Automated image analysis as a tool to measure individualised growth and population structure in Chinook salmon (Oncorhynchus tshawytscha)

• Published in: Aquaculture, fish and fisheries Vol. 2; no. 5; pp. 402 - 413
• Main Authors: Tuckey, Nicholas P. L., Ashton, David T., Li, Jiakai, Lin, Harris T., Walker, Seumas P., Symonds, Jane E., Wellenreuther, Maren
• Format: Journal Article
• Language: English
• Published: Sydney John Wiley & Sons, Inc 01.10.2022; Wiley
• Subjects: Accuracy; Anesthesia; Aquaculture; Automation; Breeding; breeding programme; Cameras; Computer vision; Data collection; Digital imaging; Food quality; Genotypes; growth; Identification systems; Image analysis; Image processing; Image quality; Machine vision; morphometric software; Oncorhynchus tshawytscha; Phenotypes; Population changes; population dynamics; Population structure; Population studies; Programming languages; Python; Salmon; Selective breeding; Software; Subpopulations; Tracking; Weight; New Zealand; Beijing China; United States > US; China
• ISSN: 2693-8847; 2693-8847
• DOI: 10.1002/aff2.66

Selective breeding programmes depend on high‐quality measurements of phenotype and genotype with repeated individualised phenotype measurements throughout the life cycle being optimal. Recent advances in electronics and computer vision technologies offer opportunities to improve both the quality, quantity and individualisation of repeated phenotypic measurements, but remain underutilised in aquaculture breeding programmes. In this study, we compare manual measurements of phenotypic traits of Chinook salmon (Oncorhynchus tshawytscha) with digital images and an automated software analysis pipeline written in the Python® programming language using the OpenCV machine vision library. Manual measurements of length, girth and weight of passive integrated transponder‐tagged individuals were compared with image‐based measures of 738 individuals over a time span from June–December 2019. Linear regressions showed strong correlations between manual and automated measurements for fork length, girth and weight (R2 = 0.989, R2 = 0.918, R2 = 0.987, respectively). Image‐based software measurements proved powerful for tracking general population changes in growth over the study period while retaining insights about subpopulations deviating from the average (e.g. losing weight). Taken together, our study demonstrates that image‐analysis can be used to estimate fish growth traits with a high degree of precision, requires reduced labour and demonstrates that additional knowledge can be gained through tracking individuals throughout production to harvest. Graphical A design for a simple image capture and automated software analysis pipeline for fish phenotypic measurements is presented in which measurements of Chinook salmon body weight, length and girth derived from automated image‐analysis were modelled and validated against manual measurements. Population structure and growth derived from automated image‐analysis measurements was shown to be comparable to that produced from manual measurements. Furthermore, individualising growth data was effective in highlighting an otherwise concealed sub‐population that lost body mass between October and December 2019.