Quantification of human sperm concentration using machine learning-based spectrophotometry

摘要: Abstract Spectrophotometry is an indirect non-invasive and quantitative method for specifying materials with unknown contents based on absorption behavior. This paper presents the first application of artificial neural network in spectrophotometry quantification human sperm concentration. A well-trained full spectrum (FSNN) model developed by examining response samples from 41 subjects to different light spectra (wavelength 390 1100 nm). It shown that this FSNN accurately estimates concentration over 93% prediction accuracy, provides 100% agreement clinical assessments differentiating healthy donor patient samples. We suggest machine learning-based approach trained as a rapid, low-cost, powerful technique quantify The performance superior available methods currently used semen analysis will provide novel research opportunities tackling male infertility.