• Corpus ID: 231419022

Predicting Semen Motility using three-dimensional Convolutional Neural Networks

  title={Predicting Semen Motility using three-dimensional Convolutional Neural Networks},
  author={Priyansi and Biswaroop Bhattacharjee and Junaid Rahim},
Manual and computer aided methods to perform semen analysis are time-consuming, requires extensive training and prone to human error. The use of classical machine learning and deep learning based methods using videos to perform semen analysis have yielded good results. The state-of-the-art method uses regular convolutional neural networks to perform quality assessments on a video of the provided sample. In this paper we propose an improved deep learning based approach using three-dimensional… 

Figures from this paper


VISEM: a multimodal video dataset of human spermatozoa
This dataset paper is a multi-modal dataset containing different data sources such as videos, biological analysis data, and participant data that is the first dataset of that kind in the field of human reproduction.
The future of computer-aided sperm analysis
Specific requirements for validating CASA technology as a semi-automated system for human semen analysis are provided, with particular reference to the accuracy and uncertainty of measurement expected of a robust medical laboratory test for implementation in clinical laboratories operating according to modern accreditation standards.
Array programming with NumPy
How a few fundamental array concepts lead to a simple and powerful programming paradigm for organizing, exploring and analysing scientific data is reviewed.
Sperm Detection and Tracking in Phase-Contrast Microscopy Image Sequences using Deep Learning and Modified CSR-DCF
RetinaNet, a deep fully convolutional neural network is used as the object detector for sperm detection and tracking, and this method has shown excellent results in sperm tracking even in high-density sperm samples, occlusions, sperm colliding, and when sperms exit from a frame and re-enter in the next frames.
Extracting Temporal Features into a Spatial Domain Using Autoencoders for Sperm Video Analysis
The accuracy of the predicted motility of a given semen sample shows that a deep learning-based model can capture the temporal information of microscopic recordings of human semen.
Machine Learning-Based Analysis of Sperm Videos and Participant Data for Male Fertility Prediction
Modern and classical machine learning techniques are used together with a dataset consisting of 85 videos of human semen samples and related participant data to automatically predict sperm motility to indicate that sperm motilty prediction based on deep learning using sperm motilities videos is rapid to perform and consistent.
Stacked dense optical flows and dropout layers to predict sperm motility and morphology
The method which had an additional multi-layer perceptron with dropout layers, shows the best results when the inputs consist of both dense optical flows and an original frame of videos.
Automatic Tracking and Motility Analysis of Human Sperm in Time-Lapse Images
An image processing method, based on radar tracking algorithms, that detects and tracks automatically the swimming paths of human sperm cells in timelapse microscopy image sequences of the kind that is analyzed by fertility clinics and provides medical practitioners and researchers with more useful data than are currently available.
Deep Residual Learning for Image Recognition
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
Adam: A Method for Stochastic Optimization
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.