Search

There is currently no standard screening technique for oral cancer and its precursors other than visual identification and biopsy of suspicious lesions. To aid noninvasive early detection of oral neoplasia in vivo, we previously developed a molecular-specific contrast agent targeted against epidermal growth factor receptor. Here, we present a simple fluorescence spectroscopy system to detect the presence of this contrast agent in biological models representative of living tissues in order to demonstrate the feasibility of using a spectroscopy system in conjunction with a contrast agent as a screening technique for oral cancer. The spectroscopy system was tested for the ability to detect the contrast agent in four in vitromodels: multilayer tissue phantoms made of cells pre-labeled with the contrast agent, multilayer tissue phantoms labeled with the contrast agent from the surface in conjunction with a permeability-enhancing agent, fresh tissue slices from normal and abnormal oral cavity biopsies, and whole normal and abnormal oral cavity biopsies. The optical signal from samples labeled with the contrast agent was 3–32 times stronger compared to controls and was detected with a signal-to-noise ratio greater than 10. These results demonstrate that an inexpensive and simple spectroscopy system can be used in biological models of living systems to detect the optical signal from a contrast agent targeted toward a cancer-related biomarker with good signal-to-noise ratios. Coupling inexpensive fluorescence spectrometers with molecular-specific contrast agents has the potential to improve the early detection of oral neoplasia by providing a low-cost screening tool.

Abstract: To successfully translate genomic classifiers to the clinical practice, it is essential to obtain reliable and reproducible measurement of the classifier performance. A point estimate of the classifier performance has to be accompanied with a measure of its uncertainty. In general, this uncertainty arises from both the finite size of the training set and the finite size of the testing set. The training variability is a measure of classifier stability and is particularly important when the training sample size is small. Methods have been developed for estimating such variability for the performance metric AUC (area under the ROC curve) under two paradigms: a smoothed cross-validation paradigm and an independent validation paradigm. The methodology is demonstrated on three clinical microarray datasets in the microarray quality control consortium phase two project (MAQC-II): breast cancer, multiple myeloma, and neuroblastoma. The results show that the classifier performance is associated with large variability and the estimated performance may change dramatically on different datasets. Moreover, the training variability is found to be of the same order as the testing variability for the datasets and models considered. In conclusion, the feasibility of quantifying both training and testing variability of classifier performance is demonstrated on finite real-world datasets. The large variability of the performance estimates shows that patient sample size is still the bottleneck of the microarray problem and the training variability is not negligible. [Copyright &y& Elsevier]