A5101436487- Advanced Fiber Laser Technologies
- Nonlinear Photonic Systems
- Nonlinear Waves and Solitons
- Advanced Text Analysis Techniques
- Language, Metaphor, and Cognition
- Natural Language Processing Techniques
- Optical Network Technologies
- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Photonic Crystal and Fiber Optics
- Systemic Sclerosis and Related Diseases
- Photonic and Optical Devices
- Speech Recognition and Synthesis
- Speech and Audio Processing
- Advanced Fiber Optic Sensors
- Colorectal Cancer Screening and Detection
- Multimodal Machine Learning Applications
- Lung Cancer Treatments and Mutations
- Single-cell and spatial transcriptomics
- Semiconductor Lasers and Optical Devices
- Domain Adaptation and Few-Shot Learning
- Music and Audio Processing
- Cancer Genomics and Diagnostics
- Sentiment Analysis and Opinion Mining
- Renal and Vascular Pathologies
Northwestern Polytechnical University
2025
Stanford University
2024
The University of Queensland
2024
Xiamen University
2011-2024
Case Western Reserve University
2020-2024
Zhejiang University of Science and Technology
2024
Southeast University
2024
Park University
2022
Beijing Institute of Technology
2022
Wuhan University
2022
The application of deep learning for automated segmentation (delineation boundaries) histologic primitives (structures) from whole slide images can facilitate the establishment novel protocols kidney biopsy assessment. Here, we developed and validated networks structures on biopsies nephrectomies. For development, examined 125 Minimal Change Disease collected across 29 NEPTUNE enrolling centers along with 459 stained Hematoxylin & Eosin (125), Periodic Acid Schiff Silver (102), Trichrome...
There is a need to define regions of gene activation or repression that control human kidney cells in states health, injury, and repair understand the molecular pathogenesis disease design therapeutic strategies. Comprehensive integration expression with epigenetic features regulatory elements remains significant challenge. We measure dual single nucleus RNA chromatin accessibility, DNA methylation, H3K27ac, H3K4me1, H3K4me3, H3K27me3 histone modifications decipher landscape regulation...
Inconsistencies in the preparation of histology slides and whole-slide images (WSIs) may lead to challenges with subsequent image analysis machine learning approaches for interrogating WSI. These variabilities are especially pronounced multicenter cohorts, where batch effects (i.e. systematic technical artifacts unrelated biological variability) introduce biases algorithms. To date, manual quality control (QC) has been de facto standard dataset curation, but remains highly subjective is too...
Applying deep learning to predict patient prognostic survival outcomes using histological whole-slide images (WSIs) and genomic data is challenging due the morphological transcriptomic heterogeneity present in tumor microenvironment. Existing learning-enabled methods often exhibit biases, primarily because knowledge used guide directional feature extraction from WSIs may be irrelevant or incomplete. This results a suboptimal sometimes myopic understanding of overall pathological landscape,...
PURPOSE Artificial intelligence (AI) holds significant promise for improving cancer diagnosis and treatment. Here, we present a foundation AI model prognosis prediction on the basis of standard hematoxylin eosin–stained histopathology slides. METHODS In this multinational cohort study, developed models to predict from images patients with GI cancers. First, trained using over 130 million patches 104,876 whole-slide self-supervised learning. Second, fine-tuned deep learning predicting...
This article investigates how choosing a different hash function might affect the overall performance of blockchain. We focus on selection for Ethereum and carry out extensive experiments to evaluate change after replacement function. Our findings indicate that some metrics blockchain be significantly affected by used. suggests specific may not trivial decision designing
Key Points Computational image analysis allows for the extraction of new information from whole-slide images with potential clinical relevance. Peritubular capillary (PTC) density is decreased in areas interstitial fibrosis and tubular atrophy when measured fractional space. PTC shape (aspect ratio) associated outcome glomerular diseases. Background The association between peritubular disease progression has been studied a variety kidney diseases using immunohistochemistry. However, other...
The analytical solutions to differential equations governing nonlinear four-photon mixing in optical fibers are presented for the general case of depleted pump power. expressions reduce those derived earlier with assumption nondepleted We find that maximum power available conversion from waves signal resulting a third-order nonlinearity depends on index mismatch and required achieving possible transfer is function frequency shift.
Deep learning (DL), a class of approaches involving self-learned discriminative features, is increasingly being applied to digital pathology (DP) images for tasks such as disease identification and segmentation tissue primitives (eg, nuclei, glands, lymphocytes). One application DP in telepathology, which involves digitally transmitting slides over the Internet secondary diagnosis by an expert at remote location. Unfortunately, places benefiting most from telepathology often have poor...
The escalating degradation of urban eco-environments has underscored the significance ecological security in sustainable development. Green infrastructure bridges green spaces cities and increases ecosystem connectivity, thereby optimizing patterns. This study uses Nanjing as a case adopts research paradigm that involves identifying sources, constructing resistance surfaces, subsequently extracting corridors within pattern. method amalgamates evaluation supply demand, leading to...
Exact solutions to the equations describing general nonlinear four-wave mixing (including parametric and three-wave sum-frequency generation) in optical fibers are presented. This complements our earlier research on four-photon [ Opt. Lett.14, 87 ( 1989)].
It is shown that the black solitons in an optical fiber or a uniform medium with arbitrary nonlinearity are all stable. The conclusion from analytical stability analysis consistent of numerical simulations. This then dismisses previous criterion suggests saturable nonlinear can be unstable.
Propagation of dark solitons in nonlinear media that include gain and loss is investigated. Two-photon absorption shown to lead dark-soliton broadening attenuation, whereas (such as arising from stimulated Raman scattering) their narrowing amplification. The relations describing the adiabatic evolution weakly perturbed are presented. In comparison with fundamental bright solitons, be less sensitive perturbations. Stationary propagation also found possible presence both amplification, but it...
Weijie Chen, Yongzhu Chang, Rongsheng Zhang, Jiashu Pu, Guandan Le Yadong Xi, Yijiang Chang Su. Proceedings of the 60th Annual Meeting Association for Computational Linguistics (Volume 1: Long Papers). 2022.
Spatial solitons of Maxwell's equations propagating in an isotropic Kerr material differ significantly from the classical soliton nonlinear Schrödinger equation unless electric field is linearly polarized along a geometric axis intensity pattern. In general polarization state changes continuously as beam propagates, with period millimeters for highly materials. This effect due to form birefringence soliton-induced waveguide. Equivalently, composed both TE and TM modes axially uniform...
Abstract Metaphor has significant implications for revealing cognitive and thinking mechanisms. Visual metaphor image generation not only presents metaphorical connotations intuitively but also reflects AI’s understanding of through the generated images. This paper investigates task generating images based on text with visual metaphors. We explore create a dataset containing sentences Then, we propose framework understanding, which is more tailored to essence metaphor, better utilizes...
Abstract Batch effects (BEs) refer to systematic technical differences in data collection unrelated biological variations whose noise is shown negatively impact machine learning (ML) model generalizability. Here we release CohortFinder ( http://cohortfinder.com ), an open-source tool aimed at mitigating BEs via data-driven cohort partitioning. We demonstrate improves ML performance downstream digital pathology and medical image processing tasks. freely available for download cohortfinder.com.
Visual scoring of tubular damage has limitations in capturing the full spectrum structural changes and prognostic potential. We investigate if computationally quantified features can enhance prognostication reveal spatial relationships with interstitial fibrosis.