IMAFISH_ML: A fully-automated image analysis software for assessing fish morphometric traits on gilthead seabream (Sparus aurata L.), meagre (Argyrosomus regius) and red porgy (Pagrus pagrus)

Navarro, Ana; Lee-Montero, Ivonne; Santana, Dulce; Henríquez, Patricia; Ferrer, Miguel A.; Morales, A.E.; Soula, Mohamed; Badilla, Rodrigo; Negrín-Báez, Davinia; Zamorano, M. J.; Afonso, Juan Manuel

doi:10.1016/j.compag.2015.11.015

Cited by 34 publications

(28 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All animals were handled under strict biosecurity measures to avoid virus propagation in the facilities. All animals were photographed individually using a Canon EOs1300D camera following the methodology previously established in PROGENSA ® [19]. Then, animals were weighted and individually frozen at −20 • C for later tissue sampling.…”

Section: Data Collection and Image Analysismentioning

confidence: 99%

“…LCDV outbreaks are recurrently observed every year and, occasionally, associated with high mortalities [3,15]. Currently, most ongoing genetic programs for this species are mostly focused on the improvement of growth, morphology and carcass quality [16][17][18][19]. Genetic estimates for disease resistance were only reported for the bacterial pathogen Photobacterium damselae subsp.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Heritability Estimates and Genetic Correlation for Growth Traits and LCDV Susceptibility in Gilthead Sea Bream (Sparus aurata)

Carballo

Shin

Berbel

et al. 2019

Fishes

View full text Add to dashboard Cite

The lymphocystis disease (LCD) is a viral infection with a high economic impact in gilthead sea bream aquaculture. In this study, genetic estimates associated with lymphocystis disease virus (LCDV) disease susceptibility and growth were determined in sea bream juveniles. Two fish batches (named batch 1 and batch 2) were built from mass spawning and reared under industrial conditions until disease outbreak. At the moment of the sampling (n = 500 specimens for each batch), all animals had the typical LCDV lesions in the skin. For phenotyping, animals were weighted and photographed for image analysis (surface covered and lesion intensity). LCDV DNA copies were quantified in the liver by qPCR. Batch 1 had a higher surface covered and lesion intensity than batch 2, and the body caudal region was the lowest affected region in both batches. The average LCDV DNA copies in liver were higher in the batch 1 than batch 2, and they were positively correlated with severity index (SI) categories (r2 = 0.90–0.94). The total number of families evaluated were 150 and 128 for batch 1 and batch 2, respectively, with a high bias in offspring contribution by family and broodstock. Heritabilities for weight and length were 0.18 and 0.14 in batch 1 and 0.06 and 0.05 in batch 2, respectively. Heritability for the number of viral DNA copies was low (<0.08) in both batches. Heritabilities for SI in binary scale were 0.32/0.33 and 0.21/0.24 (underlying liability/Bayesian approach) for batch 1 and batch 2, respectively. Genetic correlations were very high and positive when growth traits (weight and length) or disease traits (LCDV DNA copies and SI) were compared. In contrast, the genetic correlations between growth and disease traits were moderate–high and positive in the batch 1 but negative in batch 2. These results indicate the genetic selection for LCDV susceptibility and growth is feasible in sea bream juveniles, although estimates are highly dependent on the age. The information provided is relevant to designing selective breeding programs in sea bream.

show abstract

Section: Data Collection and Image Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Heritability Estimates and Genetic Correlation for Growth Traits and LCDV Susceptibility in Gilthead Sea Bream (Sparus aurata)

Carballo

Shin

Berbel

et al. 2019

Fishes

View full text Add to dashboard Cite

show abstract

“…Information about the full dataset and culture conditions was previously reported [13]. Fish were individually weighted (W) using Gram FC-200 and a photograph was taken using a Canon EOs1300D camera following the methodology previously established in PROGENSA ® [19]. Image analysis was carried out using the Fiji 2.0.0-rc-69/1.52p and standard length (SL), body height at the insertion of the pectoral fin (BHP), body maximum height (BMH) and caudal peduncle height (CPH) were measured (Figure 1).…”

Section: Animalsmentioning

confidence: 99%

Genetic Estimates for Growth and Shape-Related Traits in the Flatfish Senegalese Sole

