从ONH OCT扫描中提取基于CNN的设备不可知特征.
Sjoerd J Driessen1,2, Karin A van Garderen1,2,3, Danilo Andrade De Jesus4,5,6
1Department of Ophthalmology, Erasmus Medical Center, Rotterdam, The Netherlands.
Translational vision science & technology
|December 3, 2024
概括
这项研究引入了一种人工智能方法,用于从跨设备的光连贯性断层扫描 (OCT) 来进行一致的光神经头部 (ONH) 测量. 人工智能方法提高了视网膜神经纤维层 (RNFL) 和最小边宽 (MRW) 生物标志物的可靠性,有助于研究和患者护理.
科学领域:
- 眼科医生 眼科 眼科
- 医疗成像医学成像
- 人工智能的人工智能
背景情况:
- 使用光连贯断层扫描 (OCT) 测量视神经头部 (ONH) 的测量在不同的设备之间有很大的差异.
- 这种缺乏可互换性使患者监测变得复杂,并阻碍了眼科领域的合作研究工作.
- 现有的制造商特定算法限制了来自海外的生物标志物的一致性和可比性.
研究的目的:
- 开发和验证一种设备无关的人工智能 (AI) 方法,用于从OCT扫描中提取ONH生物标志物.
- 评估人工智能提取的生物标志物的可靠性,与多个OCT设备的制造商特定算法相比.
主要方法:
- 来自海德堡SPECTRALIS,ZEISS CIRRUS HD-OCT 5000和Topcon 3D OCT设备的以ONH为中心的OCT卷进行了注释.
- 一个卷积神经网络 (CNN) 在细分B扫描上受训,以提取像视网膜神经纤维层 (RNFL) 和最小边缘宽度 (MRW) 这样的生物标志物.
- 通过使用独立的测试集,将CNN衍生的生物标志物值与设备之间的比较以及与制造商报告的值进行比较.
主要成果:
- 与制造商值相比,人工智能方法在环囊性RNFL (cpRNFL) 测量中显示出更高的可靠性.
- 对AI衍生cpRNFL的类内相关系数 (ICC) 在不同设备和扫描参数中分别为0.667和0.656.
- 由人工智能获得的最小边框宽度 (MRW) 测量显示,设备之间 (ICC = 0.917) 和制造商值 (ICC = 0.983) 之间有很好的一致性.
结论:
- 开发的设备无关人工智能方法为提取ONH OCT生物标志物,特别是cpRNFL提供了更可靠的方法.
- 使用人工智能方法,MRW测量显示在不同OCT设备之间具有很强的一致性.
- 这种开源软件提供了一个强大的解决方案,用于一致的生物标志物提取,减少对制造商算法的依赖,并有利于临床实践和研究.
更多相关视频
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...
Extraction: Advanced Methods
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is formed in...


