The fluorescence of carbon nanotubes and machine learning create a ‘spectral fingerprint’ of a hard-to-diagnose cancer. (Credit: Lehigh University)

A new platform uses machine learning techniques to efficiently analyze spectral signatures of carbon nanotubes to detect biomarkers of ovarian cancer and to recognize the cancer itself. The perception-based nanosensor consisted of single-wall carbon nanotubes wrapped in strands of DNA.

The way in which the DNA was wrapped, and the variety of DNA sequences that were used, created a diversity of surfaces on the nanotubes. The diverse surfaces, in turn, attracted a range of proteins within a uterine lavage sample enriched with varying levels of ovarian cancer biomarkers.

The machine learning algorithm was trained using the data from the nanotube emission — the spectral signatures — to recognize the pattern of emission that signaled the presence and concentration of each biomarker. The nanotubes were functionalized with quantum defects, which essentially increased the diversity of responses the nanotubes would provide.

Source 

Topics:
Artificial Intelligence Medical Nanotechnology

More From SAE Media Group

Medical Design Briefs INSIDER
Artificial Intelligence Detects New Class of Mutations behind Autism
Related Article Image
Medical Design Briefs INSIDER
Biochip Combines AI and Nanoparticle Printing for Cancer Cell Analysis
Related Article Image
Medical Design Briefs INSIDER
Chip Simplifies COVID-19 Testing, Delivers Results on a Phone
Related Article Image
Medical Design Briefs
Personalized Medicine: The Role of Nanosensors in Disease Detection
Related Article Image