arXiv subjects

Yuchen Xu

Publications and source records attributed to Yuchen Xu.

35 records · Page 2Linked to original sources

arXiv2025

Non-Invasive Temporal Interference Electrical Stimulation for Spinal Cord Injury Rehabilitation: A Simulation Study

Background: Spinal cord injury (SCI) rehabilitation remains a major clinical challenge, with limited treatment options for functional recovery. Temporal interference (TI) electrical stimulation has emerged as a promising non-invasive neuromodulation technique capable of delivering deep and targeted stimulation. However, the application of TI stimulation in SCI rehabilitation remains largely unexplored. Methods: This study aims to investigate the feasibility of applying non-invasive TI electrical stimulation for SCI rehabilitation. Through computational modeling, we analyzed the electric field distribution characteristics in the spinal cord under different TI stimulation configurations. Based on these findings, we propose a clinically applicable TI stimulation protocol for SCI rehabilitation. Results: The results demonstrate that TI stimulation can effectively deliver focused electric fields to targeted spinal cord segments while maintaining non-invasiveness. The electric field intensity varied depending on individual anatomical differences, highlighting the need for personalized stimulation parameters. The proposed protocol provides a practical framework for applying TI stimulation in SCI rehabilitation and offers a non-invasive alternative to traditional spinal cord stimulation techniques. Conclusions: This study establishes the feasibility of using non-invasive TI stimulation for SCI rehabilitation. The proposed stimulation protocol enables precise and targeted spinal cord modulation. However, further research is needed to refine personalized stimulation parameters and validate the clinical efficacy of this approach.

physics.med-ph↗

arXiv2025

Poststroke rehabilitative mechanisms in individualized fatigue level-controlled treadmill training -- a Rat Model Study

Individualized training improved post-stroke motor function rehabilitation efficiency. However, the mechanisms of how individualized training facilitates recovery is not clear. This study explored the cortical and corticomuscular rehabilitative effects in post-stroke motor function recovery during individualized training. Sprague-Dawley rats with intracerebral hemorrhage (ICH) were randomly distributed into two groups: forced training (FOR-T, n=13) and individualized fatigue-controlled training (FAT-C, n=13) to receive training respectively from day 2 to day 14 post-stroke. The FAT-C group exhibited superior motor function recovery and less central fatigue compared to the FOR-T group. EEG PSD slope analysis demonstrated a better inter-hemispheric balance in FAT-C group compare to the FOR-T group. The dCMC analysis indicated that training-induced fatigue led to a short-term down-regulation of descending corticomuscular coherence (dCMC) and an up-regulation of ascending dCMC. In the long term, excessive fatigue hindered the recovery of descending control in the affected hemisphere. The individualized strategy of peripheral fatigue-controlled training achieved better motor function recovery, which could be attributed to the mitigation of central fatigue, optimization of inter-hemispheric balance and enhancement of descending control in the affected hemisphere.

eess.SP↗

arXiv2024

Efficacy of Temporal Interference Electrical Stimulation for Spinal Cord Injury Rehabilitation: A Case Series

Spinal cord injury (SCI) is a debilitating condition that often results in significant motor and sensory deficits, impacting the quality of life. Current rehabilitation methods, including physical therapy and electrical stimulation, offer variable outcomes and often require invasive procedures. Temporal interference (TI) stimulation has emerged as a novel, non-invasive neuromodulation technique capable of targeting deep neural structures with precision, providing a promising alternative for SCI rehabilitation. This study explores the efficacy of TI stimulation as a non-invasive approach for improving motor and sensory function in patients with incomplete SCI. Three male patients with incomplete cervical SCI (AIS D) participated in a two-week intervention consisting of 14 sessions of TI stimulation targeting their injury sites. TI stimulation was delivered using frequencies of 1000 Hz and 1040 Hz, with assessments conducted pre- and post-intervention, including motor and sensory evaluations, functional scales, and imaging studies.All participants demonstrated significant improvements in neurological function, motor strength, sensory perception, and functional independence. Neurological levels of injury shifted upward in all cases, with one patient improving from C5 to C7. Graded Redefined Assessment of Strength, Sensibility and Prehension (GRASSP) results shows additional strength, prehension and sensory outcomes obtained for the arm and hand functions of participants. Motor scores (UEMS and LEMS) increased, sensory scores for light touch and pin prick improved, and functional assessments, such as the Berg Balance Scale (BBS) and Barthel Index (BI), showed marked gains. Pain scores also decreased in two participants, highlighting additional therapeutic benefits.

