Sperm Abnormality Detection Using Sequential Deep Neural Network

Sperm morphological analysis (SMA) is an essential step in diagnosing male infertility. Using images of human sperm cells, this research proposes a unique sequential deep-learning method to detect abnormalities semen samples. The proposed technique identifies and examines several components sperm. In order conduct study, we used the online Modified Human Morphology Analysis (MHSMA) dataset containing 1540 collected from 235 infertile individuals. For purposes, freely available online. To identify different parts sperm, such as head, vacuole, acrosome, deep neural network (SDNN) architecture. This also particularly effective with low-resolution, unstained images. Sequential networks (SDNNs) demonstrate high accuracy based on given our tests benchmark. Our algorithm successfully detected vacuole 89%, 90%, 92%, respectively. It noteworthy that system detects acrosome head greater than current state-of-the-art approaches suggested On low-specification computer/laptop, requires less execution time. Additionally, it can classify photos real Based results embryologist quickly decide whether use