不变内容表示用于可泛化的医疗图像细分.
Zhiming Cheng1, Shuai Wang2,3, Yuhan Gao1,4
1School of Automation, Hangzhou Dianzi University, Hangzhou, 310018, China.
Journal of imaging informatics in medicine
|May 17, 2024
概括
本研究介绍了一个不变内容表示网络 (ICRN),用于在不同领域进行强大的医疗图像细分. 该方法增强了对不变内容的学习,同时减少了风格过拟合,提高了细分的准确性.
科学领域:
- 医学图像分析 医学图像分析
- 计算机视觉 计算机视觉
- 机器学习 机器学习
背景情况:
- 医学成像中的域泛化 (DG) 对于保护隐私,单源学习至关重要.
- 现有的 DG 方法经常使用全球数据增强,限制多样性,并可能导致风格过度匹配.
- 这导致了医疗图像细分未见的目标域的低最佳稳定性.
研究的目的:
- 开发一种新的方法来增强不变的内容学习,并抑制医学图像细分中的风格变化.
- 提高训练在单个源域上的模型的稳定性和概括能力,以未见的目标域.
主要方法:
- 提出了一个不变内容表示网络 (ICRN),采用使用马校正的本地样式增强 (LSA).
- 引入了不变内容学习 (ICL),以从增强和源域样本中学习可概括的特征.
- 实现了风格对抗式学习 (SAL) 与域特定批量规范化 (DSBN) 以减轻源域风格偏差.
主要成果:
- 在跨领域数据集 (Fundus和前列腺) 的细分性能方面取得了显著的改进.
- 在整体子系数 (Dice) 中显示了8.74%和11.33%的增长.
- 与最先进的方法相比,总平均表面距离 (ASD) 减少了15.88mm和3.87mm.
结论:
- 拟议的ICRN方法有效地增强了医疗图像细分领域的泛化.
- 这种方法成功地平衡了不变的内容学习与风格抑制,从而在未见的领域取得了卓越的性能.
- 这项工作为开发更强大,更普遍的医疗图像细分模型提供了有前途的方向.
相关概念视频
01:29Positron Emission Tomography
4.2K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
4.2K
01:24Magnetic Resonance Imaging
5.1K
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...
5.1K