q-bio.NC↗

arXiv2024

Self-supervised Anomaly Detection Pretraining Enhances Long-tail ECG Diagnosis

Current computer-aided ECG diagnostic systems struggle with the underdetection of rare but critical cardiac anomalies due to the imbalanced nature of ECG datasets. This study introduces a novel approach using self-supervised anomaly detection pretraining to address this limitation. The anomaly detection model is specifically designed to detect and localize subtle deviations from normal cardiac patterns, capturing the nuanced details essential for accurate ECG interpretation. Validated on an extensive dataset of over one million ECG records from clinical practice, characterized by a long-tail distribution across 116 distinct categories, the anomaly detection-pretrained ECG diagnostic model has demonstrated a significant improvement in overall accuracy. Notably, our approach yielded a 94.7% AUROC, 92.2% sensitivity, and 92.5\% specificity for rare ECG types, significantly outperforming traditional methods and narrowing the performance gap with common ECG types. The integration of anomaly detection pretraining into ECG analysis represents a substantial contribution to the field, addressing the long-standing challenge of long-tail data distributions in clinical diagnostics. Furthermore, prospective validation in real-world clinical settings revealed that our AI-driven approach enhances diagnostic efficiency, precision, and completeness by 32%, 6.7%, and 11.8% respectively, when compared to standard practices. This advancement marks a pivotal step forward in the integration of AI within clinical cardiology, with particularly profound implications for emergency care, where rapid and accurate ECG interpretation is crucial. The contributions of this study not only push the boundaries of current ECG diagnostic capabilities but also lay the groundwork for more reliable and accessible cardiovascular care.

cs.CV↗

arXiv2024

Anomaly Detection in Electrocardiograms: Advancing Clinical Diagnosis Through Self-Supervised Learning

The electrocardiogram (ECG) is an essential tool for diagnosing heart disease, with computer-aided systems improving diagnostic accuracy and reducing healthcare costs. Despite advancements, existing systems often miss rare cardiac anomalies that could be precursors to serious, life-threatening issues or alterations in the cardiac macro/microstructure. We address this gap by focusing on self-supervised anomaly detection (AD), training exclusively on normal ECGs to recognize deviations indicating anomalies. We introduce a novel self-supervised learning framework for ECG AD, utilizing a vast dataset of normal ECGs to autonomously detect and localize cardiac anomalies. It proposes a novel masking and restoration technique alongside a multi-scale cross-attention module, enhancing the model's ability to integrate global and local signal features. The framework emphasizes accurate localization of anomalies within ECG signals, ensuring the method's clinical relevance and reliability. To reduce the impact of individual variability, the approach further incorporates crucial patient-specific information from ECG reports, such as age and gender, thus enabling accurate identification of a broad spectrum of cardiac anomalies, including rare ones. Utilizing an extensive dataset of 478,803 ECG graphic reports from real-world clinical practice, our method has demonstrated exceptional effectiveness in AD across all tested conditions, regardless of their frequency of occurrence, significantly outperforming existing models. It achieved superior performance metrics, including an AUROC of 91.2%, an F1 score of 83.7%, a sensitivity rate of 84.2%, a specificity of 83.0%, and a precision of 75.6% with a fixed recall rate of 90%. It has also demonstrated robust localization capabilities, with an AUROC of 76.5% and a Dice coefficient of 65.3% for anomaly localization.

