Fei Xia

Identifying Imaging Follow-Up in Radiology Reports: A Comparative Analysis of Traditional ML and LLM Approaches

Namu Park, Giridhar Kaushik Ramachandran, Kevin Lybarger, Fei Xia et autres

Large language models (LLMs) have shown considerable promise in clinical natural language processing, yet few domain-specific datasets exist to rigorously evaluate their performance on radiology tasks. In this work, we introduce an annotated corpus of 6,393 radiology reports from 586 patients, each …

Hyperspectral Band Selection with Learnable Weights for Efficient Glioblastoma Detection

Albert Li, Jacob Yih-Jer Wu, Li Lei, Linda Shi et autres

Hyper-spectral imaging (HSI) provides rich spatial-spectral information for medical diagnostics, but faces challenges due to its extremely high dimensionality and computational overhead. We focus on glioblastoma detection using HSI patches and propose an adaptive band selection approach with learnable weights embedded in …

us, pe (code pays fourni par la source)

Structural nonlinear optical encoding with multiple scattering for high-level learning tasks

Fei Xia

Optical information processing and computing promise enhanced performance, scalability, and energy efficiency, but achieving nonlinearity—a key computation component— remains challenging. We present a new design that uses a multiple-scattering cavity to induce structural optical nonlinear encoding with a low-power continuous-wave laser. Each …

us (code pays fourni par la source)

On-chip programmable nonlinearity

Fei Xia

us (code pays fourni par la source)

Disulfiram alleviates epithelial barrier disruption in ozone-induced chronic obstructive pulmonary disease mouse models via inhibiting Gasdermin D-mediated pyroptosis

Jianwei Gao, Lei Han, Yingying Zhang, Xue Zhang et autres

cn (code pays fourni par la source)

Time-domain resolution enhanced fiber loop ring-down system based on microwave photonics for pressure and curvature measurement

Fei Xia, Lingge Gao, Jingzhan Shi, Dan Zhu et autres

A dual-channel fiber loop ring-down (FLRD) sensing system with enhanced time-domain resolution based on microwave photonics is proposed and experimentally demonstrated. The integration of FLRD and microwave photonics enables fast response, high SNR and pure frequency domain measurement compared to traditional time-domain …

Replica-Assisted Super-Resolution Fluorescence Imaging in Scattering Media

Tengfei Wu, YoonSeok Baek, Fei Xia, Sylvain Gigan et autres

Far-field super-resolution fluorescence microscopy has been rapidly developed for applications ranging from cell biology to nanomaterials. However, it remains a significant challenge to achieve super-resolution imaging at depth in opaque materials. In this study, we present a super-resolution microscopy technique for imaging …

fr, es, cn (code pays fourni par la source)

Simultaneous 2-photon and 3-photon excitation with a red fluorescent protein-cyanine dye probe pair in the 1700-nm excitation window for deep in vivo neurovascular imaging

Fei Xia, David Sinefeld, Zong Chang, Xiaojing Gong et autres

In vivo imaging of the neurovascular network is considered to be one of the most powerful approaches for understanding brain functionality. Nevertheless, simultaneously imaging the biological neural network and blood vessels in deep brain layers in a non-invasive manner remains to a …

us, fr, il, cn, de, kr (code pays fourni par la source)

Microscopy at a glance: New poster article series exploring the intersection of art, science and imaging

Kirti Prakash, Christian Franke, Fei Xia, Nabanita Chatterjee et autres

nl, de, fr (code pays fourni par la source)

Optical wavefront shaping in deep tissue using photoacoustic feedback

Fei Xia, Ivo T. Leite, Robert Prevedel, Thomas Chaigne

Abstract Over the past decade, optical wavefront shaping has been developed to focus light through highly opaque scattering layers, opening new possibilities for biomedical applications. To probe light intensity deep inside soft scattering media such as biological tissues, internal guide-stars are required. …

fr, de (code pays fourni par la source)

Research on sound recognition algorithm for home environment based on residual neural network

mingde zhou, Fei Xia, Xiang Zhao

This paper proposes a sound recognition algorithm for home environment based on deep learning. This algorithm uses the fusion feature extraction method to fuse the two feature extraction methods GFCC and FBank, and uses the fused feature value as the input of …

cn (code pays fourni par la source)

Nonlinear optical encoding enabled by recurrent linear scattering

Fei Xia, Kyungduk Kim, Yaniv Eliezer, Seung Yun Han et autres

Optical information processing and computing can potentially offer enhanced performance, scalability and energy efficiency. However, achieving nonlinearity-a critical component of computation-remains challenging in the optical domain. Here we introduce a design that leverages a multiple-scattering cavity to passively induce optical nonlinear random …

fr, us (code pays fourni par la source)