A Novel Tissue Identification Framework in Cataract Surgery Using an Integrated Bioimpedance-Based Probe and Machine Learning Algorithms.
A Novel Tissue Identification Framework in Cataract Surgery Using an Integrated Bioimpedance-Based Probe and Machine Learning Algorithms.
复制标题
使用基于生物阻抗的集成探针和机器学习算法的白内障手术中的新型组织识别框架。
DOI：
10.1109/tbme.2021.3109246
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Rosen,Jacob
中科院分区：
文献类型：
--
作者：
AghajaniPedram,Sahba;Ferguson,Peter;Gerber,Matthew;Shin,Changyeob;Hubschman,J-P;Rosen,Jacob
这项工作的目的是开发和实验验证一个生物阻抗为基础的框架，以确定组织接触的手术仪器在白内障surgery.MethodsThis工作介绍了一个集成的硬件和软件解决方案的基础上独特的生物阻抗不同的眼内组织。开发的硬件可以很容易地与常用的手术器械集成。所提出的软件框架，其中包括数据采集和机器学习分类器，是足够快的实时手术干预部署。实验方案包括生物阻抗数据收集从31ex vivopig眼睛针对四个眼内组织：虹膜，角膜，透镜，andVitald.ResultsA分类器的基础上支持向量机表现出91%的整体准确性在所有试验。该算法在检测透镜的眼内组织方面提供了实质性的性能，具有100%的可靠性和95%的灵敏度，沿着，对玻璃体的可靠性为88%，敏感性为94%。结论所开发的基于阻抗的框架证明了成功的眼内组织识别。通过透镜检测提高手术效果，可靠性100%。
ObjectiveThe objective of this work was to develop and experimentally validate a bioimpedance-based framework to identify tissues in contact with the surgical instrument during cataract surgery.MethodsThis work introduces an integrated hardware and software solution based on the unique bioimpedance of different intraocular tissues. The developed hardware can be readily integrated with commonly used surgical instruments. The proposed software framework, which encompasses data acquisition and a machine-learning classifier, is fast enough to be deployed in real-time surgical interventions. The experimental protocol included bioimpedance data collected from 31ex vivopig eyes targeting four intraocular tissues:Iris,Cornea,Lens, andVitreous.ResultsA classifier based on a support vector machine exhibited an overall accuracy of 91% across all trials. The algorithm provided substantial performance in detecting the intraocular tissues with 100% reliability and 95% sensitivity for the lens, along with 88% reliability and 94% sensitivity for the vitreous.ConclusionThe developed impedance-based framework demonstrated successful intraocular tissue identification.SignificanceClinical implications include the ability to ensure safe operations by detecting posterior capsule rapture with 94% probability and improving surgical efficacy through lens detection with 100% reliability.