Výsledky vyhledávání

Report

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

Autor: Jiang, Aofan, Huang, Chaoqin, Cao, Qing, Xu, Yuchen, Zeng, Zi, Chen, Kang, Zhang, Ya, Wang, Yanfeng

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 pretrai

Externí odkaz: http://arxiv.org/abs/2408.17154

Zobrazit plný text záznamu

Report

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

Autor: Jiang, Aofan, Huang, Chaoqin, Cao, Qing, Xu, Yuchen, Zeng, Zi, Chen, Kang, Zhang, Ya, Wang, Yanfeng

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 coul

Externí odkaz: http://arxiv.org/abs/2404.04935

Zobrazit plný text záznamu

Report

Accelerating Distributed Deep Learning using Lossless Homomorphic Compression

Autor: Li, Haoyu, Xu, Yuchen, Chen, Jiayi, Dwivedula, Rohit, Wu, Wenfei, He, Keqiang, Akella, Aditya, Kim, Daehyeok

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 soluti

Externí odkaz: http://arxiv.org/abs/2402.07529

Zobrazit plný text záznamu

Report

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

Autor: Xu, Yuchen, Thomas, Andrew M., Crozier, Peter A., Matteson, David S.

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 sequ

Externí odkaz: http://arxiv.org/abs/2302.00816

Zobrazit plný text záznamu

Report

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

Autor: Thomas, Andrew M., Crozier, Peter A., Xu, Yuchen, Matteson, David S.

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 trans

Externí odkaz: http://arxiv.org/abs/2209.13584

Zobrazit plný text záznamu

Akademický článek

Therapeutic effects of tofacitinib on steroid-resistant immune checkpoint inhibitor-associated myocarditis

Autor: XU Yuchen, ZHANG Jian, WANG Yan, LIN Jinyi, ZHOU Yuhong, CHENG Leilei, GE Junbo

Publikováno v: Zhongguo aizheng zazhi, Vol 34, Iss 4, Pp 400-408 (2024)

Background and purpose: Outcomes for cancer patients with steroid-resistant immune checkpoint inhibitor-associated myocarditis (srICIAM) are poor. Intensified immunosuppressive therapies, including tofacitinib, a novel Janus kinase (JAK) inhibitor, m

Externí odkaz: https://doaj.org/article/3794bb51c60249e5adb22d6060ea3671