cs.CV↗

arXiv2024

Accelerating Distributed Deep Learning using Lossless Homomorphic Compression

As deep neural networks (DNNs) grow in complexity and size, the resultant increase in communication overhead during distributed training has become a significant bottleneck, challenging the scalability of distributed training systems. Existing solutions, while aiming to mitigate this bottleneck through worker-level compression and in-network aggregation, fall short due to their inability to efficiently reconcile the trade-offs between compression effectiveness and computational overhead, hindering overall performance and scalability. In this paper, we introduce a novel compression algorithm that effectively merges worker-level compression with in-network aggregation. Our solution is both homomorphic, allowing for efficient in-network aggregation without CPU/GPU processing, and lossless, ensuring no compromise on training accuracy. Theoretically optimal in compression and computational efficiency, our approach is empirically validated across diverse DNN models such as NCF, LSTM, VGG19, and BERT-base, showing up to a 6.33$\times$ improvement in aggregation throughput and a 3.74$\times$ increase in per-iteration training speed.

cs.DC↗

arXiv2023

Dynamic Atomic Column Detection in Transmission Electron Microscopy Videos via Ridge Estimation

Ridge detection is a classical tool to extract curvilinear features in image processing. As such, it has great promise in applications to material science problems; specifically, for trend filtering relatively stable atom-shaped objects in image sequences, such as Transmission Electron Microscopy (TEM) videos. Standard analysis of TEM videos is limited to frame-by-frame object recognition. We instead harness temporal correlation across frames through simultaneous analysis of long image sequences, specified as a spatio-temporal image tensor. We define new ridge detection algorithms to non-parametrically estimate explicit trajectories of atomic-level object locations as a continuous function of time. Our approach is specially tailored to handle temporal analysis of objects that seemingly stochastically disappear and subsequently reappear throughout a sequence. We demonstrate that the proposed method is highly effective and efficient in simulation scenarios, and delivers notable performance improvements in TEM experiments compared to other material science benchmarks.

stat.AP↗

arXiv2023

Feature detection and hypothesis testing for extremely noisy nanoparticle images using topological data analysis

We propose a flexible algorithm for feature detection and hypothesis testing in images with ultra low signal-to-noise ratio using cubical persistent homology. Our main application is in the identification of atomic columns and other features in transmission electron microscopy (TEM). Cubical persistent homology is used to identify local minima and their size in subregions in the frames of nanoparticle videos, which are hypothesized to correspond to relevant atomic features. We compare the performance of our algorithm to other employed methods for the detection of columns and their intensity. Additionally, Monte Carlo goodness-of-fit testing using real valued summaries of persistence diagrams derived from smoothed images (generated from pixels residing in the vacuum region of an image) is developed and employed to identify whether or not the proposed atomic features generated by our algorithm are due to noise. Using these summaries derived from the generated persistence diagrams, one can produce univariate time series for the nanoparticle videos, thus providing a means for assessing fluxional behavior. A guarantee on the false discovery rate for multiple Monte Carlo testing of identical hypotheses is also established.

stat.AP↗

arXiv2020

Outlier Guided Optimization of Abdominal Segmentation

Abdominal multi-organ segmentation of computed tomography (CT) images has been the subject of extensive research interest. It presents a substantial challenge in medical image processing, as the shape and distribution of abdominal organs can vary greatly among the population and within an individual over time. While continuous integration of novel datasets into the training set provides potential for better segmentation performance, collection of data at scale is not only costly, but also impractical in some contexts. Moreover, it remains unclear what marginal value additional data have to offer. Herein, we propose a single-pass active learning method through human quality assurance (QA). We built on a pre-trained 3D U-Net model for abdominal multi-organ segmentation and augmented the dataset either with outlier data (e.g., exemplars for which the baseline algorithm failed) or inliers (e.g., exemplars for which the baseline algorithm worked). The new models were trained using the augmented datasets with 5-fold cross-validation (for outlier data) and withheld outlier samples (for inlier data). Manual labeling of outliers increased Dice scores with outliers by 0.130, compared to an increase of 0.067 with inliers (p<0.001, two-tailed paired t-test). By adding 5 to 37 inliers or outliers to training, we find that the marginal value of adding outliers is higher than that of adding inliers. In summary, improvement on single-organ performance was obtained without diminishing multi-organ performance or significantly increasing training time. Hence, identification and correction of baseline failure cases present an effective and efficient method of selecting training data to improve algorithm performance.

cs.CV↗

arXiv2020

Validation and Optimization of Multi-Organ Segmentation on Clinical Imaging Archives

