YNetr：基于平面扫描肝脏肿瘤的双编码器架构
摘要
背景：肝脏肿瘤是肝脏的异常生长，可为良性或恶性，肝癌为全球范围内的重大健康问题。然而，目前尚无针对平面扫描肝脏肿瘤的分割数据集或相关算法。为填补这一空白，我们提出Plain Scan Liver Tumors(PSLT)数据集和YNetr模型。方法：组建并注释了40个肝脏肿瘤平面扫描分割数据集。同时，我们采用Dice系数作为评估YNetr分割结果的指标，利用小波变换捕获不同频率信息。结果：YNetr模型在PSLT数据集上实现62.63%的Dice系数，相较于其他公开模型提高1.22%的准确率。我们针对多种模型进行了比较评估，包括UNet 3+、XNet、UNetr、Swin UNetr、Trans-BTS、COTr、nnUNetv2（2D）、nnUNetv2（3D fullres）、MedNext（2D）和MedNext（3D fullres）。结论：我们不仅提出了名为PSLT（Plain Scan Liver Tumors）的数据集，还探索了一种名为YNetr的结构，利用小波变换提取不同频率信息，该结构在PSLT上实现了最佳结果。
引用
@article{arxiv.2404.00327,
title = {YNetr: Dual-Encoder architecture on Plain Scan Liver Tumors (PSLT)},
author = {Wen Sheng and Zhong Zheng and Jiajun Liu and Han Lu and Hanyuan Zhang and Zhengyong Jiang and Zhihong Zhang and Daoping Zhu},
journal= {arXiv preprint arXiv:2404.00327},
year = {2024}
}
备注
My academic research interests have undergone significant changes. I believe that continuing to retain the paper is no longer in line with my academic development path, and may also mislead readers. And some of the content may involve the boundaries of personal privacy. To respect and protect the privacy of relevant personnel, I decided to withdraw it to avoid any unnecessary controversy or harm