神经疾病诊断放射学中的可解释的人工智能:系统性审查,以及医生对它的看法.
Yasir Hafeez1, Khuhed Memon2, Maged S Al-Quraishi3
1Faculty of Science and Engineering, University of Nottingham, Jalan Broga, Semenyih 43500, Selangor Darul Ehsan, Malaysia.
Diagnostics (Basel, Switzerland)
|January 25, 2025
概括
可解释的人工智能 (XAI) 可能弥合了诊断放射学和临床实践中的AI之间的差距. 目前的研究将准确性优先于解释性,阻碍了采用.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 放射学 放射学是一门学科.
背景情况:
- 人工智能还没有被广泛纳入诊断医学或临床实践.
- 尽管计算机辅助诊断 (CAD) 工具的进步,但它们在医疗保健中的大规模采用仍然有限.
- 诊断放射学虽然利用像MRI和CT这样的先进成像技术,但尚未将AI驱动的扫描分析纳入标准程序.
研究的目的:
- 审查人工智能在开发用于神经障碍诊断大脑MRI分析系统方面的贡献.
- 强调包括可解释性的计算机辅助诊断 (CAD) 系统.
- 探索可解释的人工智能 (XAI) 是否可以成为在诊断放射学中采用AI的转折点.
主要方法:
- 对2017年至2024年的研究进行了全面的文献综述,重点是AI和脑MRI分析.
- 强调具有可解释性特征的CAD系统.
- 包括医学领域专家的意见和XAI在医学诊断中的挑战.
主要成果:
- 总结了47项研究,详细介绍了XAI技术,数据集和性能准确性.
- 讨论了审查的研究的优点和弱点.
- 七位国际医学专家的意见被介绍为指导人工智能工具开发.
结论:
- 目前的CAD研究重点是性能准确性,忽视了解释的真实性和有用性.
- 观察到缺乏可解释性基础真相数据,视觉解释方法占主导地位.
- 需要更全面,更像人类的解释来建立信任,同时解决法律,道德,安全和安全方面的问题.
相关概念视频
01:14Brain Imaging
204
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
204
01:24Magnetic Resonance Imaging
4.9K
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...
4.9K