用贝叶斯频率重新参数化扩大3D内核,用于医疗图像分割
Ho Hin Lee1, Quan Liu1, Shunxing Bao1
1Department of Computer Science, Vanderbilt University, Nashville, TN 37212, USA.
概括
RepUX-Net是一种新的卷积神经网络 (CNN) 架构,通过优化大型内核卷积来增强医疗图像细分. 这种方法在多个数据集中实现了最先进的性能,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
- 深度学习架构 深度学习架构
背景情况:
- 卷积神经网络 (CNN) 中的大内核 (LK) 尺寸旨在增加医疗图像细分的有效受体场 (ERF).
- 然而,性能和和降解发生在过大的内核中,阻碍了最佳的局部学习.
- 结构重新参数化 (SR) 提高了与小内核的融合,但可能会影响计算效率.
研究的目的:
- 提出RepUX-Net,一种纯粹的CNN架构,利用一种新的大型内核块设计来改进医疗图像细分.
- 为了解决传统的大型内核卷积的局限性,并增强融合特性.
- 为了与现有的最先进的 (SOTA) 分段网络竞争并超越它们.
主要方法:
- 开发了RepUX-Net,这是一个CNN架构,具有简单但有效的大型内核块.
- 导出了内核重新参数化和内核融合变量之间的等价值.
- 引入了以空间频率为灵感的元素智能内核收变化,并将其建模为培训期间重量重新参数化的贝叶斯前置.
- 使用一个反向函数来估计频率加权值用于在随机梯度下降中重新缩放内核元素.
主要成果:
- 在6个具有挑战性的公共数据集中,RepUX-Net与3D SOTA基准测试相比表现优越.
- 在内部验证 (FLARE),外部验证 (MSD,KiTS,LiTS,TCIA) 和转移学习 (AMOS) 场景中取得了持续的改进.
- 持续优于现有方法,展示了拟议的大型内核块设计和重新参数化策略的有效性.
结论:
- RepUX-Net为医疗图像细分提供了一种具有竞争力和高效的替代方案,其性能优于当前的SOTA方法.
- 提出的方法有效地解决了大型内核卷积的局限性,通过结合空间频率启发的重新参数化.
- 该架构为基于深度学习的医学图像分析的未来研究提供了坚实的基础.
相关概念视频
Computed Tomography
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
Imaging Studies III: Computed Tomography
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...