Segmentation of abdominal computed tomography(CT) provides spatial context, morphological properties, and a framework for tissue-specific radiomics to guide quantitative Radiological assessment. A 2015 MICCAI challenge spurred substantial innovation in multi-organ abdominal CT segmentation with both traditional and deep learning methods. Recent innovations in deep methods have driven performance toward levels for which clinical translation is appealing. However, continued cross-validation on open datasets presents the risk of indirect knowledge contamination and could result in circular reasoning. Moreover, 'real world' segmentations can be challenging due to the wide variability of abdomen physiology within patients. Herein, we perform two data retrievals to capture clinically acquired deidentified abdominal CT cohorts with respect to a recently published variation on 3D U-Net (baseline algorithm). First, we retrieved 2004 deidentified studies on 476 patients with diagnosis codes involving spleen abnormalities (cohort A). Second, we retrieved 4313 deidentified studies on 1754 patients without diagnosis codes involving spleen abnormalities (cohort B). We perform prospective evaluation of the existing algorithm on both cohorts, yielding 13% and 8% failure rate, respectively. Then, we identified 51 subjects in cohort A with segmentation failures and manually corrected the liver and gallbladder labels. We re-trained the model adding the manual labels, resulting in performance improvement of 9% and 6% failure rate for the A and B cohorts, respectively. In summary, the performance of the baseline on the prospective cohorts was similar to that on previously published datasets. Moreover, adding data from the first cohort substantively improved performance when evaluated on the second withheld validation cohort.

eess.IV↗

arXiv2019

Contrast Phase Classification with a Generative Adversarial Network

Dynamic contrast enhanced computed tomography (CT) is an imaging technique that provides critical information on the relationship of vascular structure and dynamics in the context of underlying anatomy. A key challenge for image processing with contrast enhanced CT is that phase discrepancies are latent in different tissues due to contrast protocols, vascular dynamics, and metabolism variance. Previous studies with deep learning frameworks have been proposed for classifying contrast enhancement with networks inspired by computer vision. Here, we revisit the challenge in the context of whole abdomen contrast enhanced CTs. To capture and compensate for the complex contrast changes, we propose a novel discriminator in the form of a multi-domain disentangled representation learning network. The goal of this network is to learn an intermediate representation that separates contrast enhancement from anatomy and enables classification of images with varying contrast time. Briefly, our unpaired contrast disentangling GAN(CD-GAN) Discriminator follows the ResNet architecture to classify a CT scan from different enhancement phases. To evaluate the approach, we trained the enhancement phase classifier on 21060 slices from two clinical cohorts of 230 subjects. Testing was performed on 9100 slices from 30 independent subjects who had been imaged with CT scans from all contrast phases. Performance was quantified in terms of the multi-class normalized confusion matrix. The proposed network significantly improved correspondence over baseline UNet, ResNet50 and StarGAN performance of accuracy scores 0.54. 0.55, 0.62 and 0.91, respectively. The proposed discriminator from the disentangled network presents a promising technique that may allow deeper modeling of dynamic imaging against patient specific anatomies.

eess.IV↗

arXiv2019

Semi-Supervised Multi-Organ Segmentation through Quality Assurance Supervision

Human in-the-loop quality assurance (QA) is typically performed after medical image segmentation to ensure that the systems are performing as intended, as well as identifying and excluding outliers. By performing QA on large-scale, previously unlabeled testing data, categorical QA scores can be generatedIn this paper, we propose a semi-supervised multi-organ segmentation deep neural network consisting of a traditional segmentation model generator and a QA involved discriminator. A large-scale dataset of 2027 volumes are used to train the generator, whose 2-D montage images and segmentation mask with QA scores are used to train the discriminator. To generate the QA scores, the 2-D montage images were reviewed manually and coded 0 (success), 1 (errors consistent with published performance), and 2 (gross failure). Then, the ResNet-18 network was trained with 1623 montage images in equal distribution of all three code labels and achieved an accuracy 94% for classification predictions with 404 montage images withheld for the test cohort. To assess the performance of using the QA supervision, the discriminator was used as a loss function in a multi-organ segmentation pipeline. The inclusion of QA-loss function boosted performance on the unlabeled test dataset from 714 patients to 951 patients over the baseline model. Additionally, the number of failures decreased from 606 (29.90%) to 402 (19.83%). The contributions of the proposed method are threefold: We show that (1) the QA scores can be used as a loss function to perform semi-supervised learning for unlabeled data, (2) the well trained discriminator is learnt by QA score rather than traditional true/false, and (3) the performance of multi-organ segmentation on unlabeled datasets can be fine-tuned with more robust and higher accuracy than the original baseline method.

