methods on both 2D and 3D segmentation tasks in a total of six datasets. Extensive ablation studies have also been conducted to provide a comprehensive analysis for our proposed methods.

Multiple Sclerosis Lesion Analysis in Brain Magnetic Resonance Images: Techniques and Clinical Applications.

Multiple sclerosis (MS) is a chronic inflammatory and degenerative disease of the central nervous system, characterized by the appearance of focal lesions in the white and gray matter that topographically correlate with an individual patient's neurological symptoms and signs. Magnetic resonance imaging (MRI) provides detailed in-vivo structural information, permitting the quantification and categorization of MS lesions that critically inform disease management. Traditionally, MS lesions have been manually annotated on 2D MRI slices, a process that is inefficient and prone to inter-/intra-observer errors. Recently, automated statistical imaging analysis techniques have been proposed to detect and segment MS lesions based on MRI voxel intensity. However, their effectiveness is limited by the heterogeneity of both MRI data acquisition techniques and the appearance of MS lesions. By learning complex lesion representations directly from images, deep learning techniques have achieved remarkable breakthroughs in the MS lesion segmentation task. Here, we provide a comprehensive review of state-of-the-art automatic statistical and deep-learning MS segmentation methods and discuss current and future clinical applications. Further, we review technical strategies, such as domain adaptation, to enhance MS lesion segmentation in real-world clinical settings.

Interleukin-6 mediates lipopolysaccharide-inhibited irisin secretion in Nile tilapia (Oreochromis niloticus).

Irisin is a novel immunomodulatory adipomyokine released upon cleavage of the fibronectin type III domain-containing protein 5 (FNDC5). We aimed to examine interleukin-6 (IL-6) role in mediating irisin secretion in immunologically challenged animal and primary head kidney leukocytes cultured from tilapia. Intraperitoneal injection of lipopolysaccharide (LPS) increased plasma IL-6 levels and decreased irisin secretion, suggesting a causal relationship between the induction of IL-6 and irisin. To address this relationship, we further produced recombinant tilapia IL-6 and the anti-tilapia IL-6 polyclonal antiserum. Intraperitoneal injection of recombinant tilapia IL-6 inhibited plasma irisin levels. Consistent with this observation, LPS-induced inhibition of plasma irisin was significantly attenuated by neutralizing circulating IL-6 using an IL-6 antiserum. Besides, IL-6 treatment could inhibit irisin secretion and FNDC5 gene expression in primary cultures of tilapia head kidney leukocytes. In parallel experiments, both LPS and IL-6 blockade of irisin secretion could be reverted by IL-6 receptor antagonism. At the level of the leukocyte, IL-6 treatment also triggered rapid phosphorylation of Janus kinase 2 (JAK2) and signal transducer and activator of transcription 3 (STAT3), whereas IL-6-reduced irisin secretion could be negated by inhibiting the JAK2 and STAT3 signaling pathways. These results, as a whole, provide the first evidence that IL-6 is the mediator of LPS-inhibited irisin secretion via activation of the JAK2/STAT3 signaling pathway.

Dynamics of a disinhibitory prefrontal microcircuit in controlling social competition.

Social competition plays a pivotal role in determining individuals' social status. While the dorsomedial prefrontal cortex (dmPFC) is essential in regulating social competition, it remains unclear how information is processed within its local networks. Here, by applying optogenetic and chemogenetic manipulations in a dominance tube test, we reveal that, in accordance with pyramidal (PYR) neuron activation, excitation of the vasoactive intestinal polypeptide (VIP) or inhibition of the parvalbumin (PV) interneurons induces winning. The winning behavior is associated with sequential calcium activities initiated by VIP and followed by PYR and PV neurons. Using miniature two-photon microscopic (MTPM) and optrode recordings in awake mice, we show that VIP stimulation directly leads to a two-phased activity pattern of both PYR and PV neurons-rapid suppression followed by activation. The delayed activation of PV implies an embedded feedback tuning. This disinhibitory VIP-PV-PYR motif forms the core of a dmPFC microcircuit to control social competition.