English
全部
搜索
图片
视频
地图
资讯
Copilot
更多
购物
航班
旅游
笔记本
Top stories
Sports
U.S.
Local
World
Science
Technology
Entertainment
Business
More
Politics
时间不限
过去 1 小时
过去 24 小时
过去 7 天
过去 30 天
最佳匹配
最新
生物通
3 个月
基于注意力U-Net与混合损失函数的COVID-19肺部CT病灶自动分割研究
本研究针对COVID-19肺部CT影像中病灶对比度低、分割难度大的问题,提出了一种结合CLAHE预处理、注意力U-Net架构和混合Dice-Tversky损失函数的自动分割框架。通过5折交叉验证,模型在公开数据集上达到Dice分数0.83、IoU 0.71的优异性能,并结合Grad-CAM可视化技术增强 ...
一些您可能无法访问的结果已被隐去。
显示无法访问的结果
今日热点
2026 Kentucky Derby winner
CA, AZ, NV announce river plan
WHO: Suspected virus kills 3
GameStop plans to buy eBay
Tops box office
Steps down after US charges
UKR strikes Russian oil port
Reach deal to sell team
USF campus science lab fire
Reviewing Iran’s new proposal
Ship attacked near Hormuz?
Indianapolis shooting
Wins F1 Miami Grand Prix
War Horse actor dies
Ex-NYC mayor hospitalized
CA AG sues kratom maker
Rubio to visit Vatican, Italy
Peru seeks election audit
US troops missing in Morocco
Wins TX SD 4 special election
Racing icon Zanardi dies
OKs plan to buy F-35, F-15I
4 charged in NJ voting case
Endorses Rep. Andy Barr
Shakira free show draws 2M
Flight strikes light pole
Texas apartment shooting
Reaches deal with studios
US warns shipping firms
OR health club crash kills 1
IU football team to visit WH
反馈