一个域适应性深度对比网络用于磁共振成像驱动的膀癌症分类
Junjun Huang1,2,3, Haixia Hu4, Mengdan Sun5
1Department of Artificial Intelligence, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur, Malaysia.
NPJ digital medicine
|March 3, 2026
概括
这项研究引入了一个域自适应深度对比网络 (DADCNet),用于从MRI扫描中改进膀癌症的分类. DADCNet增强了跨中心的概括和分类准确性,解决了关键的临床部署挑战.
科学领域:
- 医学图像分析 医学图像分析
- 在瘤学中使用人工智能
- 尿道瘤学 尿道瘤学
背景情况:
- 膀癌具有显著的发病率和死亡率.
- 深度学习显示了通过MRI自动化膀癌症分类的潜力.
- 深度学习的临床应用受到数据差异和非肌肉侵入性膀癌 (NMIBC) 和肌肉侵入性膀癌 (MIBC) 之间的特征差异的阻碍.
研究的目的:
- 开发一种新的深度学习框架,即域自适应深度对比网络 (DADCNet),用于基于MRI的稳健膀癌症分类.
- 通过学习域不变表示来改进交叉中心概括.
- 通过提高特征可区分性来提高分类性能.
主要方法:
- 提出了一个域自适应深度对比网络 (DADCNet),集成源域和目标域数据用于特征学习.
- 采用深度对比的学习策略,以促进类间的分离性和类内紧性.
- 在多中心膀癌MRI数据集上验证了框架.
主要成果:
- 与现有的CNN和基于变压器的方法相比,DADCNet实现了更高的性能.
- 该模型获得了0.955的精度,0.955的F1得分和0.991.99的AUC.
- 证明了改进的交叉中心概括和特征可歧视性.
结论:
- DADCNet有效地解决了多中心MRI膀癌症分类方面的挑战.
- 拟议的域适应和对比学习方法导致更强大和更准确的分类.
- DADCNet显示出在膀癌诊断中临床部署的重大前景.
相关概念视频
01:24Magnetic Resonance Imaging
7.6K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
7.6K
01:27Imaging Studies IV: Magnetic Resonance Imaging
427
Introduction:Magnetic Resonance Imaging, or MRI, can include a specialized imaging technique of the urinary system known as Magnetic Resonance Urography (MRU). This radiation-free technique uses strong magnetic fields and radio waves to produce detailed images with the help of a computer. MRU is particularly effective for visualizing fluid-filled structures like the kidneys, ureters, and bladder.Applications of MRI in the Genitourinary SystemKidneys and Ureters: MRI detects tumors, cysts,...
427