ContraReg:多模式的对比学习无监督可变形图像注册
Neel Dey1, Jo Schlemper2, Seyed Sadegh Mohseni Salehi2
1Department of Computer Science & Engineering, New York University, Brooklyn, NY, USA.
概括
ContraReg使用无监督的对比学习进行多模式可变形的注册,提高了对齐准确度. 这种新的方法可以学习强大的表示,用于非刚性医疗图像对齐,而无需手动功能工程.
科学领域:
- 医疗图像分析 医疗图像分析
- 计算机视觉 计算机视觉 计算机视觉
- 机器学习 机器学习
背景情况:
- 多模式注册对于整合不同成像类型的信息至关重要.
- 现有的方法难以处理复杂的变形和非线性强度变化.
- 当前的技术往往需要对特定任务进行重新设计,并且可能缺乏稳定性.
研究的目的:
- 引入ContraReg,一种无监督的对比表示学习方法,用于多模式可变形注册.
- 克服传统注册技术在处理非线性关系和变形方面的局限性.
- 为了在不同的成像领域实现准确和强大的非刚性对齐.
主要方法:
- ContraReg将多个规模的本地补丁特征项目纳入一个共享的嵌入空间.
- 使用无监督的对比学习来学习域不变表示.
- 应用学习的表示方式,用于非刚性多模式图像对齐.
主要成果:
- ContraReg 证明了准确而强大的注册性能.
- 在实验中实现了光滑和可逆变形.
- 在新生儿T1-T2脑MRI注册任务中表现优于基线.
- 通过各种变形调节强度验证.
结论:
- ContraReg提供了一种有效的无监督方法,用于多模式可变形注册.
- 学习的表示方便了强大的非刚性对齐,无需手动的特征工程.
- 该方法在需要跨模式调整的多种医学成像应用中显示出前景.
相关概念视频
Deformation of Member under Multiple Loadings
187
When a rod is made of different materials or has various cross-sections, it must be divided into parts that meet the necessary conditions for determining the deformation. These parts are each characterized by their internal force, cross-sectional area, length, and modulus of elasticity. These parameters are then used to compute the deformation of the entire rod.
In the case of a member with a variable cross-section, the strain is not constant but depends on the position. The deformation of an...
In the case of a member with a variable cross-section, the strain is not constant but depends on the position. The deformation of an...
187
Deconvolution
188
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
188