eess.IV↗

arXiv2017

Coupling of evanescent waves into propagation channels within two-dimensional random waveguides

The transformation from evanescent waves to propagation waves is the key mechanism for the realization of some super-resolution imaging methods. By using the recursive Green function and scattering-matrix theory, we investigated in details on the transport of evanescent waves through a random medium and analyzed quantitatively the coupling of evanescent channels to propagation channels. By numerical calculations, we found that the transmission for the incident evanescent channel is determined by both the eigenvalues of the scattering matrix and the coupling strength to the corresponding propagation channels in random medium, and the disorder strength of the random medium influences both of them.

cond-mat.mes-hall↗

arXiv2016

Low lattice thermal conductivity of stanene

A fundamental understanding of phonon transport in stanene is crucial to predict the thermal performance in potential stanene-based devices. By combining first-principle calculation and phonon Boltzmann transport equation, we obtain the lattice thermal conductivity of stanene. A much lower thermal conductivity (11.6 W/mK) is observed in stanene, which indicates higher thermoelectric efficiency over other 2D materials. The contributions of acoustic and optical phonons to the lattice thermal conductivity are evaluated. Detailed analysis of phase space for three-phonon processes shows that phonon scattering channels LA+LA/TA/ZA$\leftrightarrow$TA/ZA are restricted, leading to the dominant contributions of high-group-velocity LA phonons to the thermal conductivity. The size dependence of thermal conductivity is investigated as well for the purpose of the design of thermoelectric nanostructures.

cond-mat.mtrl-sci↗

arXiv2016

Behaviour of light transmission channels in random media with inhomogeneous disorder

We present a numerical study on the light transport properties and statistics of transmission channels in random media with inhomogeneous disorder. For the case of longitudinal inhomogeneity of disorder we find that the statistics of the transmission channels is independent of the inhomogeneity and the system can be equivalent to a counterpart with homogeneous disorder strength, both of which have the same statistical distribution of the transmission channels. However, for the case of transverse inhomogeneity of disorder, such equivalence does not exist, moreover, the transmission eigenvalues are pushed to the two ends of the distribution and the distribution of the total transmission is broadened since the spatial structure gives rise to larger and smaller transmitted incident channels.

physics.optics↗

arXiv2015

Light transport behaviours in quasi-1D disordered waveguides composed of random photonic lattices

We present a numerical study on the light transport properties which are modulated by the disorder strength in quasi-one-dimensional disordered waveguide which consists of periodically arranged scatterers with random dielectric constant. The transport mean free path is found to stay inversely proportional to the square of the relative fluctuation of the dielectric constant as in the 1D and 2D cases but with . The transport properties of light through a sample with a fixed size can be modulated from ballistic to localized regime as well, and a generalized scaling function is defined to determine the light transport status in such a sample. The calculation of the diffusion coefficient and the energy density profile of the most transmitted eigenchannel clearly exhibits the transition of transport behaviour from diffusion to localization.

physics.optics↗

arXiv2015

Thermal conductivity of monolayer MoS2, MoSe2, and WS2: Interplay of mass effect, interatomic bonding and anharmonicity

Phonons are essential for understanding the thermal properties in monolayer transition metal dichalcogenides, which limit their thermal performance for potential applications. We investigate the lattice dynamics and thermodynamic properties of MoS2, MoSe2, and WS2 by first principles calculations. The obtained phonon frequencies and thermal conductivities agree well with the measurements. Our results show that the thermal conductivity of MoS2 is highest among the three materials due to its much lower average atomic mass. We also discuss the competition between mass effect, interatomic bonding and anharmonic vibrations in determining the thermal conductivity of WS2. Strong covalent W-S bonding and low anharmonicity in WS2 are found to be crucial in understanding its much higher thermal conductivity compared to MoSe2.

cond-mat.mes-hall↗