Machine learning paired with photoacoustic microscopy and ultrasound for improved rectal cancer imaging

Tech ID: T-019449

Technology Description:

Researchers led by Quing Zhu at Washington University have developed a method for imaging rectal tumors using photoacoustic microscopy and ultrasound with a machine learning component. This method is better able to differentiate residual cancer from healthy tissue following chemotherapy and radiation.

The inventors have developed an endorectal probe to enable photoacoustic microscopy coregistered with ultrasound (PAM/US) to observe the submucosal vasculature. They also trained a convolutional neural network capable of using the imaging data to predict residual tumor presence, with an AUC of 0.98. This imaging system is able to accurately classify tissue as healthy or tumor even in the presence of heavy scarring, unlike MRIs. By more accurately identifying healthy tissue, the system could reduce the number of unnecessary surgical resections.