Related Experiment Video For artificial neural networks
Updated: Aug 28, 2025

Longitudinal Intravital Imaging of Brain Tumor Cell Behavior in Response to an Invasive Surgical Biopsy
Published on: May 3, 2019
DEEP Surveillance of Brain Cancer Using Self-Functionalized 3D Nanoprobes for Noninvasive Liquid Biopsy
Srilakshmi Premachandran1,2,3,4, Rupa Haldavnekar1,2,3,4, Sunit Das5,6
1Institute for Biomedical Engineering, Science and Technology (I BEST), Partnership between Toronto Metropolitan University (formerly Ryerson University) and St. Michael's Hospital, Toronto, Ontario M5B 1W8, Canada.
Abstract:
Brain cancers, one of the most fatal malignancies, require accurate diagnosis for guided therapeutic intervention. However, conventional methods for brain cancer prognosis (imaging and tissue biopsy) face challenges due to the complex nature and inaccessible anatomy of the brain. Therefore, deep analysis of brain cancer is necessary to (i) detect the presence of a malignant tumor, (ii) identify primary or secondary origin, and (iii) find where the tumor is housed. In order to provide a diagnostic technique with such exhaustive information here, we attempted a liquid biopsy-based deep surveillance of brain cancer using a very minimal amount of blood serum (5 μL) in real time. We hypothesize that holistic analysis of serum can act as a reliable source for deep brain cancer surveillance. To identify minute amounts of tumor-derived material in circulation, we synthesized an ultrasensitive 3D nanosensor, adopted SERS as a diagnostic methodology, and undertook a DEEP neural network-based brain cancer surveillance. Detection of primary and secondary tumor achieved 100% accuracy. Prediction of intracranial tumor location achieved 96% accuracy. This modality of using patient sera for deep surveillance is a promising noninvasive liquid biopsy tool with the potential to complement current brain cancer diagnostic methodologies.

