Determination of annual reproductive cycle in male sterlet, Acipenser ruthenus using histology and ultrasound imaging

A practical evaluation of machine learning for classification of ultrasound images of ovarian development in channel catfish (Ictalurus punctatus)

Machine learning is a powerful tool to improve efficiency of industrial processes, but it has not yet been well utilized in aquacultural and hatchery applications. The goal of the present study was to evaluate the feasibility of using a broad array of machine learning approaches (testing of > 200 vectorization and model combinations, reporting on 20) to classify ultrasound images spanning annual ovarian development (i.e., from undeveloped to mature) of channel catfish (Ictalurus punctatus). The specific objectives were to: 1) establish dataset preprocessing to standardize image features; 2) develop and train image classification models with deep learning methods; 3) develop and train models with traditional machine learning methods; 4) compare performance of deep learning and traditional methods on two classification problems (2-class and 5-class), and 5) propose insights to deploy models in practical aquaculture applications for research and hatchery use. A total of 931 ultrasound images of catfish ovaries were used to train and evaluate models for a 2-class problem (as a 'yes' or 'no' answer) to support hormone-injection decisions for spawning management in hatcheries, and a 5-class problem for classifying gonadal development stages for research. By using feature extraction, cropping, dimension reduction, and histogram normalization, a preprocessing method was created to standardize images to develop traditional (i.e., vector input), and deep learning convolutional neural network (CNN) (i.e., image input) approaches. Traditional machine learning models with image classification achieved 100% median accuracy on the 2-class problem (with the models RN-50 and RN-152), and 96% median accuracy for the 5-class problem (with VGG-19 image vectorization). The deep learning approach for the 2-class problem had a median accuracy of > 98% for 15models. The 5-class deep learning models produced a steady increase in median accuracy with training net size, achievable through expansion of the dataset. These models can be developed further, but traditional models (using CNN architectures to simply calculate image vectors) outperformed the deep learning approach. These models can be directly applicable to aquaculture in hatcheries and reproductive biology research, in addition to a wide variety of other image-based applications.

Influence of Environmental Temperature and Hormonal Stimulation on the In Vitro Sperm Maturation in Sterlet Acipenser ruthenus in Advance of the Spawning Season

Simple Summary

Sperm maturation (acquisition of the potential for motility and fertilization by morphologically developed spermatozoa) in sturgeons is atypical of ray-finned fishes: it occurs outside the testes during the transit of testicular spermatozoa through the kidneys into the Wolffian ducts. We recently developed a method in which testicular spermatozoa of sterlet Acipenser ruthenus are matured in vitro when incubated in seminal fluid derived from Wolffian duct sperm. In this study, we explored whether in vitro maturation of testicular spermatozoa depends on the environmental temperature and/or hormonal stimulation of spermiation. We studied spermatozoa motility parameters after in vitro maturation of testicular sperm, concentrations of sex steroid hormones and testis morphology in sterlet males at different stages of male preparation for spawning with and without hormonal induction of spermiation. The obtained data suggest that the ability of testicular spermatozoa to be matured was not related to the environmental temperature, while hormonal stimulation was an absolute requirement for optimal in vitro maturation. The use of in vitro matured testicular spermatozoa might have considerable potential in aquaculture or conservation programs, which can be realized in cases of accidental death of valuable broodstock or failure to obtain Wolffian duct sperm of high quality.

Abstract

Sturgeon sperm maturation occurs outside the testes during the transit of testicular spermatozoa (TS) through the kidneys and the Wolffian ducts. A method of in vitro TS maturation in sterlet Acipenser ruthenus was used to investigate the effects of temperature and hormonal stimulation of spermiation on the ability of TS to complete this process. Spermatozoa motility parameters after in vitro maturation of testicular sperm, concentrations of sex steroid hormones and testis morphology were studied in three groups of sterlet: (1) after overwintering in ponds (OW), (2) adapted to spawning temperature (ST), and (3) adapted to spawning temperature with hormonal induction of spermiation (ST-HI). Blood plasma concentrations of testosterone, 11-ketotestosterone and 17,20β-dihydroxy-pregnenolone increased significantly after hormonal induction of spermiation (group ST-HI). In all groups, TS were not motile. After in vitro sperm maturation, motility was up to 60% only in group ST-HI. The data suggest that the ability of TS to be matured in vitro was not related to the environmental temperature, while hormonal stimulation of spermiation during the spawning season was an absolute requirement for optimal in vitro maturation.