Guerrero-Cózar

Jiménez-Fernández

Berbel

et al. 2021

Animals

View full text Add to dashboard Cite

Shape quality is very important in flatfish aquaculture due to the impact on commercialization. The Senegalese sole (Solea senegalensis) is a valuable flatfish with a highly elliptic body that slightly changes with age and size, and it is prone to accumulating malformations during the production cycle. The present study aims to investigate the genetic parameters of two growth traits (weight and standard length) and six shape quality predictors (ellipticity, three body heights (body height at the pectoral fin base [BHP], body maximum height [BMH] and caudal peduncle height [CPH]) and two ratios (BMH/BHP and BMH/CPH)). These traits were measured before the on-growing stage (age ~400 days (d)) and at harvest (~800 d). Phenotypic data, heritabilities and genetic and phenotypic correlations between the traits are presented and discussed. High or very high heritabilities (0.433–0.774) were found for growth traits, body heights and ellipticity and they were higher at 400 than 800 d. In contrast, the ratios of BMH/BHP and BMH/CPH were less heritable (0.144–0.306). Positive and very high (>0.95) correlations between growth traits and the three heights were found and decreased with age. In contrast, ellipticity had negative and medium-high genetic correlations with growth traits and heights, indicating fish selected for bigger size would also become rounder. The ratio of BMH/CPH showed low genetic correlations with all traits and provided complementary information to ellipticity for a better fitting to the expected lanceolate body morphology of sole. The genetic correlations for all traits at both ages were very high, indicating that selection before entering the growth-out stage in recirculation aquaculture systems is recommended to accelerate genetic gains.

show abstract

“…Successful underwater application of PR has been performed for specific use cases. Fish were classified by a deep neural network 15 and by manually tuning shape features 16 . Nematode biomass was assessed by manually tuning intensity thresholds 17 and scallop abundance has been quantified using Adaboost 18 .…”

Section: Introductionmentioning

confidence: 99%

Compact-Morphology-based poly-metallic Nodule Delineation

Schoening

Jones

Greinert

2017

Sci Rep

View full text Add to dashboard Cite

1Poly-metallic nodules are a marine resource considered for deep sea mining. Assessing nodule abundance is of interest for mining companies and to monitor potential environmental impact. Optical seafloor imaging allows quantifying poly-metallic nodule abundance at spatial scales from centimetres to square kilometres. Towed cameras and diving robots acquire high-resolution imagery that allow detecting individual nodules and measure their sizes. Spatial abundance statistics can be computed from these size measurements, providing e.g. seafloor coverage in percent and the nodule size distribution. Detecting nodules requires segmentation of nodule pixels from pixels showing sediment background. Semi-supervised pattern recognition has been proposed to automate this task. Existing nodule segmentation algorithms employ machine learning that trains a classifier to segment the nodules in a high-dimensional feature space. Here, a rapid nodule segmentation algorithm is presented. It omits computation-intense feature-based classification and employs image processing only. It exploits a nodule compactness heuristic to delineate individual nodules. Complex machine learning methods are avoided to keep the algorithm simple and fast. The algorithm has successfully been applied to different image datasets. These data sets were acquired by different cameras, camera platforms and in varying illumination conditions. Their successful analysis shows the broad applicability of the proposed method.Poly-metallic nodules (PMNs -also referred to as manganese nodules) are a marine mineral resource. They contain relevant concentrations of Copper, Nickel and Cobalt 1 . Most PMN research and resource assessment focusses on the deep abyssal plains in the eastern Pacific Ocean. Economically interesting areas were found within the Clarion Clipperton Zone (CCZ) where several countries are exploring PMN claims. These are license areas provided to the countries through the International Seabed Authority.International research projects are investigating aspects of nodule mining (Ecological Aspects of Deep-Sea Mining: https://jpio-miningimpact.geomar.de; Managing Impacts of Deep-Sea Resource Exploitation: https://www.eu-midas.net/). Current foci of these research projects lie on environmental aspects: e.g. epifauna associated with PMNs, mining-induced habitat disturbances and the resilience of the ecosystem to cope with this anthropogenic pressure 2,3 . Quantitative measurements of PMN abundance are required for various applications. Individual nodule sizes (in cm 2 ) provide basic measurements that can be aggregated to create descriptive spatial statistics. Examples are PMN density (nodules/m 2 ) and seafloor coverage (in %) that data can related to environmental parameters, like faunal densities or chemical gradients.Quantitative nodule information is traditionally provided by two methods. First, by physical sea floor sampling, e.g. using box cores. Second, by hydro-acoustic sensors, e.g. Multi-beam Echo Sounder (MBES) or Side Scan Sonar (SSS). Physi...

show abstract

IMAFISH_ML: A fully-automated image analysis software for assessing fish morphometric traits on gilthead seabream (Sparus aurata L.), meagre (Argyrosomus regius) and red porgy (Pagrus pagrus)

Cited by 34 publications

References 42 publications

Heritability Estimates and Genetic Correlation for Growth Traits and LCDV Susceptibility in Gilthead Sea Bream (Sparus aurata)

Heritability Estimates and Genetic Correlation for Growth Traits and LCDV Susceptibility in Gilthead Sea Bream (Sparus aurata)

Genetic Estimates for Growth and Shape-Related Traits in the Flatfish Senegalese Sole

Compact-Morphology-based poly-metallic Nodule Delineation

Contact Info

Product

Resources

About