相关实验视频

Updated: May 15, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

一本教科书治疗领域转移的方法:医学图像分析的知识先验

Yue Yang¹, Mona Gandhi¹, Yufei Wang¹

¹University of Pennsylvania.

Advances in neural information processing systems

|May 12, 2025

概括

深度学习模型与医疗图像领域的转变作斗争. 引入知识增强的瓶 (KnoBo) 整合了医学知识,显著改善了跨不同数据集的模型概括性,并减少了对数据变异的敏感性.

科学领域:

人工智能的人工智能
医学成像分析医学成像分析
计算机视觉计算机视觉

背景情况:

深度学习模型在自然图像方面表现出色,但由于域移动,医疗扫描通常会失败.
现有的视觉骨干缺乏在医学成像中可靠的概括的建筑先验.
域名转移包括不同医院或人口统计学混因素 (性别,种族) 的变化.

研究的目的:

为了研究模型对医学成像领域转移的敏感性.
开发一种新的深度学习方法,将明确的医学知识纳入其中,以提高概括性.
提高AI模型在分析胸部X射线和皮肤病变图像方面的可靠性.

主要方法:

引入知识增强的瓶 (KnoBo),一个概念瓶模型,整合医疗知识的先验.
使用检索增强语言模型来定义概念空间和训练概念识别.
在20个数据集中对KnoBo进行评估,其中包括多种领域转移和两种成像模式.

主要成果:

在混杂的数据集上,KnoBo显著优于微调模型的性能,平均提高了32.4%.
公共医学 (PubMed) 成为一个高效的知识资源,在信息多样性和预测性能方面超越其他资源.
拟议的方法表明医疗AI模型对领域转移的敏感性降低.

结论:

通过KnoBo集成明确的医学知识,提高了医学成像中的深度学习模型概括性.
KnoBo提供了一个框架,用于为临床应用构建更强大,更可靠的AI系统.
在临床相关性和减轻领域转移问题方面,PubMed是建立人工智能模型的宝贵资源.

更多相关视频

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

相关概念视频

Magnetic Resonance Imaging

Magnetic Resonance Imaging

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...

Positron Emission Tomography

Positron Emission Tomography

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...