Noninvasive diagnostic imaging using machine-learning analysis of nanoresolution images of cell surfaces: Detection of bladder cancer

Abstract

We report an approach in diagnostic imaging based on nanoscale-resolution scanning of surfaces of cells collected from body fluids using a recent modality of atomic force microscopy (AFM), subresonance tapping, and machine-leaning analysis. The surface parameters, which are typically used in engineering to describe surfaces, are used to classify cells. The method is applied to the detection of bladder cancer, which is one of the most common human malignancies and the most expensive cancer to treat. The frequent visual examinations of bladder (cytoscopy) required for follow-up are not only uncomfortable for the patient but a serious cost for the health care system. Our method addresses an unmet need in noninvasive and accurate detection of bladder cancer, which may eliminate unnecessary and expensive cystoscopies. The method, which evaluates cells collected from urine, shows 94% diagnostic accuracy when examining five cells per patient’s urine sample. It is a statistically significant improvement (P < 0.05) in diagnostic accuracy compared with the currently used clinical standard, cystoscopy, as verified on 43 control and 25 bladder cancer patients.

Nanomechanical mapping of soft materials with the atomic force microscope: methods, theory and applications

“…The potential of big data analysis and machine learning algorithms in AFM and force spectroscopy remains largely unexplored. [357][358][359][360] High-speed nanomechanical mapping will generate large data files that will require the use of optimized processing tools. At the same time, many technological and biomedical applications will demand the automatization of AFM imaging.…”

Marine Objects Recognition Using Convolutional Neural Networks

“…In recent years, image recognition techniques have become commonly used techniques in a wide spectrum of science and technology [12] [13]. Image recognition techniques are used in fi elds of medicine [14] [15], agriculture [16] [17], traffi c [18] etc. The most used AI algorithm for tasks of image recognition and computer vision is CNN [19].…”

Potential of infrared microscopy to differentiate between dementia with Lewy bodies and Alzheimer’s diseases using peripheral blood samples and machine learning algorithms

“…We considered a binary classification problem with spectra from blood components being grouped based on their categories as dementias or controls using SVM and RF. 51,55,56,58,59 For this analysis, we focused on the low-wavenumber spectral region (950 to 1760 cm −1 ); LOGOCV was used for the optimization of the parameters of the classifiers and estimation of their performances.…”

“…The RF's decision trees were constructed based on different training subsets chosen randomly from the original data (training data), with replacement, using a bootstrap sample. 58,59 The reduced dimension trees (classifiers) were used to determine the category of the validation spectra; thus the prediction is more accurate.…”