作者: Miki Haifler , Isaac Pence , Yu Sun , Alexander Kutikov , Robert G Uzzo
关键词:
摘要: Renal mass biopsy is still controversial due to imperfect accuracy. Raman spectroscopy (RS) demonstrated promise as an in vivo real-time, nondestructive diagnostic tool many malignancies. Short wave infrared (SWIR) RS has the potential improve on previous systems for renal diagnosis. The aim of this study evaluate a SWIR system differentiating normal and malignant samples. Measurements were acquired using benchtop with excitation wavelength at 1064 nm InGaAs array detector. Processed spectra classified Bayesian machine learning algorithm, sparse multinomial logistic regression. Sensitivity receiver operating characteristic curve analyses evaluated classifier Accuracy was 92.5% sensitivity specificity 95.8% 88.8%, respectively. For posterior probability class assignment, area under ROC 0.94 (95% confidence interval: 0.89-0.99, P < .001). accurately differentiated kidney tumors. be used cancer.