Zhixin Xu

Transformer-based fast image reconstruction for high fidelity MR knee imaging: an evaluation study

Yajing Zhang, Zhixin Xu, Jin Qi

Motivation: Address the challenges of prolonged MRI reconstruction, especially in knee imaging, to enhance clinical efficiency. Goal(s): Develop an efficient knee MRI reconstruction framework utilizing the transformer-based deep learning approach to improve image quality allowing reduced scan time. Approach: Employ the transformer-based …

Model Discrepancy Learning: Synthetic Faces Detection Based on Multi-Reconstruction

Qingchao Jiang, Zhixin Xu, Zhiying Zhu, Ning Chen et autres

Advances in image generation enable hyper-realistic synthetic faces but also pose risks, thus making synthetic face detection crucial. Previous research focuses on the general differences between generated images and real images, often overlooking the discrepancies among various generative techniques. In this paper, …

cn (code pays fourni par la source)

CCNet: A Cross‐Channel Enhanced CNN for Blind Image Denoising

Minling Zhu, Zhixin Xu

ABSTRACT Nowadays, blind image denoising with deep convolutional neural network (CNN) is one of the research hotspots in the field of image denoising. Relying on the convolutional operation and respective field, CNN is excellent in processing local information. However, this also brings …

cn (code pays fourni par la source)

GCSTormer: Gated swin transformer with channel weights for image denoising

Minling Zhu, Zhixin Xu, Qi Zhang, Yonglin Liu et autres

cn, tw, gb (code pays fourni par la source)

A Multi-contrast Cardiac MRI Reconstruction Method Using an Advanced Unrolled Network Architecture

Yajing Zhang, Yanxin Huang, Zhixin Xu, Jin Qi

cn (code pays fourni par la source)

Cross-Domain Denoising for Low-Dose Multi-Frame Spiral Computed Tomography

Yucheng Lu, Zhixin Xu, Moon Hyung Choi, Jimin Kim et autres

Computed tomography (CT) has been used worldwide as a non-invasive test to assist in diagnosis. However, the ionizing nature of X-ray exposure raises concerns about potential health risks such as cancer. The desire for lower radiation doses has driven researchers to improve …

kr, dk (code pays fourni par la source)

Wafmf: Weighted Adaptive Frequency Median Filter for Salt-and-Pepper Noise Denoising

Minling Zhu, Zhixin Xu, Chunwei Tian

CAWM: Class-Aware Weight Map for Improved Semi-Supervised Nuclei Segmentation

Seohoon Lim, Zhixin Xu, Yosep Chong, Seung‐Won Jung

Due to the rich histopathological information of nuclei in whole slide images, nuclei segmentation becomes essential for medical analysis. Since collecting sufficient pixel-wise annotations for supervised training of nuclei segmentation networks is challenging, semi-supervised nuclei segmentation methods have been extensively studied. In …

kr (code pays fourni par la source)

Exploring 3D U-Net Training Configurations and Post-Processing Strategies for the MICCAI 2023 Kidney and Tumor Segmentation Challenge

Kwang-Hyun Uhm, Hyunjun Cho, Zhixin Xu, Seohoon Lim et autres

In 2023, it is estimated that 81,800 kidney cancer cases will be newly diagnosed, and 14,890 people will die from this cancer in the United States. Preoperative dynamic contrast-enhanced abdominal computed tomography (CT) is often used for detecting lesions. However, there exists …

Reversed domain adaptation for nuclei segmentation-based pathological image classification

Zhixin Xu, Seohoon Lim, Yucheng Lu, Seung‐Won Jung

kr, jp (code pays fourni par la source)

Cross-domain Denoising for Low-dose Multi-frame Spiral Computed Tomography

Yucheng Lu, Zhixin Xu, Moon Hyung Choi, Jimin Kim et autres

Computed tomography (CT) has been used worldwide as a non-invasive test to assist in diagnosis. However, the ionizing nature of X-ray exposure raises concerns about potential health risks such as cancer. The desire for lower radiation doses has driven researchers to improve …

kr, dk (code pays fourni par la source)

Risk-aware survival time prediction from whole slide pathological images

Zhixin Xu, Seohoon Lim, Hong-Kyu Shin, Kwang-Hyun Uhm et autres

Deep-learning-based survival prediction can assist doctors by providing additional information for diagnosis by estimating the risk or time of death. The former focuses on ranking deaths among patients based on the Cox model, whereas the latter directly predicts the survival time of …

kr (code pays fourni par la source)