Dataset Information

Vision-based egg quality prediction in Pacific bluefin tuna (Thunnus orientalis) by deep neural network.

ABSTRACT: Closed-cycle aquaculture using hatchery produced seed stocks is vital to the sustainability of endangered species such as Pacific bluefin tuna (Thunnus orientalis) because this aquaculture system does not depend on aquaculture seeds collected from the wild. High egg quality promotes efficient aquaculture production by improving hatch rates and subsequent growth and survival of hatched larvae. In this study, we investigate the possibility of a simple, low-cost, and accurate egg quality prediction system based only on photographic images using deep neural networks. We photographed individual eggs immediately after spawning and assessed their qualities, i.e., whether they hatched normally and how many days larvae survived without feeding. The proposed system predicted normally hatching eggs with higher accuracy than human experts. It was also successful in predicting which eggs would produce longer-surviving larvae. We also analyzed the image aspects that contributed to the prediction to discover important egg features. Our results suggest the applicability of deep learning techniques to efficient egg quality prediction, and analysis of early developmental stages of development.

SUBMITTER: Ienaga N

PROVIDER: S-EPMC7804258 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Vision-based egg quality prediction in Pacific bluefin tuna (Thunnus orientalis) by deep neural network.

Ienaga Naoto N Higuchi Kentaro K Takashi Toshinori T Gen Koichiro K Tsuda Koji K Terayama Kei K

Scientific reports 20210112 1

Closed-cycle aquaculture using hatchery produced seed stocks is vital to the sustainability of endangered species such as Pacific bluefin tuna (Thunnus orientalis) because this aquaculture system does not depend on aquaculture seeds collected from the wild. High egg quality promotes efficient aquaculture production by improving hatch rates and subsequent growth and survival of hatched larvae. In this study, we investigate the possibility of a simple, low-cost, and accurate egg quality prediction ...[more]

PMID: 33436861

Similar Datasets

Project description:BackgroundThe Pacific bluefin tuna (Thunnus orientalis) is a regionally endothermic fish that maintains temperatures in their swimming musculature, eyes, brain and viscera above that of the ambient water. Within their skeletal muscle, a thermal gradient exists, with deep muscles, close to the backbone, operating at elevated temperatures compared to superficial muscles near the skin. Their heart, by contrast, operates at ambient temperature, which in bluefin tunas can range widely. Cardiac function in tunas reduces in cold waters, yet the heart must continue to supply blood for metabolically demanding endothermic tissues. Physiological studies indicate Pacific bluefin tuna have an elevated cardiac capacity and increased cold-tolerance compared to warm-water tuna species, primarily enabled by increased capacity for sarcoplasmic reticulum calcium cycling within the cardiac muscles.ResultsHere, we compare tissue-specific gene-expression profiles of different cardiac and skeletal muscle tissues in Pacific bluefin tuna. There was little difference in the overall expression of calcium-cycling and cardiac contraction pathways between atrium and ventricle. However, expression of a key sarcoplasmic reticulum calcium-cycling gene, SERCA2b, which plays a key role maintaining intracellular calcium stores, was higher in atrium than ventricle. Expression of genes involved in aerobic metabolism and cardiac contraction were higher in the ventricle than atrium. The two morphologically distinct tissues that derive the ventricle, spongy and compact myocardium, had near-identical levels of gene expression. More genes had higher expression in the cool, superficial muscle than in the warm, deep muscle in both the aerobic red muscle (slow-twitch) and anaerobic white muscle (fast-twitch), suggesting thermal compensation.ConclusionsWe find evidence of widespread transcriptomic differences between the Pacific tuna ventricle and atrium, with potentially higher rates of calcium cycling in the atrium associated with the higher expression of SERCA2b compared to the ventricle. We find no evidence that genes associated with thermogenesis are upregulated in the deep, warm muscle compared to superficial, cool muscle. Heat generation may be enabled by by the high aerobic capacity of bluefin tuna red muscle.

Dataset Information

Vision-based egg quality prediction in Pacific bluefin tuna (Thunnus orientalis) by deep neural network.

Publications

Vision-based egg quality prediction in Pacific bluefin tuna (Thunnus orientalis) by deep neural network.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets