Supervised learning for semantic segmentation of human spermatozoa

FELIX THOMSEN; CLAUDIO DELRIEUX; NATALIA REVOLLO; ROLANDO GONZÁLEZ-JOSÉ

SPIE

SPIE

Año: 2020

0277-786X

Image-based diagnosis is able to spot several diseases and clinical conditions faster and more accurately thantraditional manual ones, becoming also an alternative in monitoring and predicting patients responses to specifichealth treatments. In this work, we present a supervised learning approach to segment pixel-wise parts ofspermatozoa using a random forest (RF) classifier. The framework created a multi-channel image combiningintensity RGB bands with three neighborhood based bands. The last neighborhood based bands were Sobel?smagnitude and orientation and Shannon?s entropy. A RF was trained using labeled pixels provided by expertandrologists, biochemists and specialists in reproductive health. We compared results with a simple model onthe RGB only. The whole automatic process (segmentation and classification) achieved an average precision of98%, recall of 98% and F-Score of 98%. Highest improvement in comparison to the RGB model was shown on thesegmentation of the tail. We provided a fully automatic spermatozoa semantic segmentation based on local andnon-local information. The results are aimed to develop a CASA (Computer Assisted Sperm Analysis) systemthat can provide results over the Internet. The experiment was conducted on normalized images of a specificmicroscope. We are planning to extend the experiment in future work to more realistic conditions includingdifferent stainings, microscopes and resolutions.