TUESDAY, Dec. 4, 2018 — Noninvasive diagnostic imaging using machine-learning analysis of nanoresolution images of cell surfaces can detect bladder cancer with high diagnostic accuracy, according to research published online Dec. 3 in the Proceedings of the National Academy of Sciences.
Igor Sokolov, Ph.D., from Tufts University in Medford, Massachusetts, and colleagues report on a diagnostic imaging approach based on nanoscale-resolution scanning of surfaces of cells collected from body fluids using a modality of atomic force microscopy (AFM), subresonance tapping, and machine-learning analysis. The surface parameters were used to classify cells. The method was applied to bladder cancer detection.
The researchers found that when examining five cells per patient urine sample, the method showed 94 percent diagnostic accuracy, which was a statistically significant improvement compared with the currently used clinical standard, cystoscopy (P < 0.05). The results were verified in 43 control and 25 bladder cancer patients.
“Our approach is based on the premises of field carcinogenesis, which has been established as a common event in many malignancies; in particular, in bladder cancer, in which both genetic and exogenous milieu risk factors lead not only to a localized tumor but may affect the entire organ area,” the authors write. “Our results provide evidence that the described method is sufficiently sensitive to detect this cancer signature.”
Tufts University has applied for a patent protection for the AFM machine-learning method described in the paper, which was invented by two of the authors.
Abstract/Full Text (subscription or payment may be required
Posted: December 2018
Source: Read Full Article