Adaptive Texture Description and Estimation of the Class Prior Probabilities for Seminal Quality Control

Abstract

Motivation of the Thesis Semen quality assessment is a crucial task in artificial insemination (AI) processes, both human and animal. Animal AI allows farmers to save time and money (e.g. working with a limited number of animals). They purchase semen samples to companies, which have to carry out strict quality controls to guarantee that they are optimal for fertilization. A sample with a high proportion of (i) dead spermatozoa, or (ii) sperm heads with damaged acrosomes (the acrosome is a membrane that covers the anterior part of the sperm head and makes possible the penetration into the ovum) will have low fertilization potential. Therefore, sperm vitality and acrosome integrity are two of the parameters assessed by veterinaries in semen quality control processes. Both are assessed by means of a visual process which entails expensive equipments (stains and fluorescence microscopes) and may be a source of errors, as any manual process is. The contributions in the field of Image Processing and Machine Learning made on this PhD. Thesis [2] may be used to develop an automatic process to assess the proportions of damaged acrosomes or dead spermatozoa using just a phase contrast microscope (which almost any lab has) and a digital camera. Concretely, several texture description approaches have been evaluated. In addition, a new intelligent segmentation process, an adaptive texture description method, and two robust approaches for estimating class proportions of unlabelled datasets have been proposed. All these methods are applied to automatic boar semen quality estimation.