Elastic scattering spectroscopy for detection of cancer risk in Barrett's esophagus: experimental and clinical validation of error removal by orthogonal subtraction for increasing accuracy.
Elastic scattering spectroscopy for detection of cancer risk in Barrett's esophagus: experimental and clinical validation of error removal by orthogonal subtraction for increasing accuracy.
复制标题
用于检测巴雷特食管癌症风险的弹性散射光谱：通过正交减法消除误差以提高准确性的实验和临床验证。
DOI：
10.1117/1.3194291
复制
发表时间：
2009
影响因子：
3.5
通讯作者：
Lovat,LaurenceB
中科院分区：
文献类型：
--
作者：
Zhu,Ying;Fearn,Tom;Mackenzie,Gary;Clark,Ben;Dunn,JasonM;Bigio,IrvingJ;Bown,StephenG;Lovat,LaurenceB
Elastic scattering spectroscopy (ESS) may be used to detect high-grade dysplasia (HGD) or cancer in Barrett’s esophagus (BE). When spectra are measuredin vivoby a hand-held optical probe, variability among replicated spectra from the same site can hinder the development of a diagnostic model for cancer risk. An experiment was carried out on excised tissue to investigate how two potential sources of this variability, pressure and angle, influence spectral variability, and the results were compared with the variations observed in spectra collectedin vivofrom patients with Barrett’s esophagus. A statistical method called error removal by orthogonal subtraction (EROS) was applied to model and remove this measurement variability, which accounted for 96.6% of the variation in the spectra, from thein vivodata. Its removal allowed the construction of a diagnostic model with specificity improved from 67% to 82% (with sensitivity fixed at 90%). The improvement was maintained in predictions on an independentin vivodata set. EROS works well as an effective pretreatment for Barrett’sin vivodata by identifying measurement variability and ameliorating its effect. The procedure reduces the complexity and increases the accuracy and interpretability of the model for classification and detection of cancer risk in Barrett’s esophagus.
