SUMMARY
UCLA researchers in the Department of Bioengineering have developed a method that utilizes snapshot hyperspectral imaging and machine learning for real-time and label-free imaging of cancerous tissue during a surgical procedure.
BACKGROUND
The use of autofluorescence imaging (AFI) and fluorescence imaging (FI) are standard-of-care endoscopic techniques for imaging tumor-specific contrast to help guide surgeons during surgery. However, AFI images suffer from low sensitivity and specificity in assessing tumor margins and while FI significantly improve tumor accuracy, it faces significant regulatory challenges since the number of FDA-approved fluorescent dyes are very limited. Furthermore, the expression of a molecular-specific dye in patients is heterogeneous and the expression can vary overtime. Therefore, there is a need for a new endoscopy method that provides high sensitivity and does not require the use of fluorescent labeling.
INNOVATION
UCLA researchers in the Department of Bioengineering developed a label-free, real-time hyperspectral imaging endoscopy method for molecular guided surgery. The method demonstrated high sensitivity and specificity for tumor detection without the use of fluorescent labeling. The method combined snapshot hyperspectral imaging and machine learning to implement a real-time data acquisition. Furthermore, it can be applied to standard clinical practice since it requires minimal modification to the established white-light surgical imaging procedure. The method can extend a surgeon’s vision at both the cellular and tissue level to improve the ability to identify the lesion and its margins.
POTENTIAL APPLICATIONS
ADVANTAGES
STATUS OF DEVELOPMENT
First description of complete invention