Perception-Based Detection of an Ovarian Cancer Disease Fingerprint

Project summary

Ovarian cancer is difficult to treat especially because it is usually diagnosed at later stages. A better detection method for early-stage ovarian cancer would markedly improve survival rates and the quality of life for many women. Serum biomarker measurements are widely used for diagnosis of ovarian cancer and many other diseases, but these methods provide low sensitivity and specificity, especially if used for screening. Therefore, innovative approaches to improve detection are needed. We believe that the differentiation of diseased from normal biofluids may be achieved by the detection of a “disease fingerprint” through the collection of large data sets of molecular binding interactions to a set of sensors. We are building sensor arrays comprising modified carbon nanotubes (called organic color centers, OCCs) to accomplish this. In preliminary experiments, we found that a library of our nanosensors, using machine learning algorithms, reliably identified late stage ovarian cancer substantially better than the established, FDA-approved methods. We propose to further develop and validate sensor platform to enable the accurate screening of ovarian cancer. If successful, this sensor technology would be game-changing. It would substantially lower the rate of ovarian cancer patient deaths, and it could be rapidly adapted to the detection of many other diseases.

This grant was made possible in part by generous donations from The Edmée Firth Fund for Research in Ovarian Cancer (EFFROC); and The Teal Foundation.